Method for determining habitat descriptor value providing target biodegradability of polymer

Abstract

The present invention relates to a method for determining a habitat descriptor value providing a target biodegradability of a polymer. Targeted biodegradability indicative of biodegradation characteristics of the polymer is provided. A digital representation of the polymer is provided that is indicative of a physicochemical property of the polymer. Biodegradable habitats are provided that indicate habitat descriptors that affect polymer biodegradation. A biodegradation model is provided based on the provided biodegradation habitat, the biodegradation model being adapted to determine habitat descriptor values that allow biodegradation of the polymer that satisfies the target biodegradability in the biodegradation habitat. The habitat descriptor value for the polymer is determined based on the selected biodegradation model, the target biodegradability, and the polymer descriptor.

Description

Technical Field

[0001] The present invention relates to a method, an apparatus and a computer program product for determining a habitat descriptor value providing a target biodegradability of a predetermined polymer. Furthermore, the present invention relates to a training method, a training apparatus and a training computer program for training a data-driven biodegradation model that can be utilized by the method, the apparatus and the computer program product for determining a habitat descriptor value. Furthermore, the present invention relates to a method and an apparatus for providing an interface for determining a habitat descriptor value. Background Art

[0002] In general, polymers are widely used in products for industrial and / or daily use due to their wide range of application properties. The uses of polymers cover coatings, personal care products, detergents, lubricants, packaging and foams. However, on the other hand, this widespread application leads to a large amount of waste containing used polymers. Although it is actually the durability of polymers that makes them popular in many uses in most cases, it is this durability that leads to many problems in waste management, specifically because polymers are also durable in waste. In particular, if non-biodegradable polymers are not properly collected in the expected waste stream, this can lead to increased microplastic pollution and bioaccumulation in the environment. Therefore, not only polymers that will decompose are needed, but also knowledge about the biodegradability of polymers needs to be taken into account at an early stage of the product design process. In addition, for the subsequent waste management of products containing biodegradable polymers, it may also be important to know under which conditions the polymer will biodegrade optimally and under which conditions the polymer may not biodegrade. This allows the subsequent waste management of polymers to be considered already in the design process. Therefore, it would be advantageous to provide the possibility of accurately predicting the conditions under which the polymer will biodegrade in a computationally inexpensive manner. Summary of the invention

[0003] The object of the present invention is to provide a method, a device and a computer program product that allow accurate determination of the conditions under which a polymer will biodegrade, which method, device and computer program product are computationally inexpensive and can be robustly applied to new polymers. Furthermore, a further object of the present invention is to provide a training method, a training device and a computer program product that allow providing a biodegradation model that can be used in the method, device and computer program product and that can be trained to provide a good determination accuracy by utilizing fewer computing resources.

[0004] In a first aspect of the invention, a computer-implemented method is presented for determining a habitat descriptor value that provides a target biodegradability of a predetermined polymer, wherein the method comprises: a) providing a target biodegradability, wherein the biodegradability indicates a biodegradation characteristic of the polymer; b) providing a digital representation of the polymer that indicates a physicochemical characteristic of the polymer; c) providing a biodegradation habitat, wherein the biodegradation habitat indicates a habitat descriptor that affects biodegradation of the polymer in the corresponding habitat, wherein the habitat descriptor indicates an environmental characteristic of the habitat; d) providing a biodegradation model based on the provided biodegradation habitat, wherein the biodegradation model is suitable for determining a habitat descriptor value that allows biodegradation of the polymer that meets the target biodegradability in the biodegradation habitat, wherein the biodegradation model is a data-driven model parameterized with respect to the biodegradation habitat such that it determines a habitat descriptor value based on the target biodegradability and the physicochemical characteristic; and e) determining a habitat descriptor value for the polymer based on the selected biodegradation model, the target biodegradability, and the polymer descriptor.

[0005] Since the biodegradation model is particularly suitable for determining habitat descriptor values ​​that allow biodegradation of a polymer that meets a target biodegradability in the respective habitat, the habitat descriptor values ​​for the respective habitat can be determined very accurately. Furthermore, since the biodegradation model is specifically trained for one or more specific biodegradation habitats, the training data necessary for training becomes less and the biodegradation model becomes more flexible in determining the biodegradation of new polymers that are not part of the training data set. Thus, the method allows accurate determination of habitat descriptor values ​​that is not only computationally inexpensive but can also be flexibly applied to new polymers.

[0006] Furthermore, since the physicochemical properties containing physicochemical information of the polymers are utilized, for example, quantum chemical information of the polymers, such as solubility or molar mass of the polymers in water and octanol, the training of the corresponding biodegradation models can be improved. Specifically, the utilization of physicochemical properties allows for the training of such models with less training data, since some of the relevant information that needs to be learned is already presented to the model by using the physicochemical properties. This further allows for the saving of tests and experiments required to provide the training data set.

[0007] The method refers to a computer-implemented method and can therefore be performed by a general or special purpose computer suitable for implementing the method, for example by running a corresponding computer program. The method is suitable for determining, in particular predicting, a habitat value for a predetermined polymer, which habitat value allows the predetermined polymer to be biodegraded with a predetermined target biodegradability. A biodegradable polymer refers to a polymer that can be degraded by a biological process, in particular, a biodegradable polymer can refer to a polymer that can be assimilated by bacteria and / or fungi to produce an environmentally friendly product, i.e., decomposed into non-polluting residues, for example by producing mineralized carbon and / or biomass. In general, the determined habitat descriptor value can refer to one or more quantifications of the environmental characteristics of the habitat. For example, a habitat descriptor value can refer to only one value, such as the salt concentration in the corresponding habitat, or can refer to more than one value, for example, can refer to a range of values, such as a range of salt concentrations.

[0008] In general, biodegradability indicates the biodegradability characteristics of a polymer. Specifically, biodegradability refers to a measure of degradation, i.e., the decomposition of a polymer caused by a biological process, i.e., a process involving biological materials, particularly microorganisms, that participate in the degradation process. Therefore, biodegradability does not refer to a purely chemical degradation process that does not include microbial activity. Target biodegradability may refer to any quantification of the biodegradability of a polymer. Biodegradability is an intrinsic property of a polymer. In this context, the intrinsic property of a polymer refers to the properties of a polymer that are caused by the properties of the polymer (i.e., its structure, composition, etc.) and therefore reflect the properties of the polymer, with respect to a specific context. Specifically, when present in a specific biologically active environment, biodegradability reflects the properties of a polymer. For example, target biodegradability may refer to only one value, such as the half-life of a polymer in a corresponding habitat, or may refer to more than one value, such as the degradation function of a polymer over time in a specific habitat. Preferably, the target biodegradability of a polymer refers to any one of the mineralization properties, biotransformation properties, and / or decomposition half-life of a polymer. Preferably, biodegradability refers to the biodegradation percentage value after a predetermined period of time. Furthermore, biodegradation is a technological property of polymers, i.e., the knowledge of polymer biodegradation strongly influences the technological applicability and utilization of polymers.

[0009] In general, polymer can be any polymer. Preferably, the target polymer is a synthetic polymer. In an embodiment, a synthetic polymer can be a compound produced by chemical production from one or more starting materials (such as monomers) and comprising at least two monomer units. The monomer unit can be regarded as a subunit of a polymer. The polymer can be prepared from monomers by commonly known polymerization techniques. The polymer can be produced from a single type of monomer or from different monomers. The polymer can be produced by a single polymerization technique or by a combination of different polymerization techniques. The monomer units can be randomly distributed or can be present in the polymer as blocks. The polymer can be a linear polymer. The polymer can be a branched polymer. The polymer can be a cross-linked polymer. The polymer can be chemically modified after polymerization.

[0010] In a first step, the method includes providing a target biodegradability indicating the biodegradability characteristics of the polymer. Specifically, providing may refer to receiving the target biodegradability from an input of a user using, for example, a corresponding input unit. In addition, providing may also refer to accessing a storage unit in which the target biodegradability has been stored. In addition, the providing may also include receiving the target biodegradability from other sources, for example via a network connection, and providing the received biodegradability. In general, the target biodegradability may refer to a target value, such as a target half-life of a polymer in a specific habitat, or may refer to a range of values ​​that a polymer should meet in a specific habitat. In addition, the target biodegradability may also refer to any type of objective function, for example, a timely sequence of biodegradation. For example, the target biodegradability may indicate that a polymer should have a first range of biodegradability values ​​during a first time range, and then should have a second range of target biodegradability values ​​during a subsequent time range. Such more complex target biodegradability may be advantageous in situations where, for example, habitat descriptor values ​​may vary in a habitat due to timely changes in the environment (such as day / night changes) or due to control of habitat descriptors (such as in a chemical reactor).

[0011] In addition, the method includes providing a digital representation of a polymer indicating the physicochemical properties of the polymer. Specifically, providing may refer to receiving a digital representation from an input of a user using, for example, a corresponding input unit. In addition, providing may also refer to accessing a storage unit that has stored a digital representation. In addition, the providing may also include, for example, receiving physicochemical properties from other sources via a network connection, and providing the received physicochemical properties as a digital representation. Specifically, the physicochemical properties of the polymer may be quantified by a polymer physicochemical parameter. In addition, indicating the physicochemical properties of the polymer or being associated with the physicochemical properties of the polymer is defined as information that allows access to the physicochemical properties. For example, the digital representation may directly include the physicochemical properties, for example, in the form of a value of a corresponding amount. However, the digital representation may also be a link to the corresponding physicochemical properties, via which the physicochemical properties may be accessed, or the digital representation may refer to an identifier associated with the physicochemical properties, and allows access to the physicochemical properties using a corresponding search storage device. In addition, the digital representation may also refer to information that allows the use of one or more known relationships to derive the physicochemical properties. For example, the synthesis specification or structural formula of the polymer may be used as a digital representation, allowing the use of known chemical and physical laws and relationships to derive the corresponding physicochemical properties.

[0012] Generally speaking, throughout the following description, if not explicitly defined, reference to a parameter or characteristic includes reference to both the corresponding quantity and the specific value of the quantity. For example, a parameter that is a temperature always refers to the quantity that is the temperature, and also to the specific value of the temperature set for the quantity. Because in most cases the explicit value of a parameter may be different for different embodiments and applications, the value is usually not mentioned. However, providing a parameter or characteristic generally means providing the quantity, such as information that the value is the temperature, and the value of the quantity or characteristic itself.

[0013] Preferably, the digital representation includes polymer physicochemical parameters, preferably, polymer descriptors, wherein the polymer physicochemical parameters indicate the physicochemical properties of the polymer. Specifically, the polymer physicochemical parameters are indications of parameters that quantify the physicochemical properties of the polymer. In this context, the term "physicochemical properties" refers to the physical and / or chemical properties of the polymer. However, the digital representation can also be provided so that it allows the polymer physicochemical parameters to be derived, for example, by providing a representation of the polymer, whose corresponding polymer physicochemical parameters have been stored or can be determined, for example, by calculation of the corresponding polymer descriptors. Preferably, the digital representation refers to at least one of the formula, structural formula, trade name, IUPAC name, chemical identifier and CAS number of the polymer.

[0014] In a preferred embodiment, the polymer physicochemical parameter indicates a parameter for the physicochemical properties of a subgroup of a quantified polymer. In this embodiment, a digital representation can also be provided so that it allows the polymer physicochemical parameter to be derived by determining the subgroup of the polymer, and the polymer physicochemical parameter is determined based on the physicochemical properties of the determined subgroup. In general, a subgroup refers to a part of a polymer, wherein all subgroups of the polymer form a polymer together. For example, a subgroup may refer to a part of a polymer, wherein the subgroups are continuously linked together along a chain or network to form a polymer. Preferably, a subgroup of a polymer refers to a repeating unit describing a part of a polymer, and a complete polymer chain is produced when repeated. However, in some cases, a subgroup may also refer to a single part that is not repeated in a polymer. In addition, it is preferred that a subgroup includes a repeated part, for example, a subgroup of a polymer may include a repeating core that is also present in other subgroups and another additional part that is not present in other subgroups. Preferably, a subgroup refers to at least one of a polymerized monomer or an oligomer fragment. More preferably, a subgroup refers to a polymerized monomer. In this context, a polymerized monomer refers to a monomer after its polymerization, sometimes also referred to as a "monomer unit" or "monomer". Specifically, a polymerized monomer does not refer to a monomer present in a reaction mixture before polymerization, i.e., a raw material, but rather to a repeating unit derived from a monomer that has been changed during or after polymerization. Therefore, the subgroup descriptor determined for a polymerized monomer is different from the subgroup descriptor determined for an unreacted monomer before polymerization. The inventors have found that, in particular, polymerized monomers allow polymer descriptors to be determined from the subgroup descriptors of the polymerized monomers, which allows the determination model to accurately determine the habitat descriptor value of the polymer. In a preferred embodiment, the digital representation of the polymer includes a subgroup provided as a molecular model that indicates the chemical structure of the subgroup after polymerization. Even more preferably, the molecular model of the subgroup is determined in a manner suitable for quantum chemical calculations involving multiple atoms and their connectivity that represent the characteristics of the subgroup within the polymer. In addition, as an alternative to a subgroup molecular model that treats the subgroup as a monomer structure, a molecular model involving an oligomer model can also be utilized that takes into account the influence of the adjacent molecular structure of the subgroup in the polymer.

[0015] Generally speaking, if the digital representation of a polymer does not directly include the physicochemical parameters of the polymer, it is preferred to determine the physicochemical parameters of the polymer by determining a subgroup of the polymer. For example, the corresponding subgroup of the polymer can be determined using known methods. However, it is preferred that the determination of the subgroup of the polymer is performed according to the embodiment described later in the present invention. Specifically, it is preferred that the subgroup is determined so that between the atoms of different subgroups in the polymer, the bond is polarized as little as possible, and preferably has a bond order (e.g., CC single bond) as small as possible. In addition, it is preferred that the subgroup representing the polymer then includes the same number of active non-hydrogen atoms as the polymer. In addition to the active atoms, the subgroup may also contain additional atoms, which can be ignored during the calculation of the physicochemical parameters of the subgroup. In addition, it is preferred to determine the subgroup in such a way that the polymer including the part constructed with different polymerization techniques is well covered and meets the above conditions. An example is a polyether used as a component of polyurethane. In general, a database or archive with multiple reactions between polymer parts can be generated, and the subgroup can be derived from the corresponding structure of the reaction. For example, specific chemical substances such as SMILES and SMARTS can be used to easily derive the subgroup of the polymer. For example, a database of reaction SMARTS can be generated, and then based on the polymerization of the corresponding polymer, the corresponding reaction SMARTS can be selected. From the selected reaction SMARTS, the SMILES of the polymer monomers can be directly derived, for example, the SMILES, i.e., the number of atoms and connectivity of the subgroups, can be determined from the SMILES of the monomers using RDkit.

[0016] The determined polymer subgroups are associated with subgroup physicochemical parameters, which indicate parameters that quantify the physicochemical properties of the subgroups in the polymer. In particular, it is preferred that if the polymer physicochemical parameters are not directly provided by the digital representation, the polymer physicochemical parameters are determined by determining the corresponding subgroup physicochemical parameters for each subgroup in the subgroup, and the polymer physicochemical parameters are determined based on the subgroup physicochemical parameters of the subgroups, for example by averaging. Therefore, the method preferably includes first providing or determining subgroups of polymers from the digital representation of the polymer, then determining or providing subgroup physicochemical parameters of these subgroups, i.e., parameter values ​​that quantify the physicochemical properties, and then determining the physicochemical parameters of the polymer based on the subgroup physicochemical parameters of each polymer.

[0017] Preferably, polymer physicochemical parameters refer to at least one of composition descriptors, count descriptors, structural fragment lists, fingerprints, graphic invariants, 3D descriptors and / or higher dimensional descriptors, which indicate parameters that quantify polymer physicochemical properties. In a preferred embodiment, polymer physicochemical parameters refer to 3D descriptors, particularly quantum chemical descriptors. In addition, the inventors have found that, in particular, molar mass describes the biodegradation of polymers very accurately. Therefore, it is particularly preferred that the physicochemical parameters include the molar mass of the polymer. In general, polymer physicochemical parameters can be derived from subgroup physicochemical parameters, and therefore, subgroup physicochemical parameters can also refer to the same physicochemical parameters as described above. However, physicochemical parameters can also be derived without using subgroups, for example, by quantum chemical simulation of the entire polymer. In the following, possible physicochemical parameters are defined in more detail. In addition, in these cases, the defined physicochemical parameters can directly refer to polymer physicochemical parameters, or alternatively refer to subgroup physicochemical parameters.

[0018] Composition descriptors may refer to any of potential, average molecular weight, polydispersity, charge, spin, boiling point, melting point, enthalpy of fusion, dissociation constant, Hansen parameters, proton, polarity and dispersion contributions, Abraham parameters, retention index, TPSA, receptor binding constant, Michaelis constant, inhibitor constant, mutagenicity, LD50, bioconcentration, toxicity, biodegradation profile, and viscosity.

[0019] Count descriptors may refer to any of the sum of atomic electronegativity, the sum of atomic polarizabilities, the amount of components, the ratio of component amounts, the number of atoms and non-H atoms, the number of H, B, C, N, O, P, S, Hal and heavy atoms, the number of H-donor and H-acceptor atoms, the number of bonds, the number of non-H or multiple bonds, the number of double bonds, triple bonds and aromatic bonds, the number of functional groups, the ratio of functional groups, the sum of bond orders, the aromatic ratio, the number of rings or circuits, the number of unpaired electrons, the number of rotatable bonds, the rotatable bond fraction and the number of conformers.

[0020] Polymer descriptors related to a list of structural fragment descriptors may refer to at least one of a molecular fraction list, a functional group list, a bond list, and an atom list. Fingerprint descriptors preferably include MACCS keys, preferably in bit format or total format, Morgan and other circular fingerprints, preferably in bit format or total format, topological torsion, atom pairs, infrared and related spectra, fingerprint counts, PubChem fingerprints, substructure fingerprints, and at least one of Klekota-Roth fingerprints. Graphic invariants / topological index descriptors preferably include at least one of a topological structure index and a topological chemical index.

[0021] In a preferred embodiment, the polymer physicochemical parameters are 3D descriptors including at least one of total sum of total atomic volume, average volume per atom, total sum of atomic area, average area per atom, area of ​​all atoms, average area per atom, solvent accessible surface, dispersion energy, dielectric energy, H-donors, H-acceptors, polar and non-polar surface area, atomically resolved H-donors, H-acceptors, polar and non-polar surface area, shape, sphericity, dipole and higher moments, polarizability, dielectric energy, protons, polar and non-polar surface area, orbital energy and orbital gap, ionization energy, electron affinity, hardness, electronegativity, electrophilicity, excitation energy and intensity, infrared and ultraviolet absorption bands, reactivity measurements, redox potential, bond critical points, partial charge, charge surface area, atomic orbital contribution, bond order, atomic radius. In particular, it is preferred that the polymer physicochemical parameters refer to 3D descriptors including at least one of the sum of the volumes of all atoms, the average volume per atom, the sum of the areas of all atoms, the average area per atom, solvent accessible surface, dispersion energy, dielectric energy, H-donors, H-acceptors, polar and / or non-polar surface area, atomically resolved H-donors, H-acceptors, polar and / or non-polar surface area, shape, sphericity, cone angle, polarizability, dielectric energy, protons, polar and / or non-polar surface area, excitation energy and intensity, infrared and / or ultraviolet absorption bands, reactivity measurements, particle charge and / or charge surface area. Preferably, the higher dimensional descriptors used may include at least one of conformational partition function, solubility, vapor pressure, activity coefficient, diffusion coefficient, partition coefficient, interfacial activity, rotation constant, moment of inertia, radius of gyration, compositional drift of the polymer, density, viscosity, conformational weighted volume and area, conformational weighted H-donors, H-acceptors, protons, polar and / or non-polar surface area, charge distribution, conformational dipole moment, and molecular refraction. Preferably, higher dimensional descriptors are used, which include at least one of solubility, vapor pressure and activity coefficient, interfacial activity, conformational weighted H-donors, H-acceptors, protons, polar and non-polar surface area, and charge distribution.

[0022] The method also includes providing a biodegradation habitat, wherein the biodegradation habitat indicates a habitat descriptor that affects the biodegradation of the polymer in the corresponding habitat. Specifically, providing can refer to receiving the biodegradation habitat from a user using, for example, an input of a corresponding input unit. In addition, providing can also refer to accessing a storage unit on which the biodegradation habitat has been stored. In addition, providing can also refer to the preset of the biodegradability habitat. For example, if the method is used in a very specific environment, which is only sensitive to a specific biodegradation habitat, the corresponding biodegradation habitat can be preset and therefore does not have to be provided as a specific input. In addition, providing can also include, for example, directly receiving a habitat descriptor from other sources via a network connection, and providing the received habitat descriptor as the biodegradation habitat. The provided biodegradation habitat can refer to a general habitat, for example, a marine habitat, wherein the corresponding habitat descriptor of the habitat has been stored in an accessible corresponding storage device. The provided habitat descriptor determines for which habitat descriptors the habitat descriptor value should be determined. For example, the provided biodegradation habitat can indicate that salt concentration is an environmental characteristic that can affect the biodegradability in the habitat. In this example, salt concentration refers to the habitat descriptor, and the value of the salt concentration will be determined as the habitat descriptor value.

[0023] In general, habitat descriptors indicate the environmental characteristics of a habitat. Specifically, the environmental characteristics of a biodegradation habitat can affect the biological activity in the corresponding habitat, for example, can affect the presence, growth or absence of a specific microbial group. Therefore, the environmental characteristics defined by the habitat descriptors also indirectly affect the biodegradation of the polymer in the corresponding habitat. For example, if a polymer can be biodegraded by a specific bacteria that requires a specific salt concentration, then the polymer will biodegrade rapidly in a habitat that provides such a salt concentration, such as an ocean habitat, but in a habitat where the salt concentration is not suitable, such as wastewater, the biodegradation will be much slower.

[0024] Preferably, the biodegradation habitat refers to any one of a marine habitat, a wastewater habitat, a lake habitat, a compost habitat or a soil habitat. In a preferred embodiment, the biodegradation habitat refers to a marine habitat, wherein the habitat descriptor refers to at least one of salt concentration, sedimentation type, oxygen level, position, sample depth, water temperature, nutrient concentration (e.g., nitrogen, phosphate, potassium and / or dissolved organic carbon concentration), pH value, environment type, oxygen content and microbial community. In another preferred embodiment, the biodegradation habitat refers to a lake habitat, and wherein the habitat descriptor refers to at least one of salt concentration, sedimentation type, oxygen level, position, sample depth, water temperature, nutrient concentration, pH value, environment type and microbial community. In another preferred embodiment, the biodegradation habitat refers to wastewater, wherein the habitat descriptor refers to at least one of water temperature, microbial community, sludge concentration, nutrient concentration, pH value, test duration, solid content and enzyme environment. In addition, in this habitat, sludge can also be a separate habitat. Thus, in embodiments, the habitat may also be a sludge habitat, e.g., as an aerobic part of a wastewater treatment plant, and the habitat descriptor refers to at least one of solid content, pH, nutrient content, heavy metal content, microbial community. In a further preferred embodiment, the biodegradation habitat refers to soil, and the habitat descriptor refers to at least one of temperature, composition (e.g., sand and / or clay content), pH, moisture content, nutrient concentration, microbial community, nitrogen content, water holding capacity, and enzyme environment. In further preferred embodiments, the biodegradation habitat refers to compost, and the habitat descriptor refers to at least one of temperature, compost activity, pH, moisture content, humidity, compost maturity, compost composition, compost source, nutrient concentration, microbial community, solid content, water holding capacity, and enzyme environment.

[0025] The method further comprises providing a biodegradation model based on the provided biodegradation habitat. Specifically, preferably, providing a biodegradation model refers to selecting a biodegradation model based on the provided biodegradation habitat. For example, a plurality of biodegradation models may be stored on a biodegradation storage device, wherein each biodegradation model has been trained for one or more different biodegradation habitats, in particular has been trained for different values ​​or value ranges of habitat descriptor values ​​of the biodegradation habitat. Based on the provided biodegradation habitat of the indicated habitat descriptor, a corresponding appropriate biodegradation model may be selected from a plurality of biodegradation models. For example, if the indicated habitat descriptor that can be determined by the biodegradation model refers to the habitat descriptor indicated by the provided habitat, the biodegradation model is appropriate. For example, a corresponding lookup table may be provided, which allows an easy comparison between the indicated habitat descriptor and the habitat descriptor to which the biodegradation model stored on the storage device has been trained, so that an appropriate biodegradation model may be directly selected. However, in another embodiment, providing a biodegradation model based on the provided biodegradation habitat may also refer to user selection of a biodegradation model. For example, a user may be provided with pre-selected biodegradation models, which refer to the provided biodegradation habitats, and then be allowed to select the corresponding biodegradation model that should be used. Generally speaking, the biodegradation models that may be stored refer to biodegradation models that have been parameterized based on corresponding training data sets for one or more habitats. Since the training data sets used to parameterize the biodegradation models are historical data, as described in more detail below, the biodegradation models may be trained and thus generated at any time before the specific habitat and target biodegradability of a specific polymer are determined, and stored in the corresponding database after training. However, the biodegradation models that are trained and thus generated can of course also be executed when it is determined that a specific biodegradation model is needed, for example for a specific habitat.

[0026] The provided biodegradation model is then adapted to determine habitat descriptor values ​​based on the target biodegradability and polymer physicochemical parameters. Specifically, the biodegradation model is a data-driven model parameterized with respect to the biodegradation habitat, such that it can determine the habitat descriptor value of the polymer based on the polymer physicochemical parameters and the target biodegradability. The term "such that" is interpreted here as parameterized adaptation and thus enabling the biodegradation model to provide biodegradability with respect to the habitat when the polymer physicochemical parameters are provided as input. For example, the biodegradation model associates polymer physicochemical parameters of the historical digital representation of the synthesis specification and the historical digital representation of the habitat with biodegradability. This allows the digital representation of the synthesis specification to be determined based on the target biodegradability. The term "data-driven" is used here to emphasize that the model is primarily based on the corresponding data inputs and is not based on, for example, intuition, personal experience or knowledge. Preferably, the biodegradation model refers to a machine learning-based model, which is based on known machine learning algorithms, such as neural networks, regression models, classification algorithms, etc. It has been found that for most applications in this context, in particular regression models based on linear regression, random forest, Lasso, boosted tree, ridge regression and MARS algorithms are suitable, while for classification models, in particular random forest, logistic regression and SVM algorithms are suitable. Preferably, the biodegradation model is based on a neural network algorithm. Generally speaking, the biodegradation model is parameterized during a training process, in which the polymer physicochemical parameters derived from the parameters quantifying the physicochemical properties of the polymer are used together with the corresponding biodegradability of specific biodegradation habitats and the corresponding habitat descriptor values ​​of these specific biodegradation habitats. Based on such training data sets specific to the biodegradation habitats, and for specific habitat descriptor values, known training methods can be used to determine the corresponding parameters of the data-driven model, so that the biodegradation model is also able to determine the habitat descriptor values ​​of polymers that do not belong to the training data set.

[0027] Then, the method includes determining the habitat descriptor value of the corresponding polymer based on the selected biodegradation model, the target biodegradability and the polymer physicochemical parameters. Specifically, if the digital representation of the polymer includes the physicochemical parameters of the polymer, the polymer physicochemical parameters are provided together with the target biodegradability as input to the biodegradation model, wherein the biodegradation model then provides the determined habitat descriptor value as output. If the digital representation does not directly include the polymer physicochemical parameters, determining the habitat descriptor value can also include first determining the physicochemical parameters of the polymer, for example, as described above. Such determined polymer physicochemical parameters can then be provided as input to the biodegradation model. Such determined habitat descriptor values ​​can then be provided to, for example, an output unit or a computing unit for further processing. Preferably, providing the habitat descriptor value results in further processing using the habitat descriptor value. In such cases, the provision as a separate step can be omitted and replaced by processing the habitat descriptor value.

[0028] In a preferred embodiment, the method further comprises providing a control signal for controlling a reactor system suitable for biodegrading polymers, wherein the control signal is provided based on the determined habitat descriptor value. Specifically, a control signal can be generated or provided so that the reactor system provides a biodegradation habitat having a determined habitat descriptor value to a substance preferably containing a polymer within the reactor system. For example, if the determined habitat descriptor value indicates that the polymer will meet a target biodegradability in a composting environment having a specific temperature, pH value, and moisture content, the control signal may include components that cause the reactor system to simulate the corresponding environment, in particular to set the corresponding temperature, moisture content, and pH value so that the polymer will biodegrade with the corresponding target biodegradability.

[0029] In addition, the processing of habitat descriptor values ​​can also refer to the step of selecting one or more polymers based on the corresponding habitat descriptor values. For example, if the corresponding habitat descriptor values ​​of a specific habitat have been determined for a variety of potential polymers, the selection can include comparing the determined habitat descriptor values ​​of different polymers with predetermined selection criteria, and selecting the polymers whose determined habitat descriptor values ​​meet these criteria. Specifically, in an embodiment, the method includes receiving a target habitat descriptor value or a target habitat descriptor value range, which can be satisfied by a corresponding reactor system, for example. In this case, the method can include comparing the received target habitat descriptor value with the determined habitat descriptor values ​​of different polymers, and selecting a polymer based on the comparison. Specifically, based on such comparisons, a control signal can be provided. A control signal can refer to any signal that allows further control of a technical system. For example, a control signal can be suitable for a control interface, which is used to provide the result of the comparison thereon. In a preferred embodiment, the comparison refers to the verification of the target habitat descriptor value, wherein if the determined habitat descriptor value falls within a predetermined range around the target habitat descriptor value, the verification is positive. In this case, the control signal may be adapted to simply control a user interface to provide an indication of a positive or negative verification result for the corresponding polymer. Preferably, however, the control signal refers to a recipe, i.e., a synthesis specification, for one or more polymers that meet a specified target habitat descriptor value (i.e., are positively verified). A recipe, i.e., a synthesis specification, is generally defined as a guide to how a polymer can be synthesized. Specifically, the recipe includes a starting material, and corresponding parameters for polymerization from the starting material. Preferably, the control signal includes a recipe in a form that directly allows automatic control of a corresponding industrial system or labor equipment for producing the polymer. Specifically, preferably, when the comparison result refers to a determined habitat descriptor value being within a predetermined range around the target habitat descriptor value, the control signal indicates a machine executable synthesis specification for the polymer.

[0030] In a preferred embodiment, the method also includes providing a synthesis specification as a digital representation of a polymer, and determining polymer physicochemical parameters from the synthesis specification. Specifically, the synthesis specification (i.e., recipe) includes information about polymer synthesis, for example, information about starting materials and methods, and the corresponding starting materials are covalently bonded to form polymer chains or polymer networks by the method. The method then includes determining polymer physicochemical parameters from the synthesis specification. Alternatively, a subgroup can be determined from the synthesis specification, and then the subgroup physicochemical parameters of the subgroup can be determined based on the subgroup physicochemical parameters of the subgroup (for example, from a database) or using a known descriptor to determine the polymer physicochemical parameters. In a preferred embodiment, the catalyst and / or non-reactive process components utilized are further determined from the synthesis specification. In this case, it is preferred that the information is also used by the biodegradation model together with the polymer physicochemical parameters to determine the habitat descriptor value. Preferably, the physicochemical parameters of the catalyst and / or non-reactive process components are also determined, and the physicochemical parameters of the polymer are also determined using the corresponding physicochemical parameters. Preferably, the physicochemical parameters of the catalyst and / or non-reactive process components refer to the amount of the corresponding components, for example, molar mass, molar percentage, etc., which are considered to be used to determine the polymer physicochemical parameters of the polymer.

[0031] In a preferred embodiment, determining the polymer physicochemical parameters from the synthesis specification includes identifying the type and amount of subgroups based on the synthesis specification, for example, as the physicochemical parameters of the subgroups, and then determining the physicochemical parameters of the polymer based on the type and amount of the identified subgroups. Generally speaking, the type of subgroup can refer to a predetermined type or category associated with a specific physicochemical property (e.g., a descriptor) of the subgroup, and therefore associated with a specific physicochemical property of the polymer containing these subgroups. However, since the general physicochemical properties of the polymer and therefore the physicochemical parameters of the polymer can also depend on the amount of the subgroup present in the polymer, the amount can also be taken into account. In a preferred embodiment, determining the type and amount of the subgroup takes into account the information indicating the type of polymerization provided by the synthesis specification. Information about the type of polymerization that can be utilized can relate to, for example, whether polymerization refers to condensation polymerization, addition polymerization, free radical polymerization, cationic polymerization, anionic polymerization, or coordination chain polymerization. Preferably, for each type of polymerization, a rule that can be used to determine the polymer subgroup is predetermined. For example, a rule can be predetermined to determine which functional groups of monomers in the synthesis specification react with which functional groups of the synthetic polymer in what order of priority. These rules can be based on, for example, kinetic considerations. Based on the number and type of polymeric functional groups, subgroups can be determined, and then the number and type of subgroups can be calculated.

[0032] In one embodiment, determining the amount of a subset includes determining the amount of at least one of the following in the polymer based on the synthesis specifications: amides, esters, thioesters, carbonates, ethers, amines, ureas, carbamates, thiocarbamates, isocyanurates, biuret, allophanate, acetals, Michael adducts, free radical polymerized double bonds, siloxanes, silanes, silazanes, phosphazene groups and residual amines, aldehydes, ketones, epoxides, aziridines, isocyanates, alcohols, thiols, carboxylic acids, acyl halides, α,β-unsaturated carbonyl groups, α,β-unsaturated carboxyl groups and double bond groups.

[0033] In an embodiment, the method further comprises providing a biodegradation test method, wherein the provided biodegradation test method indicates a standardized biodegradation test method for experimentally determining the biodegradation of a polymer, wherein a biodegradation model is further provided based on the provided biodegradation test method. Generally speaking, there are a variety of standardized biodegradation test methods for testing the biodegradation of a polymer. For example, such test methods can be found in DIN or ISO standards. Further providing a biodegradation test method and providing a biodegradation model that has been trained based on the provided biodegradation test method allows for determining a biodegradation that can be easily compared to, for example, biodegradation measured separately using a corresponding test method. Specifically, for this embodiment, it is preferred that the biodegradation model is trained based on a data set in which the test method based on which the biodegradation has been determined is clearly specified, so that the biodegradation model can be specifically trained for one or more test methods.

[0034] In one embodiment, the target application of the polymer is further provided to relate to the intended application of the polymer, wherein the biodegradation habitat is provided based on the target application. The target application of the polymer may refer to, for example, the intended application habitat of the polymer, for example, if the polymer is intended to be used as a coating, for personal care products, for detergents, or for product packaging. Such target applications indicate specific biodegradation habitats. For example, for the packaging of the product, it may be interesting if the polymer biodegrades in compost. In another example, if the target application refers to the use of the polymer in personal care products, it is likely that the polymer will be found in a water environment sooner or later. Therefore, the corresponding target application indicates the corresponding biodegradation habitat. In this context, a predetermined list can be provided on a storage device, on which the corresponding target application and the corresponding biodegradation habitat are stored. The target application of the polymer can then be provided, for example, by providing a list of target applications to the user and allowing the user to select the corresponding target application, wherein the corresponding target application is connected to one or more biodegradation habitats. The biodegradability of each biodegradation habitat to which the target application is associated can then be determined, or the user can again select the corresponding biodegradation habitat associated with the target application. Additionally or alternatively, information indicating the expected end-of-life treatment of the polymer can be provided. For example, the end-of-life treatment may indicate whether the polymer is intended to biodegrade in a particular environment, or whether it should be subjected to a particular treatment, such as in a bioreactor. Thus, as described above, information on the expected end-of-life treatment may also be used to determine the biodegradation habitat of the polymer.

[0035] In an embodiment, the biodegradation model can be further trained to provide information other than the habitat descriptor value, which indicates the accessible surface area of ​​the product containing the polymer that allows the target biodegradability of the product to be met. For example, the information can refer to whether the product should be provided in a solid, powdered, foamed, granular or any other form to meet the target biodegradability in the corresponding habitat. Preferably, the information indicates the accessible surface area per mass of the product or the geometry of the smallest independent part of the product. In general, although the biodegradability of a polymer is an inherent property of the polymer, the exact timing of the biodegradability of the product containing the polymer also depends on the surface area that can be contacted by the microbial components in the habitat responsible for biodegradation, for example. Therefore, further determining the accessible surface area of ​​the product containing the polymer that allows the target biodegradability to be met allows the corresponding product to be further accurately biodegraded. For example, based on the information about the accessible surface area, control data, i.e., a control signal, can be generated to control a grinder or a mill to chop or crush the product to be biodegraded.

[0036] In an embodiment, the habitat and / or habitat descriptor are stored in association with a corresponding geographic location, wherein providing a biodegradation habitat refers to providing a geographic location of the habitat, and retrieving the habitat and / or habitat descriptor of the geographic location from a storage device. For example, a geographic location may refer to coordinates or other regional identifiers. For example, a geographic location may refer to the name of a city, a country, a region of a country, a sea area, a geographical feature, etc. Based on such a geographic location, a corresponding habitat descriptor, such as a typical environmental characteristic, may be determined. Therefore, by providing a geographic location, a corresponding habitat descriptor for the geographic location may be provided. This has the following advantages: the user does not have to know the exact habitat or exact habitat descriptor of the area. Therefore, the user can simply provide a location where the expected polymer may be biodegraded in the area.

[0037] In an embodiment, the polymer physicochemical parameters indicated by the digital representation of the polymer refer to at least one of a recipe parameter from polymer synthesis, a composition descriptor, a count descriptor, a list of structural fragments, a fingerprint, a graphical invariance, a 3D descriptor, and / or a higher dimensional descriptor indicating a polymer chemical property. The corresponding connection of the digital representation with, for example, a previously calculated polymer physicochemical parameter or additional information about the polymer may have been stored and connected to the corresponding digital representation. For example, if the digital representation refers to a brand name, the corresponding structural formula, subgroup and / or subgroup physicochemical parameters or polymer physicochemical parameters corresponding to the brand name may have been stored, for example, on a storage device of the brand name owner.

[0038] In a preferred embodiment, the polymer belongs to at least one of the following polymer types: polyalkoxylates, polycondensates, addition polymers, vinyl polymers, natural polymers, polymer dispersions, polymer foils, biopolymers, silicone polymers, resins, rubbers and polyketones, wherein the biodegradation model is specifically trained for the respective polymer type to which the polymer belongs. In particular, the training data used to parameterize the biodegradation model include polymers of the respective polymer type. However, the biodegradation model can also be parameterized with training data for polymers from more than one polymer type.

[0039] In a preferred embodiment, the polymer is a polyalkoxylate and the habitat is a wastewater habitat, in particular a sludge habitat. In addition, in this embodiment, it is preferred that the physicochemical properties include at least one of molar mass, composition, chemical moiety, solubility in water and partition coefficient, more preferably, the physicochemical properties include molar mass, even more preferably, include molar mass, composition, even more preferably, include molar mass, composition and partition coefficient.

[0040] In a preferred embodiment, the polymer is a polycondensate, preferably polyester, polyamide and phenolic plastic, and the habitat is a wastewater habitat, in particular a sludge habitat or a soil habitat. Furthermore, in this embodiment, it is preferred that the physicochemical properties include at least one of molar mass, composition, chemical moiety, solubility in water, partition coefficient, measure of stability to hydrolysis and crystallinity, more preferably, the physicochemical properties include molar mass and composition, even more preferably, include molar mass, composition and chemical moiety, even more preferably, include molar mass, composition, chemical moiety and crystallinity.

[0041] In a preferred embodiment, the polymer is an addition polymer, preferably polyurethane and polyurea, and the habitat is a soil habitat or a marine habitat. In addition, in this embodiment, it is preferred that the physicochemical properties include at least one of composition, chemical moiety, ratio of chemical moieties, ratio of components and crystallinity, more preferably, the physicochemical properties include composition, even more preferably, include composition and ratio of chemical moieties, even more preferably, include composition, ratio of chemical moieties, ratio of components.

[0042] In a preferred embodiment, the polymer belongs to the class of vinyl polymers, preferably polyethylene, polyacrylate, polystyrene, polyvinyl ether and polyvinyl alcohol, and the habitat is a wastewater habitat, in particular a sludge habitat or a soil habitat. In addition, in this embodiment, it is preferred that the physicochemical properties include at least one of molar mass, composition, chemical part, solubility in water, and partition coefficient, more preferably, the physicochemical properties include molar mass, even more preferably, include molar mass and composition, even more preferably, include molar mass, composition and chemical part.

[0043] In a preferred embodiment, the polymer is a natural polymer, preferably a polysaccharide, a polynucleotide, a lignin, a suberin, a keratin, a gelatin film, a melanin, a natural rubber and a polypeptide, and the habitat is a wastewater habitat, in particular a sludge habitat or a soil habitat. In addition, in this embodiment, it is preferred that the physicochemical properties include at least one of a molar mass, a chemical part, a solubility in water and a partition coefficient, more preferably the physicochemical properties include a chemical part, and even more preferably include a chemical part and a molar mass.

[0044] In a preferred embodiment, the polymer is a polymer dispersion and the habitat is a marine habitat or a soil habitat. In addition, in this embodiment, it is preferred that the physicochemical properties include at least one of composition, chemical moiety, solubility in water and particle size, more preferably, the physicochemical properties include composition and particle size, and even more preferably, include composition, chemical moiety and particle size.

[0045] In a preferred embodiment, the polymer belongs to a polymer foil and the habitat is a soil habitat or a marine habitat. Furthermore, in this embodiment, it is preferred that the physicochemical properties include at least one of composition, molar mass, chemical moiety, solubility in water, crystallinity and surface / volume ratio, more preferably, the physicochemical properties include composition and surface / volume ratio, even more preferably, include composition, chemical moiety and surface / volume ratio, even more preferably, include composition, chemical moiety, crystallinity and surface / volume ratio.

[0046] In a preferred embodiment, the polymer is an organosilicon polymer and the habitat is a soil habitat, a wastewater habitat, in particular a sludge habitat or a marine habitat. Furthermore, in this embodiment, it is preferred that the physicochemical properties include at least one of composition, molar mass, chemical moiety, solubility in water, partition coefficient and surface / volume ratio, more preferably, the physicochemical properties include molar mass, even more preferably, include molar mass and composition, even more preferably, include molar mass, composition and partition coefficient.

[0047] In a preferred embodiment, the polymer is a resin and the habitat is a soil habitat or a marine habitat. Furthermore, in this embodiment, it is preferred that the physicochemical properties include at least one of composition, molar mass, chemical moiety, solubility in water, crystallinity and surface / volume ratio, more preferably, the physicochemical properties include molar mass, even more preferably, include molar mass and composition, even more preferably, include molar mass, composition and surface / volume ratio.

[0048] In a preferred embodiment, the polymer is a rubber and the habitat is a soil habitat or a marine habitat. In addition, in this embodiment, it is preferred that the physicochemical properties include at least one of composition, chemical moiety, solubility in water, crystallinity and surface / volume ratio, more preferably, the physicochemical properties include composition, even more preferably, include composition and surface / volume ratio, even more preferably, include composition, chemical moiety, crystallinity and surface / volume ratio.

[0049] In a preferred embodiment, the physicochemical properties include at least one of molar mass, chemical moiety, solubility in water and / or octanol, crystallinity, and surface area / volume ratio. More preferably, the physicochemical properties include chemical moieties, and even more preferably, molar mass, chemical moieties, and solubility in water. For polymers belonging to polyalkoxylates, condensation polymers, vinyl polymers, or organosilicon polymers, it is preferred that the physicochemical properties also include at least one of partition coefficient and composition. For polymers belonging to condensation polymers, addition polymers, polymer foils, resins, rubbers, or polyketones, it is preferred that the physicochemical properties also include at least one of crystallinity and anti-hydrolytic stability measures. For polymers belonging to resins, rubbers, addition polymers, or organosilicon polymers, it is preferred that the physicochemical properties also include surface / volume ratio.

[0050] In another aspect, an interface method for providing an interface is presented, wherein the interface method includes: a) receiving a target biodegradability, a numerical representation, and a habitat as input via a user interface, and providing the received target biodegradability, the numerical representation, and the habitat to a processor that performs the method as described above; and b) providing a determined habitat descriptor value for a polymer as a result, wherein the result is received from a processor that performs the method as described above.

[0051] In another aspect, a computer-implemented training method is presented for training a data-driven based biodegradation model for parameterizing the biodegradation model, wherein the training method comprises: a) providing training data associated with a predetermined biodegradation habitat, wherein the training data comprises i) digital representations of a plurality of training polymers indicating physicochemical properties of each of the training polymers, ii) habitat descriptor values ​​of corresponding habitat descriptors of the biodegradation habitat, and iii) biodegradability of the corresponding biodegradation habitat descriptor values ​​associated with each of the training polymers; b) providing a data-driven based trainable biodegradation model; c) training the provided data-driven based biodegradation model based on the provided training data, such that the trained biodegradation model is suitable for determining habitat descriptor values ​​based on biodegradability and physicochemical properties; and d) providing the trained biodegradation model.

[0052] In a further aspect, an apparatus is presented for determining a habitat descriptor value providing a target biodegradability of a predetermined polymer, wherein the apparatus comprises: a) a target biodegradability providing unit for providing a target biodegradability, wherein the biodegradability indicates a biodegradability characteristic of the polymer; b) a digital representation providing unit for providing a digital representation of the polymer indicating or associated with a physicochemical characteristic of the polymer; c) a habitat providing unit for providing a biodegradation habitat, wherein the biodegradation habitat indicates a biodegradation factor that affects the biodegradation of the polymer in the corresponding habitat. A habitat descriptor of a solution, wherein the habitat descriptor indicates an environmental characteristic of the habitat; d) a model providing unit, the model providing unit is used to provide a biodegradation model based on the provided biodegradation habitat, wherein the biodegradation model is suitable for determining a habitat descriptor value that allows biodegradation of the polymer that meets a target biodegradability in the biodegradation habitat, wherein the biodegradation model is a data-driven model parameterized with respect to the biodegradation habitat so that it determines the habitat descriptor value based on the target biodegradability and physicochemical characteristics; and e) a determination unit, the determination unit is used to determine the habitat descriptor value of the polymer based on the selected biodegradation model, the target biodegradability and the polymer description.

[0053] In another aspect, an interface device for providing an interface is presented, wherein the interface device comprises: a) an input interface unit for receiving a target biodegradability, a digital representation and a habitat as input via a user interface, and for providing the received target biodegradability, the digital representation and the habitat to a device as described above; and b) a result interface for providing a habitat descriptor value of a polymer as a result, wherein the result is received from a device as described above.

[0054] In another aspect, a training device is presented for training a data-driven biodegradation model for parameterizing the biodegradation model, wherein the training device includes: a) a training data providing unit for providing training data associated with a predetermined biodegradation habitat, wherein the training data includes i) digital representations of multiple training polymers indicating the physicochemical properties of each of the training polymers, ii) habitat descriptor values ​​of corresponding habitat descriptors of the biodegradation habitat, and iii) biodegradability of the corresponding biodegradation habitat descriptor values ​​associated with each training polymer; b) a trainable model providing unit for providing a data-driven trainable biodegradation model; c) a training unit for training the provided data-driven biodegradation model based on the provided training data, so that the trained biodegradation model is suitable for determining the habitat descriptor value based on the biodegradability and the physicochemical properties; and d) a trained model providing unit for providing the trained biodegradation model.

[0055] In a further aspect of the invention, the use of the method as described above is presented, wherein the method is used to determine the habitat descriptor value of any of the following: i) polymers related to polyesters, in particular, polymers for cover film and packaging applications, such as aromatic aliphatic copolyesters, ii) polymers related to polyalkoxylates, in particular, polymers for household applications and personal care applications, iii) polymers related to polyurethane dispersions, iv) polymers for fragrance applications, v) polymers for paper coatings for packaging applications based on multilayer blends, and vi) polymers related to polyurethanes, polymers for adhesives.

[0056] In another aspect of the present invention, a system is presented, wherein the system comprises i) a control signal comprising synthesis specifications of a polymer indicating one or more ingredients used to produce the polymer, wherein the control signal is generated according to the above method, and ii) one or more ingredients indicated by the synthesis specifications in the control signal.

[0057] In a further aspect of the invention, the use of a control signal generated according to the above method for controlling a production process, in particular a production process comprising polymer production, or for controlling a reactor, in particular a waste degradation reactor, is presented.

[0058] In another aspect of the invention, a control signal is presented, wherein the control signal is generated according to the above method. Preferably, the control signal i) comprises a machine executable synthesis specification for producing a polymer or ii) refers to a signal for controlling a reactor.

[0059] In a further aspect, a computer program product for determining a habitat descriptor value providing a target biodegradability of a predetermined polymer is presented, wherein the computer program product comprises program code means for causing an apparatus as described above to perform a method as described above.

[0060] In another aspect, a computer program product for training a biodegradation model is presented, wherein the computer program product comprises program code means for causing the apparatus as described above to perform the method as described above.

[0061] It should be understood that the method as described above, the device as described above and the computer program product as described above have similar and / or identical preferred embodiments, in particular the preferred embodiments as defined in the dependent claims. In addition, the training method as described above, the training device as described above and the training computer program product as described above also have similar and / or identical preferred embodiments, in particular the preferred embodiments as defined in the dependent claims.

[0062] It shall be understood that a preferred embodiment of the invention can also be the dependent claims or any combination of the above-mentioned embodiments with corresponding dependent claims.

[0063] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In the following figures:

[0065] Figure 1 Schematically and exemplarily, an embodiment of a system comprising an apparatus for determining a habitat descriptor value is shown,

[0066] Figure 2 A flow chart schematically and exemplarily shows a method for determining a habitat descriptor value,

[0067] Figure 3 A flow chart schematically and exemplarily showing a method for training a biodegradation model for determining habitat descriptor values,

[0068] Figure 4 A flow chart schematically and exemplarily showing an embodiment of a method for determining a habitat descriptor value,

[0069] Figure 5 Schematically and exemplarily an optional extension of the method for determining a habitat descriptor value is shown,

[0070] Figures 6 to 8 A block diagram schematically and exemplarily shows a system architecture of a system and apparatus for determining a habitat descriptor value,

[0071] Fig. 9 The output screen and input screen of an exemplary user interface are schematically and exemplarily shown, and

[0072] Fig.10 and Fig.11 A further flow chart of a preferred, more detailed embodiment of the method for determining a habitat is shown schematically and exemplarily. DETAILED DESCRIPTION

[0073] Figure 1 Schematically and exemplarily, an embodiment of a system 100 is shown, which includes an apparatus 110 for determining a habitat descriptor value providing a target biodegradability of a predetermined polymer. In addition, the system 100 includes a training device 130 for training a biodegradation model utilized in the apparatus 110, a database 140 on which the determination results of the polymer, i.e. the determined habitat descriptor value, can be stored, and a waste management system 120 for managing waste containing the polymer, for example by utilizing a reactor system, which can be controlled using the determined habitat descriptor value.

[0074] The device 110 comprises a target biodegradability providing unit 111, a digital representation providing unit 112, a habitat providing unit 113, a model providing unit 114 and a determining unit 115. Optionally, the device 110 may further comprise an output and / or control unit 116, which may be adapted to output the determined habitat descriptor value and / or provide a control signal for controlling the waste management process of the waste management system 120 based on the determined habitat descriptor value.

[0075] The target biodegradability providing unit 111 is adapted to provide a target biodegradability indicating a desired biodegradability characteristic of a polymer. The target biodegradability providing unit 111 may refer to, for example, an input unit into which a user may input a corresponding target biodegradability. Furthermore, the target biodegradability providing unit 111 may refer to or may be part of a user interface that allows a user to interact with the device 110 for providing a target biodegradability. However, the target biodegradability providing unit 111 may also refer to or be communicatively coupled to a storage unit on which, for example, a target biodegradability for a specific application has been stored.

[0076] The digital representation providing unit 112 is suitable for providing a digital representation of the polymer physicochemical parameters for which the habitat descriptor value should be determined. The digital representation providing unit 112 may refer to, for example, an input unit to which a user can input the corresponding digital representation. In addition, the digital representation providing unit 112 may refer to a user interface that allows a user to interact with the device 110 and / or the database 140 or a part of the user interface. However, the digital representation providing unit 112 may also refer to a storage unit on which the digital representation of the polymer has been stored or is communicatively coupled thereto. Generally speaking, the digital representation may directly include polymer physicochemical parameters, which indicate parameters that quantify the physicochemical properties of the corresponding polymer. However, instead of directly providing the physicochemical parameters of the polymer, the synthesis specification of the polymer may also be provided. In this case, it is preferred that the digital representation providing unit 112 is also suitable for determining the polymer physicochemical parameters according to the synthesis specification. Specifically, it is preferred that the digital representation providing unit 112 is suitable for identifying the type and amount of polymer subgroups from the synthesis specification, and determining the physicochemical parameters of the polymer based on the type and amount of the identified subgroups. In particular, the digital representation providing unit 112 may be adapted to determine the corresponding subgroup physicochemical parameters for each identified subgroup, for example, by accessing a database on which the corresponding physicochemical parameters of a plurality of the most relevant subgroups are stored. The physicochemical parameters of the polymer may then be determined based on the subgroup physicochemical parameters of the subgroups, and preferably also based on the amount and type of the determined subgroups, for example, by a weighted average of the subgroup physicochemical parameters of the subgroups. Subsequently, the digital representation providing unit 112 is adapted to provide the digital representation comprising the physicochemical parameters of the polymer to, for example, the determining unit 115.

[0077] The habitat providing unit 113 is adapted to provide a biodegradation habitat. The habitat providing unit 113 may refer, for example, to an input unit into which a user may input a corresponding biodegradation habitat. For example, a user interface may be provided that allows a user to select from a number of predetermined biodegradation habitats. In a preferred embodiment, the habitat providing unit may be communicatively coupled to or relate to a user interface that allows, for example, indicating a geographical location by marking a location on a map, by indicating coordinates or providing the name of a region (e.g., a political region or a geological region), wherein the habitat providing unit may then be adapted to provide a biodegradation habitat based on the geographical location. For example, if the geographical location indicates a specific sea area, such as the North Sea or the Atlantic Ocean, the habitat providing unit may be adapted to determine a marine habitat as a biodegradation habitat.

[0078] Generally speaking, a biodegradation habitat indicates a habitat descriptor that affects the biodegradation of a polymer in the corresponding habitat. Specifically, a habitat descriptor indicates an environmental characteristic of the habitat, for example, for a marine habitat, the salt concentration can strongly affect the biodegradation of a polymer in the marine habitat. The indicated habitat descriptor then refers to a habitat descriptor for which a habitat descriptor value should be determined. Specifically, the habitat descriptor value to be determined is determined so that the provided polymer will biodegrade in a fortunate habitat with a corresponding determined habitat descriptor value, so that a target biodegradability is met within limits. For example, if the marine habitat provides a corresponding salt concentration value and a temperature value or a corresponding value range, it can be determined that a specific polymer in the marine habitat meets a specific biodegradation half-life.

[0079] The model providing unit 114 is suitable for providing a biodegradation model based on the provided biodegradation habitat. Specifically, it is preferred that the model providing unit 114 is suitable for selecting a biodegradation model from a plurality of biodegradation models already stored in a database. For example, the biodegradation model may be trained with respect to training data corresponding to one or more specific biodegradation habitats. These specific biodegradation habitats may be defined relative to habitat descriptors that define which habitat descriptor values ​​may be accurately determined by the corresponding biodegradation model. For example, a lookup table may be provided that allows the model providing unit to select which biodegradation model is appropriate based on the biodegradation habitat, for example based on the habitat descriptor values ​​that should be determined. However, the model providing unit 114 may also include or refer to an input unit, into which the biodegradation model may be received, for example, by a user selection or user input indicating which biodegradation model should be used.

[0080] Biodegradation model is a parameterized data-driven model, so that it can be based on digital representation, particularly based on polymer descriptors indicating the physicochemical properties associated with polymers, and based on the target biodegradability of one or more habitat descriptor values, to determine the biodegradability of polymers in the habitat. In a preferred embodiment, the data-driven model refers to a machine learning model, for example, utilizing an algorithm based on a regression model or an algorithm based on a classifier model. The algorithm based on the regression model can be based on any one of a neural network algorithm, a linear regression algorithm, a LASSO algorithm, a ridge regression algorithm, a MARS algorithm, a random forest algorithm, and a boosted tree algorithm. The algorithm based on the classifier model can be based on any one of a random forest algorithm, a logistic regression algorithm, and a SVM algorithm. The inventors have found that for most applications, particularly linear regression, random forest, neural network, and an algorithm based on MARS are suitable.

[0081] For example, the training device 130 can be used to train the biodegradation model. Specifically, the training device 130 includes a training data providing unit 131, which is used to provide training data for training a data-driven biodegradation model. The training data includes a) polymer physicochemical parameters of multiple training polymers, b) biodegradability associated with each training polymer in one or more different habitats, and c) habitat descriptor values ​​associated with the corresponding habitat and the corresponding biodegradability. Preferably, in the training data, the biodegradability provided for each training polymer refers to the biodegradability measured according to the same measurement method. However, biodegradability can also be provided for different measurement methods, in which case it is preferred to clearly indicate which biodegradability is associated with which measurement methods so that the biodegradability model can be trained to distinguish different measurement methods. In general, the training data can be designed to cover a predetermined habitat space of the biodegradation model to be trained, wherein the habitat space is defined by the value range of the corresponding habitat descriptor to which the biodegradation model will be trained. For example, the training data can be designed to cover a predetermined polymer type for a predetermined habitat. Known methods for designing and optimizing training data for a predetermined habitat space may be utilized so that the habitat space is well covered by the training data and random outliers are avoided.

[0082] In addition, the training device 130 includes a model providing unit 132, which is suitable for providing a data-driven trainable biodegradation model, for example, a biodegradation model including parameters that can be set during a training process for training the biodegradation model. For example, the trainable biodegradation model may have been stored on a storage unit, and the model providing unit 132 can access the storage unit for providing the model. In addition, the training device 130 includes a training unit 133, which is used to train the provided data-driven biodegradation model based on the provided training data. In particular, training may refer to changing the parameters of the biodegradation model based on the corresponding training data until the biodegradation model is suitable for determining one or more habitat descriptor values ​​of the polymer based on the digital representation, in particular the polymer physicochemical parameters of the polymer and the target biodegradability. In general, any known training algorithm for training data-driven, in particular a model based on machine learning, can be used. Preferably, during the training of the biodegradation model, the physicochemical parameters of the polymer that have the greatest influence on the biodegradability and / or habitat descriptor values ​​in the corresponding habitat are also determined, and then the model is trained based on these most influential descriptors. In order to determine these most influential physicochemical parameters and / or habitat descriptors, for example, cluster analysis or PCA analysis tools can be used. Specifically, the polymer physicochemical parameters can be used to determine the application space of the training data, wherein the application space can then be defined by the polymer physicochemical parameters of the polymers and the habitat descriptors covered by the data. The determination of the most influential physicochemical parameters and / or habitat descriptors can then be performed as a dimensionality reduction of the application space. Algorithms for optimizing the training data in the application space can then be applied, for example, to cover the application space with as little training data as possible.

[0083] Thus, the training device 130 comprises a trained model providing unit 134, which is adapted to provide the trained biodegradation model to, for example, a storage unit on which biodegradation models trained for different habitats and / or different types of polymers are stored. However, the trained model providing unit 134 may also be adapted to directly provide the trained biodegradation model, for example, to the biodegradation model providing unit 114 of the device 110.

[0084] In all cases, the biodegradation model providing unit 114 is then adapted to provide a suitable trained biodegradation model to the determination unit 115. The determination unit 115 can then determine the habitat descriptor value using the biodegradation model, the provided digital representation and the provided target biodegradability. In particular, the determination unit 115 can be adapted to use the polymer physicochemical parameters indicated by the digital representation together with the target biodegradability as input to the biodegradation model, which has been trained as described above, and then provide a determination of the habitat descriptor value as output. For example, an output unit involving a display can then be adapted to output the determined habitat descriptor value. In addition, the determined habitat descriptor value can also be provided to a database 140 for storing, for example, polymers associated with the determined habitat descriptor value for a specific habitat for future use. For example, a polymer that meets a predetermined target biodegradability in a specific habitat can be selected from the database 140, and the corresponding determined habitat descriptor value can then be utilized, for example, by the waste management system 120. However, polymers may also be selected based on the determined habitat descriptor values, for example in order to only allow polymers within a reactor of the waste management system 120 that can provide corresponding suitable biodegradation conditions for these polymers.

[0085] Optionally, the apparatus 110 may comprise a control unit 116 adapted to provide a control signal based on the determined habitat descriptor values ​​for controlling a reactor system, e.g. as part of a waste management system 120, to biodegrade the polymer. In particular, it is preferred that the provided control signal controls the reactor system such that the reactor system provides at least one of the determined habitat descriptor values ​​to a substance comprising the polymer within the reactor system. For example, the control signal may control the temperature or humidity within the reactor system such that it satisfies the corresponding determined habitat descriptor value. This allows controlling the waste management facility 120 such that polymers that should biodegrade within the facility, e.g. in different reactor systems, are degraded, e.g. within a predetermined time, with a desired target biodegradability.

[0086] Figure 2A flow chart of a method for determining a habitat descriptor value providing a target biodegradability of a predetermined polymer is schematically and exemplarily shown. The method 200 comprises a first step 210 of providing a target biodegradability. In addition, the method 200 comprises a step 220 of providing a digital representation of the polymer indicating the physicochemical parameters of the polymer. Specifically, providing the target biodegradability and providing the digital representation in steps 210 and 220 can be performed according to the principles described above regarding the target biodegradability providing unit 111 and the digital representation providing unit 112, respectively. In addition, in step 230, a biodegradation habitat is provided, which indicates a habitat descriptor that affects the biodegradation of the polymer in the corresponding habitat. For this step 230 as well, the principles described above, for example, regarding the habitat providing unit 113 can be applied. In addition, in step 240, a biodegradation model is provided, and it is suitable for determining a habitat descriptor value based on the target biodegradability and the physicochemical parameters of the polymer. As has been discussed in more detail above, providing a biodegradation model can also refer to selecting a biodegradation model based on the provided biodegradation habitat. In addition, the biodegradation model is a data-driven model parameterized with respect to the biodegradation habitat as discussed in more detail above. Generally speaking, steps 210, 220, 230 and 240 can be performed in any order, even simultaneously. In a subsequent step 250, the habitat descriptor value is then determined using the provided target biodegradability, the provided polymer physicochemical parameters and the selected biodegradation model. In an optional step 260, the habitat descriptor can then be provided to, for example, a user interface for display on a display. In addition, in step 260, the method can additionally or alternatively include generating a control signal that allows control of a reactor system in, for example, a waste management facility to provide at least one of the determined habitat descriptor values ​​to a substance within a reactor system containing a polymer so that the polymer will biodegrade in the reactor system with the target biodegradability.

[0087] Figure 3 A flow chart of a method for training a data-driven biodegradation model is schematically and exemplarily shown. Figure 2 In general, the method 300 may be used, for example, as described in relation to Figure 1 The method 300 includes a step 310 of providing training data for training a data-driven biodegradation model. The training data includes a) polymer physicochemical parameters of a plurality of training polymers, b) biodegradability associated with each training polymer in a corresponding biodegradation habitat, and c) habitat descriptor values ​​associated with each biodegradability. Specifically, the training data may be provided according to the above description of Figure 1The training data providing unit 131 described above is provided according to the principles described above. The method further comprises a step 320 of providing a data-driven trainable biodegradation model, such as a machine learning-based biodegradation model, such as a neural network. In general, step 310 and step 320 may be performed in any order, or even simultaneously. The method 300 then further comprises a step 330 of training the provided data-driven trainable biodegradation model based on the provided training data, for example, by changing parameters in the data-driven trainable biodegradation model so that the trained biodegradation model is suitable for determining one or more habitat descriptors of the polymer based on the digital representation of the polymer and the target biodegradability. In step 340, the trained biodegradation model may then be provided, for example, by storing the trained biodegradation model on a storage device, or by providing the trained biodegradation model directly to the device 130, as described with respect to FIG. Figure 1 as described.

[0088] In the following, a more detailed preferred example of the above method and the corresponding device will be described. An exemplary embodiment of the method may consist of a plurality of steps described below. Figure 4 A schematic and exemplary flow chart of an exemplary embodiment of the method is provided. In this exemplary embodiment, the method begins by requesting a digital representation of a new polymer, for example, via a user interface. In addition, for example, a target application of the new polymer may also be requested via a user interface. The target application may involve, for example, how the new polymer provided with the digital representation should be used in a product, or which waste treatment is expected for the polymer. The corresponding target application then indicates, for example, a corresponding biodegradation habitat and a corresponding target biodegradability. For example, a list may be presented to the user via a user interface, from which the user may select a corresponding target application, and based on the corresponding selection, in addition, a selection of biodegradation habitats and target biodegradability associated with the target application may also be provided for the user to select. Based on the target application, in particular based on the biodegradation habitat, and optionally based on the target biodegradability indicated by the target application, a corresponding determination model, i.e., a biodegradation model, may be selected. Optionally, additional pre-selected conditions indicated by the selected biodegradation model may be required. For example, the biodegradation model can be adapted to utilize additional descriptors, such as optional habitat descriptors, application constraints, etc., which can be requested if necessary and which can allow the biodegradation model to determine the habitat descriptor values ​​with higher accuracy or specifically for these constraints. Furthermore, from the provided digital representation, values ​​of physicochemical parameters of the polymer can be derived, wherein the physicochemical parameters of the polymer can also depend on the provided target application. Further details on the possibility of deriving values ​​of physicochemical parameters of the polymer will be described below with respect to Figure 5Using the selected biodegradation model, the derived physicochemical parameter values ​​and the target biodegradability then allow providing one or more corresponding determined habitat physicochemical parameter values, ie the corresponding target performance. Fig.10 The same method is schematically and exemplarily shown specific to a target technical application characteristic, which is a habitat descriptor value.

[0089] Figure 5 A preferred method 500 for deriving physicochemical parameter values ​​from a digital representation of a new polymer is schematically and exemplarily shown. In a first step 510, a digital representation of the polymer is provided. The digital representation may directly include the polymer physicochemical parameters, in which case the Figure 5 , until step 550. However, in many cases, the physicochemical parameters of the polymer must first be determined based on the provided digital representation, in such cases, for example, involving a recipe for polymer synthesis, or involving a chemical representation of the polymer indicating the chemical composition and bonds in the polymer. In this step 510, the digital representation may include any one or more of the following information: the amount of monomer components; a certain amount of non-monomer components, such as initiators, fillers, additives; reaction conditions, such as temperature, container, pressure, stirring rate; condition profile, such as temperature profile, pH value, solvent; feed profile; polymerization type, such as free radical, cationic, anionic, condensation polymerization, addition polymerization, polyether formation; post-treatment, such as the amount of components, conditions and temperature and feed profile; type of post-treatment, such as free radical, cationic, anionic, condensation polymerization, addition polymerization, polyether formation; chemical information about the components, such as mixtures, connectivity of non-polymer pure compounds, composition of polymer pure compounds based on subgroups, connectivity of monomers associated with subgroups in polymer pure components; for block copolymers, it also includes information, in which block each monomer and reactive prepolymer is combined; for structural / layered materials and composite materials, information should also be provided in which phase / layer each component is included. If such information is not directly provided by the digital representation, then in optional step 520 the reactive components and subgroups may also be derived from the digital representation, for example, from a recipe.

[0090] If the information provided indicates that a mixture is present, in the next step, the mixture is resolved into its pure components and each polymer component is considered as an input polymer. In addition, the polymer composition can also be converted to mole %, weight %, volume % or absolute moles if desired.

[0091] In the next step 530, the polymerizable components can be converted into subgroups, such as repeating units, and the subgroups are determined into different types. For example, the polymerizable subgroups can be determined based on the connectivity information of the non-polymer pure compound by using SMARTS, such as via the KNIME workflow. The connectivity information of all possible subgroups can also be derived from the connectivity information of the non-polymer pure compound by using reaction SMARTS, such as also via the KNIME workflow.

[0092] After the subgroups and their types have been determined, in step 540, the types of physicochemical parameters that should be utilized can be provided. However, the physicochemical parameters can also be determined without first selecting the type of subgroup. In order to reduce the computational resources of the method, it is preferred that in step 541, it is determined whether the subgroup physicochemical parameters associated with the corresponding type of subgroup are already stored in the database, for example, whether the entries of the subgroups with the same connectivity information already exist in the database. If this is the case, for example, in step 544, the corresponding associated subgroup physicochemical parameters can be directly downloaded. If the determined subgroup type is not stored on the database, the subgroup physicochemical parameters associated with the corresponding subgroup type can be determined, for example, in step 542. For example, the 3D structure of the subgroup of the corresponding type can be derived based on the connectivity information, and the automatic calculation of the subgroup physicochemical parameters can be started using, for example, a computer cluster, or an existing machine learning determination can be used as the subgroup physicochemical parameters. Generally speaking, it is preferred that if calculations on new subgroups are necessary, then in step 543, after the calculations are completed, the results are stored in the database. Alternatively, additional subgroup physicochemical parameters may be provided from subgroup topological analysis, quantum chemical calculations, molecular dynamics calculations, coarse-grained methods, finite element calculations and kinetic simulations. In particular, polymer reaction engineering methods may be used to derive subgroup descriptors that allow the microstructure of the polymer to be taken into account.

[0093] In step 531, for example, based on the provided polymer formula information, the amount of the subgroup, i.e., the amount of each type of subgroup, is determined and provided in step 532. For example, the amount can be determined by counting the amount of polymerizable groups per polymerizable component (optionally including prepolymers). In this case, the information about the polymerizable groups can be derived from the non-polymer components, and such determined amounts can be added to the count of the optionally non-polymerized polymerizable groups in the subgroup of the polymer component based on the composition of the polymer component to determine the resulting amount. In addition, it is preferred to remove the amount of polymerizable groups from the reagents used for post-treatment after polymerization from the resulting amount.

[0094] However, although it is preferred that the polymer physicochemical parameters are derived from a subgroup of polymers, in other embodiments of the present invention, the polymer physicochemical parameters may also be derived in other ways, for example, by directly determining the polymer physicochemical parameters from the complete polymer. In addition, the polymer physicochemical parameters of the corresponding polymer may also be already stored on the storage unit, so that deriving the polymer physicochemical parameters from the digital representation of the polymer may refer to determining information about the polymer from the digital representation, which allows accessing a database and retrieving the corresponding polymer physicochemical parameters.

[0095] Alternatively, the derived quantities of the subgroups can be used for additional interpretation of the polymer composition. For example, the total number of polymerized functional groups, such as double bonds, amine groups, alcohol groups, thiol groups, carboxylic acid groups, isocyanate groups, epoxy groups, and formed functional groups, such as amide groups, ester groups, thioester groups, urea groups, urethane groups, thiourethane groups, ether groups can be determined. the molar weighted total number of polymerized functional groups, the mass weighted total number of polymerized functional groups, the total number of residual functional groups, such as double bonds, amine groups, alcohol groups, thiol groups, carboxylic acid groups, isocyanate groups, epoxy groups, the molar weighted total number of residual functional groups, the mass weighted total number of residual functional groups, the sum of all residual functional groups, the ratio between functional groups after polymerization, the number of crosslinks in the polymer, the molar fraction of crosslinks in the polymer, optionally also with mass weights, the average number of atoms per subgroup (optionally, also per weight), the average number of non-H atoms per subgroup (optionally, also per weight), the average number of bonds per subgroup (optionally, also per weight), the average number of bonds between non-H atoms per subgroup (optionally, also per weight), the average number of rotors between non-H atoms per subgroup (optionally, also per weight), the average number of rings per subgroup (optionally, also per weight), the average polarity table per subgroup (optionally, also per weight) The area, the average refractive index per subgroup (optionally, also per weight), the total number of blocks, the molar size of the first block, the molar size of the last block, the HLB value of the polymer, optionally, the HLB value with area weighted, the HLB value of the block with the lowest HLB value, optionally, the HLB value with area weighted, the HLB value of the block with the largest HLB value, optionally, the HLB value with area weighted, the HLB value of the first block, optionally, the HLB value with area weighted, the HLB value of the last block, optionally, the HLB value with area weighted, the mass of the first block, the mass of the last block, the area of ​​the block with the lowest HLB value, the area of ​​the block with the largest HLB value, the difference in HLB values ​​of the blocks can be determined, optionally, the difference with area weighted HLB value, the hydrophilic area of ​​the polymer, the lipophilic area of ​​the polymer, the number of arms of ring-opening polymerization or the arm length of ring-opening polymerization.

[0096] In step 550, the determined amount and type of subgroups and the associated subgroup physicochemical parameters can be used to calculate polymer physicochemical parameters. For example, the polymer physicochemical parameters can be determined by mole weighting, such as arithmetic, harmonic or logarithmic mean, mass weighting, such as arithmetic, harmonic or logarithmic mean, volume weighting, such as arithmetic, harmonic or logarithmic mean, surface area weighting, such as arithmetic, harmonic or logarithmic mean, and one or more of the average of the associated physicochemical parameters of the subgroups. In addition, the polymer physicochemical parameters can be determined by determining one or more of a mole weighted standard deviation, a mass weighted standard deviation, a volume weighted standard deviation, a surface area weighted standard deviation, a mole weighted maximum, a mass weighted maximum, a volume weighted maximum, a surface area weighted maximum, a mole weighted minimum, a mass weighted minimum, a volume weighted minimum, a surface area weighted minimum, a mole weighted sum, a mass weighted sum, a volume weighted sum, a surface area weighted sum, and a maximum difference from the associated subgroup physicochemical parameters.

[0097] In step 560, the derived or provided physicochemical parameters (e.g., related to polymer descriptors) can then be provided to the trained biodegradation model to determine habitat descriptor values, e.g., as relative to Figure 4As described above. Generally speaking, as already described above, in order to determine the habitat descriptor values ​​of different habitats, different trained biodegradation models can also be used. However, the biodegradation model can also be suitable for determining the habitat descriptor values ​​of more than one biodegradation habitat. The biodegradation model can be trained based on training data, specifically automatic statistical preprocessing of the physicochemical parameters of the training polymer, for example, using feature engineering. For example, feature engineering may include first determining a plurality of different polymer physicochemical parameters of the polymer, for example, based on the physicochemical parameters of the subgroups, and preselecting those parameters with a predetermined probability associated with the biodegradability and / or habitat descriptor value of the polymer in a specific habitat from the plurality of physicochemical parameters. Based on the relevant physicochemical parameters, a cluster analysis is preferably performed to identify strongly correlated physicochemical parameter groups. Such a group allows selection of only one of the group members, i.e., only one physicochemical parameter in the group, for representing the entire physicochemical parameter group. Therefore, based on cluster analysis, the number of relevant physicochemical parameters can be further reduced. The same process can be optionally performed on the habitat descriptor to determine the habitat descriptor that is most relevant to the biodegradability of the polymer in a specific habitat. Based on the remaining polymer descriptors, and optionally also based on the habitat descriptors, the application space can be determined and optimized. The application of the trained biodegradation model, such as the application to a specific habitat or polymer physicochemical parameters, can be determined by the space spanned by the training data that forms the application space. For example, the space can be optimized by modifying the training data to regularly cover the application space, by removing strong outliers, by adding training data in the space part that has not been covered, etc. This also allows maximizing the application space. The biodegradation model is then trained based on the optimized training data. The biodegradation model can generally refer to sparse, such as spline, LASSO regression, PLS, and non-sparse, such as ridge regression, tree methods, kernel-based methods, statistical learning models for associating polymer physicochemical parameters with biodegradability in a specific habitat. In addition, the biodegradation model can also provide a determined reliability estimate according to the corresponding biodegradation model used. In step 570 , the determined habitat descriptor values, ie the technical application characteristics, may then be provided to a user, for example via a user interface. Fig.11 The same method is schematically and exemplarily shown specific to a target technical application characteristic, which is a habitat descriptor value.

[0098] Figure 6A block diagram of an exemplary system architecture of an automated laboratory system 1000 for synthesizing polymers is illustrated, the automated laboratory system having a laboratory equipment control device 1102, a network 1150, and synthesis specifications, i.e., recipes, modules 1100 / 1110, and client devices 1108. The automated laboratory system includes a laboratory equipment control device layer 1152 as part of the laboratory equipment control device 1102, a synthesis specification module layer 1154 associated with the synthesis specification module, and a remote control or client layer 1156 associated with the client device 1108. The laboratory equipment control device layer can be divided into several hierarchical layers: hardware, middleware, and interface layers. The hardware layer involves hardware resources, such as sensors and actuators, specifically for controlling the synthesis of polymers. Middleware involves any known middleware for laboratory or equipment synthesis operations. An example is LABS / QM, which provides different abstractions for hardware, networks, and operating systems, such as low-level device control and message passing. The communication layer involves communication protocols, one of which may be REST, which may be implemented over different transport protocols (i.e., UDP, TCP, telemetry), allowing messages to be exchanged between the lab equipment control device and the lab equipment device. Such software architecture allows control and monitoring of lab equipment without having to interact with the hardware.

[0099] The synthesis specification module layer 1154 may include: a mass storage layer, a computing layer, and an interface layer. The storage layer is configured to provide a mass storage device for a data-driven biodegradation model so as to provide a recipe (i.e., a synthesis specification) for a polymer based on a habitat descriptor value, resulting in a specific target biodegradability in a habitat, as described in detail above. Specifically, as described above, the functions performed by the device may be provided as program code components stored on a mass storage device. In addition, the synthesis specifications of a variety of polymers may be stored in a mass storage device. Such data may be stored in a structured database, such as an SQL database, or in a distributed file system, such as HDFS, a NoSQL database, such as HBase, MongoDB. The computing layer may include an application layer that allows customization of functions provided by a standard cloud service to perform a computational process based on target characteristics. Such functions may include determining a digital representation of a target polymer based on a target biodegradability and / or a target habitat descriptor value and a biodegradation model, generating a synthesis specification from the digital representation of the target polymer, and providing the synthesis specification as control data to a laboratory equipment control device. The interface layer can implement web services, network interfaces as UDP or TCP, or Websocket interfaces. For communication with laboratory equipment control devices, a REST API is implemented.

[0100] The client layer 1156 provides an interface for the end user. For the end user, the client layer 1156 can run a client-side web application that provides an interface to the synthetic specification module layer 1154 or the laboratory equipment control device layer 1152. A UI can be provided to the user for selecting a target biodegradability, a biodegradation habitat of the target biodegradability, and optionally a target habitat descriptor value. The target biodegradability may also include a range of biodegradability values. In other examples, a UI may be provided to the user for selecting more than one target biodegradability and / or more than one target habitat and target habitat value. The application can be configured to allow the user to remotely monitor and control laboratory equipment control devices and operations. In other examples, the client device layer and the synthetic specification module layer can be integrated into one device. The alternatives described herein are for illustrative purposes only and should not be considered limiting.

[0101] Figure 7 A block diagram illustrating an exemplary system architecture of a system and apparatus for generating a biodegradation model for determining habitat descriptor values ​​that result in polymer biodegradation in a particular habitat meeting a target biodegradability, a network 2150, and a model generation module 2100 / 2110, which may be viewed as or include a training model apparatus, a synthesis specification module 1100 / 1110, and a client device 2108. The system for generating a biodegradation model includes a model generation module layer 2154 as part of the model generation module, and a client layer 2156 associated with the client device 2108.

[0102] The model generation module layer 2154 may include: a mass storage layer, a computing layer, and an interface layer. The storage layer is configured to provide a mass storage device for the data-driven biodegradation model as described above. In addition, the mass storage device is configured to store the synthesis specifications of the polymer and the measured biodegradability of one or more habitats. Such data may be stored in a structured database, such as an SQL database, or in a distributed file system, such as HDFS, a NoSQL database, such as HBase, MongoDB. The computing layer may include an application layer that allows customization of the functions provided by the standard cloud service to perform the computational process for generating the biodegradation model, which is used to determine the habitat descriptor value. Such functionality may include receiving at least two previously measured polymers and their corresponding digital representations associated with synthesis specifications, measured data of at least one biodegradability in at least one habitat for a specific habitat descriptor value for each of the at least two previously measured polymers, receiving at the model generation module a digital representation of at least one unmeasured polymer, training a model according to the above training principles based on the digital representations of the at least two previously measured polymers, the measured data of biodegradability in at least one habitat, and the corresponding habitat descriptor value for each of the at least two previously measured polymers, and preferably a measure of similarity between the digital representation associated with the synthesis specification for each of the at least two previously measured polymers and the corresponding digital representation associated with the synthesis specification for the at least one unmeasured polymer, and providing the biodegradation model of the habitat descriptor values ​​via an output interface. The model generation module layer may be configured to deploy the generated model and synthesis specification database to the synthesis specification module layer. This may include storing the generated model and synthesis specification database in a mass storage device associated with the synthesis specification module.

[0103] The model generation module layer may also be configured to determine a digital representation of a polymer associated with the synthesis specification based on the synthesis specification. The digital representation may include a set of polymer physicochemical parameters and polymer physicochemical parameter values ​​associated with the synthesis specification of each measured polymer. A method for deriving these polymer physicochemical parameters may be to apply the SMILES algorithm or any other principle described above. In the case of generating a model based on a digital representation derived from a recipe, the relationship between the synthesis specification and the physicochemical parameters may be stored in a mass storage device associated with the model generation module. In this case, deploying the model includes providing the relationship.

[0104] The interface layer can implement web services, network interfaces as UDP or TCP, or Websocket interfaces. In order to communicate with the client device, a REST API is implemented in this example. The client layer 2156 provides access to a large-capacity storage device, which contains the synthesis specifications of the polymer, and at least one biodegradability of at least two polymers and the corresponding habitat descriptor value. The client layer also provides an interface for the end user. For the end user, the client layer 2156 can run a client-side network application, which provides an interface to the model generation module layer 2154 or a large-capacity storage device associated with the client layer. A UI can be provided to the user for selecting a test method and / or a habitat for which a habitat descriptor value should be determined. A UI for selecting synthesis specification data can also be provided to the user. The user interface can also provide the option of uploading the selected data to the model generation module layer, and optionally provide the option of starting model generation.

[0105] Figure 8 An exemplary system 700 for biodegrading chemical products based on control data for controlling a reactor generated according to the present invention is shown. In this example, the system includes a user interface 710 and a processor 720 associated with a control unit 740. The user interface 710 and the processor 720 can be associated with or implemented according to the above principles, and in particular, can be adapted to perform a computer-implemented method to determine a target habitat descriptor value, as described above. The control unit 740 is, for example, configured to receive control data generated according to the present invention as described above, in particular to receive control data generated based on a habitat descriptor value that allows a polymer product to degrade with a target biodegradability. In this example, the control data is provided by a database 730, however, in other examples, the control data can also be provided by a server or any other computing unit for distributing data. The containers 750, 752 can contain components for influencing conditions in the reactor, such as components that affect pH, microorganisms, etc. Valves 760, 762 are associated with the containers 750, 752. Based on the target habitat descriptor value, the valves 750 and 752 can be controlled to incorporate the appropriate amount of each component into the reactor 770. The motor 800 of the mixer and / or grinder 780 can also be controlled by the control unit based on the control data. The optional heater 790 can also be controlled based on the determined habitat descriptors. Finally, an outlet valve 810 in fluid communication with the reactor can be controlled by the control unit to provide the final biodegradable product to a waste container or discharge system 820.

[0106] Fig. 9A possible user interface for interacting, for example, with a processor performing the above-described method for determining a habitat descriptor value for a polymer is shown exemplarily and schematically. In this example, an input screen is shown on the left. The input screen allows the definition of a target biodegradability for one or more habitats for which a habitat descriptor value should be determined. In this example, a target biodegradability range for two different habitats is provided, wherein the biodegradability is defined as the percentage of polymer that degrades after a specified time frame of the ISO-Norm. Optionally, additional information can also be determined, such as the measurement method for the biodegradability, or how to weight different targets. Furthermore, the input screen allows the definition of the polymer for which the habitat descriptor value should be determined. In this case, for example, polyalkoxylates are defined as a polymer class by using a drop-down menu. Furthermore, further fields can be provided for further optional specifications and inputs. In this example, the polymer is then further defined below by defining its components in the form of component types and associated components, amounts and blocks. An exemplary further definition of polyalkoxylates is provided at Fig. 9 In general, the input may also involve additional information, such as habitat descriptors defining the values ​​to be determined, intended applications, measurement methods, etc. For this example, it can be seen that good prediction accuracy can be achieved when using descriptors related to polymer molar mass, descriptors related to subgroup amounts, and descriptors related to polymer hydrophilicity as polymer descriptor types. The values ​​of such polymer descriptors can then be determined according to the principles described above for defining polymers. Fig. 9 An exemplary output screen is shown on the right side of FIG. In this case, the output screen provides the results of the determination of the habitat descriptor value of the polymer and the biodegradability of the polymer in the corresponding habitat.

[0107] In a preferred embodiment, a target biodegradability is provided as a target requirement. A habitat is then selected. Based on the habitat selection, a biodegradation model is selected. This allows for separate biodegradation models for different habitats. A digital representation of the polymer that needs to be waste treated is then provided. The digital representation of biodegradation and the target value are provided as input to the biodegradation model. The model generates habitat descriptor values ​​for the habitat required to meet the target biodegradability as output. These can then be used as control data for an apparatus that controls polymer biodegradation. Assuming that a reactor is used for the biodegradation of certain polymers, the temperature, soil / water / ocean composition, and enzyme, bacteria concentration composition can be proposed.

[0108] Potential representations of biodegradability may be one or more of mineralization, which relates to whether the polymer is fully mineralized or the time it takes to reach mineralization, biotransformation, which relates to changes in the chemical structure that result in a loss of specific polymer properties, such as toxicology, or the time it takes to reach this point, and half-life, which relates to the time it takes for 50% of the polymer to decompose. The main habitats are oceans, wastewaters, and soils. For the oceans, the following parameters may have an impact on biodegradation production: salt concentration, sediment, water temperature, bacterial culture, etc. In some examples, marine habitat descriptors may be stored in a database along with the geographic location. In this case, the geographic location may be entered and the parameter values ​​associated with that geographic location may be retrieved from the database. For wastewater, the following parameters may have an impact on biodegradation production: temperature, bacterial population, bacterial type, enzyme concentration, enzymes. For soil, the following parameters may have an impact on biodegradation production: temperature, bacterial population, bacterial type, enzyme concentration, enzymes.

[0109] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

[0110] For the processes and methods disclosed herein, the operations performed in the processes and methods may be implemented in different orders. In addition, the operations outlined are provided only as examples, and some of these operations may be optional, combined into fewer steps and operations, supplemented with further operations, or expanded into additional operations without departing from the essence of the disclosed embodiments.

[0111] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0112] A single unit or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0113] The procedures performed by one or several units or devices, such as providing polymer physicochemical parameters and biodegradation models, determining habitat descriptor values, providing habitat descriptor values, etc., can be performed by any other number of units or devices. These processes can be implemented as program code components of a computer program and / or dedicated hardware.

[0114] The computer program product may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

[0115] Any unit described herein may be a processing unit as part of a classical computing system. The processing unit may include a general-purpose processor and may also include a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or any other dedicated circuit. Any memory may be a physical system memory, which may be volatile, non-volatile, or some combination of the two. The term "memory" may include any computer-readable storage medium, such as a non-volatile mass storage device. If the computing system is distributed, the processing and / or memory capabilities may also be distributed. The computing system may include multiple structures as "executable components". The term "executable component" is a structure that is well understood in the computing field as a structure that can be software, hardware, or a combination thereof. For example, when implemented in software, a person of ordinary skill in the art will understand that the structure of the executable component may include software objects, routines, methods, etc. that can be executed on the computing system. This may include executable components in the stack of the computing system or on a computer-readable storage medium. The structure of the executable component may exist on a computer-readable medium so that when interpreted by one or more processors of the computing system (e.g., by a processor thread), the computing system performs a function. Such a structure may be directly computer readable by a processor, for example, as in the case where the executable component is binary, or it may be structured to be, for example, interpretable and / or compilable, whether in a single stage or in multiple stages, so as to generate such binary that can be directly interpreted by a processor. In other instances, the structure may be a hard-coded or hard-wired logic gate that is implemented exclusively or nearly exclusively in hardware, such as in a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or any other dedicated circuit. Therefore, the term "executable component" is a term for a structure that is well understood by a person of ordinary skill in the field of computing, whether implemented in software, hardware, or a combination. Any embodiment of the present invention is described with reference to actions performed by one or more processing units of a computing system. If such actions are implemented in software, one or more processors direct the operation of the computing system in response to having executed the computer executable instructions constituting the executable component. The computing system may also include a communication channel that allows the computing system to communicate with other computing systems, such as through a network. "Network" is defined as one or more data links that enable electronic data to be transmitted between computing systems and / or modules and / or other electronic devices. When information is transferred or provided to a computing system over a network or another communications connection (e.g., hardwired, wireless, or a combination of hardwired or wireless), the computing system properly views the connection as a transmission medium. Transmission media may include networks and / or data links that may be used to carry desired program code components in the form of computer-executable instructions or data structures and which may be accessed by a general-purpose or special-purpose computing system or combination thereof.Although not all computing systems require a user interface, in some embodiments, a computing system includes a user interface system for interfacing with a user. The user interface serves as an input or output mechanism to the user, such as via a display.

[0116] Those skilled in the art will appreciate that at least parts of the present invention can be practiced in a network computing environment with many types of computing system configurations, including personal computers, desktop computers, laptop computers, message processors, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, mobile phones, PDAs, pagers, routers, switches, data centers, wearable devices (such as glasses), etc. The present invention can also be practiced in a distributed system environment, where local and remote computing systems linked, for example, by hardwired data links, wireless data links, or by a combination of hardwired and wireless data links, all perform tasks over a network. In a distributed system environment, program modules can be located in both local and remote memory storage devices.

[0117] Those skilled in the art will also appreciate that at least a portion of the present invention can be practiced in a cloud computing environment. A cloud computing environment can be distributed, although this is not required. When distributed, a cloud computing environment can be distributed internationally within an organization and / or have components owned across multiple organizations. In this specification and the following claims, "cloud computing" is defined as a model for implementing on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage devices, applications, and services). The definition of "cloud computing" is not limited to any of the other numerous advantages that can be obtained from such models when deployed. The computing system of the accompanying drawings includes various components or functional blocks that can implement various embodiments disclosed herein as explained. Various components or functional blocks can be implemented on a local computing system, or can be implemented on a distributed computing system that includes elements residing in the cloud or implementing various aspects of cloud computing. Various components or functional blocks can be implemented as software, hardware, or a combination of software and hardware. The computing system shown in the figure may include more or fewer components than those shown in the figure, and some of the components can be combined when the environment guarantees.

[0118] Any reference signs in the claims should not be construed as limiting the scope.

[0119] The present invention relates to a method for determining a habitat descriptor value providing a target biodegradability of a polymer. A target biodegradability is provided that indicates the biodegradation characteristics of the polymer. A digital representation of the polymer is provided that indicates the physicochemical characteristics of the polymer. A biodegradation habitat is provided that indicates habitat descriptors that affect the biodegradation of the polymer. A biodegradation model is provided based on the provided biodegradation habitat, the biodegradation model being suitable for determining a habitat descriptor value for the biodegradation of the polymer that allows the target biodegradability to be met in the biodegradation habitat. A habitat descriptor value for the polymer is determined based on the selected biodegradation model, the target biodegradability and the polymer descriptor.

Claims

1. A computer-implemented method for determining a habitat descriptor value that provides a target biodegradability of a predetermined polymer, wherein the method (200) comprises: providing (210) a target biodegradability, wherein the biodegradability is indicative of a biodegradation characteristic of a polymer, providing (220) a digital representation of the polymer indicative of or associated with a physicochemical property of the polymer, providing (230) a biodegradation habitat, wherein the biodegradation habitat indicates a habitat descriptor that affects biodegradation of a polymer in the corresponding habitat, wherein the habitat descriptor indicates an environmental characteristic of the habitat, providing (240) a biodegradation model based on the provided biodegradation habitat, wherein the biodegradation model is adapted to determine habitat descriptor values ​​that allow biodegradation of the polymer that meets the target biodegradability in the biodegradation habitat, wherein the biodegradation model is a data-driven model parameterized with respect to the biodegradation habitat such that it determines the habitat descriptor values ​​based on the target biodegradability and the polymer physicochemical properties, and The habitat descriptor value of the polymer is determined (250) based on the selected biodegradation model, the target biodegradability, and the polymer physicochemical properties.

2. The method of claim 1, wherein the method further comprises providing a control signal for controlling a reactor system suitable for biodegrading polymers, wherein the control signal is provided based on the determined habitat descriptor value.

3. The method according to any one of the preceding claims, wherein the biodegradation habitat refers to any one of a marine habitat, a wastewater habitat, a lake habitat, a compost habitat, an anaerobic habitat or a soil habitat.

4. The method of claim 3, wherein the biodegradation habitat is a marine habitat, and wherein the habitat descriptor is at least one of salt concentration, sedimentation type, oxygen level, location, sample depth, water temperature, nutrient concentration, pH, environment type, and microbial community.

5. The method of claim 3, wherein the biodegradation habitat is a limnological habitat, and wherein the habitat descriptor is at least one of salt concentration, sedimentation type, oxygen level, location, sample depth, water temperature, nutrient concentration, pH, environment type, and microbial community.

6. The method of claim 3, wherein the biodegradation habitat is wastewater and the habitat descriptors are at least one of water temperature, microbial flora, sludge concentration, nutrient concentration, pH, test duration, and enzyme environment.

7. The method of claim 3, wherein the biodegradation habitat is soil and the habitat descriptor is at least one of temperature, sand content, pH, water content, nutrient concentration, microbial community, and enzyme environment.

8. The method of claim 3, wherein the biodegradation habitat is a compost and the habitat descriptors are at least one of temperature, compost activity, pH, moisture content, humidity, compost maturity, compost composition, compost origin, nutrient concentration, microbial community, and enzyme environment.

9. An interface method for providing an interface, wherein the interface method comprises: receiving as input a target biodegradability, a numerical representation and a habitat via a user interface, and providing the received target biodegradability, numerical representation and the habitat to a processor performing the method according to any one of claims 1 to 8, and providing as a result the determined habitat descriptor value for the polymer, wherein the result is received from the processor performing the method according to any one of claims 1 to 8.

10. A computer-implemented training method for training a data-driven biodegradation model for parameterizing the biodegradation model, wherein the training method (300) comprises: providing (310) training data associated with a predetermined biodegradation habitat, wherein the training data comprises a) digital representations of a plurality of training polymers indicating a physicochemical property of each of the training polymers, b) habitat descriptor values ​​of the corresponding habitat descriptors of the biodegradation habitat, and c) biodegradability of the corresponding biodegradation habitat descriptor values ​​associated with each of the training polymers, Providing (320) a data-driven trainable biodegradation model, training (330) the provided data-driven biodegradation model based on the provided training data, such that the trained biodegradation model is suitable for determining habitat descriptor values ​​based on biodegradability and polymer physicochemical properties, and The trained biodegradation model is provided (340).

11. An apparatus for determining a habitat descriptor value providing a target biodegradability of a predetermined polymer, wherein the apparatus (110) comprises: a target biodegradability providing unit (111), the target biodegradability providing unit being used to provide a target biodegradability, wherein the biodegradability indicates the biodegradation characteristics of the polymer, a digital representation providing unit (112) for providing a digital representation of the polymer indicative of or associated with a physicochemical property of the polymer, a habitat providing unit (113), the habitat providing unit being used to provide a biodegradation habitat, wherein the biodegradation habitat indicates a habitat descriptor affecting the biodegradation of the polymer in the corresponding habitat, wherein the habitat descriptor indicates an environmental characteristic of the habitat, A model providing unit (114) for providing a biodegradation model based on a provided biodegradation habitat, wherein the biodegradation model is suitable for determining a habitat descriptor value that allows biodegradation of the polymer to meet the target biodegradability in the biodegradation habitat, wherein the biodegradation model is a data-driven model parameterized relative to the biodegradation habitat so that it determines the habitat descriptor value based on the target biodegradability and the polymer physicochemical properties, and a determination unit (115) for determining the habitat descriptor value of the polymer based on the selected biodegradation model, the target biodegradability and the polymer description.

12. An interface device for providing an interface, wherein the interface device comprises: an input interface unit for receiving as input via a user interface the target biodegradability, the numerical representation and the habitat, and for providing the received target biodegradability, the numerical representation and the habitat to the apparatus according to claim 11, and A result interface for providing the habitat descriptor value of the polymer as a result, wherein the result is received from the apparatus according to claim 11.

13. A training device for training a data-driven biodegradation model for parameterizing the biodegradation model, wherein the training device (120) comprises: a training data providing unit (121) for providing training data associated with a predetermined biodegradation habitat, wherein the training data comprises a) digital representations of a plurality of training polymers indicating the physicochemical properties of each of the training polymers, b) habitat descriptor values ​​of the corresponding habitat descriptors of the biodegradation habitat, and c) biodegradability of the corresponding biodegradation habitat descriptor values ​​associated with each training polymer, A trainable model providing unit (122), wherein the trainable model providing unit is used to provide a data-driven trainable biodegradation model, a training unit (123) for training the provided data-driven biodegradation model based on the provided training data, so that the trained biodegradation model is suitable for determining the habitat descriptor value based on the biodegradability and the polymer physicochemical properties, and A trained model providing unit (124) is used to provide a trained biodegradation model.

14. A computer program product for determining a habitat descriptor value providing a target biodegradability of a predetermined polymer, wherein the computer program product comprises program code means for causing an apparatus according to claim 13 to perform a method according to any one of claims 1 to 8.

15. A computer program product for training a biodegradation model, wherein the computer program product comprises program code means for causing the apparatus according to claim 11 to perform the method according to claim 11.

Images