Prediction of pesticide residues in harvested products

Description

[0001] The present invention relates to the prediction of pesticide residues in plants or plant parts intended for human and / or animal consumption, preferably in vegetables and / or fruit. The present invention relates to a method, a device, a system, and a computer program product for predicting pesticide residues.

[0002] Pesticide residues are residues of active substances (e.g. insecticides, fungicides, herbicides or other pesticides) that were used to protect plants, i.e. during plant production, and are detectable in the final product.

[0003] The use of pesticides is regulated by law in many countries and is intended to prevent any risk to animal and human health from pesticides. Specific application regulations (withdrawal periods or intervals between the last application and harvest, application quantities, and application restrictions) take the substance's properties into account and thus influence the formation and level of residues.

[0004] In many countries, foodstuffs are excluded from trade if they contain pesticides that exceed certain maximum levels set for the individual substances.

[0005] Maximum residue levels for pesticides in conventional food and feed have been harmonized in all European member states since September 1, 2008, with the entry into force of Regulation (EC) No. 396 / 2005. However, there are no globally uniform limits. Some retail chains (retailers) require their producers to use plant-based foods with pesticide residues that are (significantly) below the legal requirements. However, the requirements may vary between individual retail chains.

[0006] Pesticide residues can be determined and quantified in laboratories, for example. Numerous service providers offer contract pesticide residue determinations in food and feed. Documents CN 112 150 300 A, EP 3 346 822 A1, WO 2020 / 137085 A1, and WO 2018 / 050580 A1 describe known pesticide spraying systems.

[0007] It would be advantageous for a producer of plant-based food and feed to receive information during the cultivation of the plants about the amounts of pesticide residues to be expected in the harvested products when the producer uses a defined pesticide according to a defined application program. The producer would then be able to control the amount of pesticide residues in the harvested product to a certain extent by changing the pesticide and / or the application program. Furthermore, it would be advantageous for such a producer to know at which residue levels which retail chains would accept their products and resell them to end customers.

[0008] This object is achieved by the subject matter of the independent patent claims. Preferred embodiments can be found in the dependent patent claims, the drawings, and the present description.

[0009] A first object of the present invention is a device comprising an input unit, a control and calculation unit and an output unit wherein the control and calculation unit is configured to cause the input unit to receive and / or determine the following input information: cultivated crop, plant protection product used, number of applications of the plant protection product and the respective applied quantities, time periods between the application(s) and the time of harvest, information on the biomass of the crop that was present at the time of the application(s) of the plant protection product, environmental conditions during the cultivation of the crop, in particular during and / or after the application(s) of the plant protection product, wherein the control and calculation unit is configured to calculate a quantity of a residue of the plant protection product in and / or on the parts of the crop intended for human and / or animal consumption at the time of harvest of the crop based on the input information,wherein the control and calculation unit is configured to cause the output unit to output information on the amount of residue. ,

[0010] Another object of the present invention is a computer-implemented method comprising the steps: Receiving and / or determining input information by a computer system, wherein the input information comprises: ∘ cultivated crop, ∘ plant protection product used, ∘ number of applications of the plant protection product and the respective amounts applied, ∘ time periods between the application / applications and the time of harvest, ∘ information on the biomass of the crop that was present at the time of the application / applications of the plant protection product, ∘ environmental conditions during the cultivation of the crop, in particular during and / or after the application / applications of the plant protection product, calculating an amount of a residue of the plant protection product in and / or on the parts of the crop intended for human and / or animal consumption, preferably at the time of harvest, by the computer system, outputting information on the amount of the residue via an output unit of the computer system.

[0011] Another object of the present invention is a system comprising a first computer system comprising an input unit, a first control and calculation unit, a first transmitting and receiving unit and an output unit, a second computer system comprising a second control and calculation unit and a second transmitting and receiving unit, wherein the first control and calculation unit is configured to cause the input unit to receive and / or determine the following input information: ∘ cultivated crop, ∘ plant protection product used, ∘ number of applications of the plant protection product and the respective amounts applied, ∘ time periods between the application(s) and the harvest time, ∘ optionally: information on the biomass of the crop that was present during the application(s) of the plant protection product, ∘ optionally: environmental conditions during the cultivation of the crop, in particular during and / or after the application(s) of the plant protection product, wherein the first control and calculation unit is configured to cause the first transmitting and receiving unit to transmit the input information to the second computer system via a network, wherein the second control and calculation unit is configured,to cause the second transmitting and receiving unit to receive the input information via the network, wherein the second control and calculation unit is configured to determine the following information, in the event that the information has not already been transmitted by the first computer system: ∘ Information on the biomass of the crop that was present during the application / applications of the plant protection product and / or ∘ Environmental conditions during the cultivation of the crop, in particular during and / or after the application / applications of the plant protection product, wherein the second control and calculation unit is configured to calculate an amount of a residue of the plant protection product in and / or on the parts of the crop intended for human and / or animal consumption, preferably at the time of harvest, based on the input information, wherein the second control and calculation unit is configured,to cause the second transmitting and receiving unit to transmit the amount of the backlog to the first computer system via the network, wherein the first control and calculation unit is configured to cause the first transmitting and receiving unit to receive the amount of the backlog via the network, wherein the first control and calculation unit is configured to cause the output unit to output information on the amount of the backlog to a user.

[0012] A further subject of the present invention is a computer program product comprising a data carrier and program code stored on the data carrier, which causes a computer system, in whose working memory the program code is loaded, to carry out the following steps: Receiving and / or determining the following input information: ∘ cultivated crop, ∘ plant protection product used, ∘ number of applications of the plant protection product and the amounts applied in each case, ∘ time periods between the application / applications and the time of harvest, ∘ information on the biomass of the crop that was present at the time of the application / applications of the plant protection product, ∘ environmental conditions during the cultivation of the crop, in particular during and / or after the application / applications of the plant protection product, Calculating a quantity of a residue of the plant protection product in and / or on the parts of the crop intended for human and / or animal consumption, preferably at the time of harvesting the crop, based on the input information, Outputting information on the quantity of the residue.

[0013] The invention is explained in more detail below, without distinguishing between the subject matter of the invention (method, device, system, computer program product). Rather, the following explanations are intended to apply analogously to all subject matter of the invention, regardless of the context (method, device, system, computer program product) in which they occur.

[0014] If steps are mentioned in a particular order in this description or in the claims, this does not necessarily mean that the invention is limited to the specified order. Rather, it is conceivable that the steps could also be performed in a different order or even in parallel; unless a step builds on another step, which absolutely requires that the subsequent step be performed (which will become clear in individual cases). The specified sequences therefore represent preferred embodiments.

[0015] The present invention is carried out using one or more computer systems.

[0016] A "computer system" is an electronic data processing system that processes data using programmable computing instructions. Such a system typically includes a "computer," the unit that includes a processor for performing logical operations, and peripherals.

[0017] In computer technology, "peripherals" refers to all devices connected to a computer that serve to control the computer and / or act as input and output devices. Examples include monitors, printers, scanners, mice, keyboards, drives, cameras, microphones, speakers, etc. Internal connectors and expansion cards are also considered peripherals in computer technology.

[0018] Today's computer systems are often divided into desktop PCs, portable PCs, laptops, notebooks, netbooks and tablet PCs, and so-called handheld devices (e.g., smartphones); all of these devices can be used to implement the invention.

[0019] Inputs to the computer are made via input devices such as a keyboard, a mouse, a microphone, a network connection, an external data storage device, and / or the like. Input is also understood to include the selection of an entry from a virtual menu or a virtual list, or the clicking of a checkbox, and the like by a user of the computer system according to the invention. Outputs are typically provided via a screen (monitor), a printer, speakers, and / or by storage on a data storage device.

[0020] The device according to the invention can be implemented as such a computer system. Furthermore, the system according to the invention can comprise several such computer systems.

[0021] The present invention serves to predict the residue amount of a plant protection product in and / or on the parts of a crop intended for human and / or animal consumption, preferably at the time of harvest.

[0022] The prediction is made for a specific crop. The term "crop" refers to a plant that is purposefully cultivated as a useful plant through human intervention. For example, parts of the cultivated crop may be suitable for human and / or animal consumption. In a preferred embodiment, the crop is a fruit plant or a vegetable plant.

[0023] The cultivated plant is preferably one of the plants listed in the following encyclopedia: Christopher Cumo: Encyclopedia of Cultivated Plants: From Acacia to Zinnia, Volumes 1 to 3, ABC-CLIO, 2013, ISBN 9781598847758.

[0024] The cultivated plant is particularly preferably selected from the following list: strawberry, tomato, cucumber, pepper, radish, radish, kohlrabi, carrot, celery, fennel, patinake, pea, bean, asparagus, spinach, chard, artichoke, salsify, lettuce, iceberg lettuce, lettuce, endive, chicory, eggplant, pumpkin, courgette, lamb's lettuce, sugar beet, rhubarb, white cabbage, red cabbage, kale, Brussels sprouts, cauliflower, broccoli, raspberry, blackberry, blueberry, elderberry, cherry, apple, pear, grape, plum, mirabelle plum, peach, apricot, melon, gooseberry.

[0025] The prediction is based on information that (in more detail) specifies the crop, the pesticide, and the cultivation conditions. This information is also referred to as "input information" in this description. The term "input information" should not be understood to mean that all of this information is entered into the computer system according to the invention by a user. Rather, some of the input information can also be determined by the computer system according to the invention (based on input information) (as explained in more detail below). In this respect, the term "input" refers more to the fact that the input information is incorporated as input into the calculation of the amount of a pesticide residue.

[0026] The term "specify" is also used in this description. Depending on how an object is "specified," the term "specify" can have the meanings "input," "determine," "select," "preselect," "calculate," and / or "derive."

[0027] In a first step, the crop is specified. This is preferably done by a user entering the name of the crop or the name of the variety of the crop or a code for the crop / crop variety (e.g., according to the International Code of Nomenclature for Cultivated Plants, ICNCP for short) into the computer system according to the invention, or by selecting the relevant information about the crop from a list or menu, or by selecting a crop based on a pictorial representation of the crop (e.g., a photo or graphic).

[0028] It is also conceivable that the cultivated plant or the container in which the cultivated plant is located, or a bed in which the cultivated plant is grown, or a catalog in which the cultivated plant is listed, or packaging for the cultivated plant or for seeds for growing the cultivated plant is equipped with a machine-readable code that provides information about the cultivated plant. In such a case, the specification of the cultivated plant can consist of reading the machine-readable code with a suitable reading device and transmitting the read information about the cultivated plant to the computer system according to the invention by means of the reading device. Such a machine-readable code can be, for example, an optoelectronically readable code (e.g. barcode), 2D code (e.g. DataMatrix or QR code) or a code stored electronically in a semiconductor memory (e.g. an RFID chip).

[0029] It is also conceivable that the computer program product according to the invention is intended only for a single crop, i.e., it can only calculate / predict the amount of a plant protection product residue for a single crop or crop variety. In such a case, the step "specifying a crop" consists in a user selecting the corresponding computer program product to calculate residue amounts of one or more plant protection products in the crop for which the computer program is intended.

[0030] In a further step, information on the cultivation of the crop (also referred to in this description as cultivation parameters or cultivation conditions) can be specified.

[0031] The cultivation parameters can specify where and / or under what conditions the crop is grown. For example, it can be specified whether the crop is grown outdoors, in a polytunnel (as practiced with strawberries), in a greenhouse, or similar. Due to the largely lack of weather influence (e.g., rain), residue levels in plants cultivated in greenhouses can be higher than in outdoor cultivation.

[0032] It can be specified whether artificial irrigation is used and, if applicable, the irrigation quantities can be specified.

[0033] In particular, in the case of a greenhouse, the user can preferably specify the conditions prevailing in the greenhouse, such as temperature (air, soil), humidity (air, soil) and carbon dioxide content in the air, for example in the form of a temporal progression over the day / night, maximum value, minimum value, mean value (e.g. arithmetic mean (average)), variance, temperature sums, radiation sums and / or the like.

[0034] The above-mentioned conditions (temperatures, humidity, carbon dioxide levels, radiation levels) can of course also be specified for crops grown in the open field or in a polytunnel. These conditions are also referred to as environmental conditions in this description. Preferably, the weather conditions are recorded during the growing season of the crop. The following values ​​can be recorded: air temperature, air humidity, air pressure, wind speed, type of precipitation, amount of precipitation, solar radiation, and / or the like. For example, daily maximums, daily minimums, and / or daily averages (e.g., arithmetic means) can be recorded. Weather conditions can, on the one hand, influence the degradation behavior of an active ingredient, and, on the other hand, determine the growth behavior of the crop (the biomass at the time of application of a plant protection product).

[0035] Preferably, the geographical location of the field where the crop is grown is specified. Based on the geographical location of the field, values ​​for the environmental conditions prevailing during the growing season (current measured and / or predicted values) or typically prevailing (past averages) can then be retrieved, for example, from databases. However, it is also conceivable that only a geographical location of a field is specified and used in a machine learning model to learn a relationship between the geographical location and the calculated residue amount.

[0036] The term "field" refers to a spatially defined area of ​​the earth's surface that is used for agricultural purposes, in which crops are planted, supplied with nutrients and harvested.

[0037] The specification of the geographical position of a field can, for example, consist of specifying the country in which the field is located. It is also conceivable that a region in which the field is located is specified. Such a region can, for example, be a region with a defined climate that differs from the climate of neighboring regions. A region can be a cultivation area for a specific crop (for the definition of a cultivation area, see, for example, Journal für Kulturpflanzen, 61 (7), pp. 247-253, 2009, ISSN 0027-7479). A region can be a soil-climate space (for the definition of a soil-climate space, see, for example, Nachrichtenbl. Deut. Pflanzenschutzd., 59 (7), pp. 155-161, 2007, ISSN 0027-7479).

[0038] The specification of the geographical position of a field can further consist in specifying the geographical coordinates (geocoordinates) of at least one point located within the field or at the edge of the field. Many fields have the shape of a polygon. For such a field, the geocoordinates of the corners of the polygon can be specified. It is conceivable that, to specify the geographical position of a field, a user could draw the field boundaries on a virtual map displayed on a screen of the computer system according to the invention using a finger or an input device (e.g., a mouse).

[0039] It is conceivable that information on the cultivation of one or more crops (e.g. usual cultivation conditions) is already stored in a data memory. It is conceivable that the device or the system according to the invention reads the cultivation conditions usual for the crop from the data memory after specifying a crop and uses the read values ​​as the basis for the further calculation of the residue amount. It is further conceivable that the cultivation conditions are determined by specifying the position; for defined countries and / or regions, usual cultivation conditions can be stored in the data memory and can form the basis for the further calculation. It is also conceivable that the computer program product according to the invention is intended only for a single crop plant that is cultivated under predetermined cultivation conditions.In such a case, the step of "specifying the cultivation conditions" consists in a user selecting the appropriate computer program product.

[0040] It is conceivable that the computer system is configured to obtain information on the climate and / or weather in the region in which the field is located from a database, e.g. via a network, given knowledge of the geographical location of the field on which the crop is grown.

[0041] This climate and / or weather information can then be used to determine the amount of residue and / or the growth of the crop.

[0042] In a next step, at least one plant protection product is specified that is used, i.e. applied, in the cultivation of the specified crop.

[0043] The term "plant protection product" refers to a product used to protect plants or plant products from pests or to prevent their effects, to destroy undesirable plants or parts of plants, to inhibit undesirable plant growth or to prevent such growth, and / or to influence the life processes of plants in a manner other than nutrients (e.g., growth regulators). These growth regulators serve, for example, to increase the stability of cereals by shortening the stalk length (stalk shorteners or, more accurately, internode shorteners), improve the rooting of cuttings, reduce plant height by compression in horticulture, or prevent the germination of potatoes. Growth regulators are usually phytohormones or their synthetic analogues. Examples of other plant protection products include herbicides, fungicides, and other pesticides (e.g.,Insecticides, nematicides, molluscicides and the like).

[0044] A plant protection product typically contains one or more active ingredients. "Active ingredients" are substances that have a specific effect in an organism and induce a specific reaction. Such an active ingredient can be a synthetically produced (chemical) active ingredient or a (biological) active ingredient obtained from an organism. Combinations are also conceivable. A plant protection product typically contains a carrier to dilute the one or more active ingredients. Additives such as preservatives, buffers, dyes, and the like are also conceivable. A plant protection product can be in solid, liquid, or gaseous form.

[0045] A "pest" is defined as an organism that can appear during the cultivation of crops and damage the crop, negatively impact the crop's yield, or compete with the crop for natural resources. Examples of such pests include weeds, grass weeds, animal pests such as beetles, caterpillars, and worms, fungi, and pathogens (e.g., bacteria and viruses). Even though viruses are not considered organisms from a biological perspective, they are nevertheless considered pests for the purposes of this description.

[0046] The term "weed" (plural: weeds) refers to plants that spontaneously accompany vegetation in crop stands, grasslands, or gardens, which are not deliberately cultivated there and develop, for example, from the seed potential of the soil or via airborne migration. The term is not limited to herbs in the true sense of the word, but also includes grasses, ferns, mosses, and woody plants. In plant protection, the term "weed" (plural: weeds) is often used to clarify the distinction from herbaceous plants. In this text, the term "weed" is used as a generic term to include weeds, unless reference is made to specific weeds or weed grasses.

[0047] The term "control" means preventing the infestation of a field / crop or part thereof with one or more pests and / or preventing the spread of one or more pests and / or reducing the number of pests present.

[0048] The specification of a plant protection product is important for two reasons: Firstly, the specification of the plant protection product also specifies the substance(s) whose residue level(s) is / are to be predicted according to the invention. The substance for which a residue level is to be predicted is usually the active ingredient of the plant protection product and / or a degradation product of the active ingredient that can (also) exert a biological effect in an organism. Secondly, the degradation behavior (and thus also the residue level) is largely determined by the chemical structure of the active ingredient and, if applicable, its formulation in the plant protection product. Models of degradation behavior are available for many active substances (see, for example, Environ. Sci. Technol. 2019, 53, 5838-5847; Soulas, G. & Lagacherie, B. Biol Fertil Soils (2001) 33: 551. https: / / doi.org / 10.1007 / s003740100363; Beulke, S. & Brown, CD Biol Fertil Soils (2001) 33: 558.https: / / doi.org / 10.1007 / s003740100364; Pagel, Holge, et al., Biogeochemistry, vol. 117, 2014, pp. 185-204., www.jstor.org / stable / 24716853; https: / / www.epa.gov / pesticide-science-and-assessingpesticide-risks / guidance-calculate-representative-half-life-values).

[0049] Exponential degradation often occurs; that is, the amount of active ingredient applied decreases exponentially over time. Furthermore, the physicochemical properties of the active ingredient determine the extent to which the active ingredient is transported into edible parts via the plant's vascular system.

[0050] The specification of a plant protection product can, for example, be based on the product name of the plant protection product or another name or chemical formula for an active ingredient contained in the plant protection product.

[0051] It is also conceivable that a plant protection product is selected from a list based on a name and / or a pictorial representation (e.g. a photo of the product).

[0052] It is also conceivable that the packaging of the plant protection product contains a machine-readable code that provides information about the plant protection product and can be read by a suitable reader. As already described above, the machine-readable code can be an optoelectronically readable code and / or a code stored electronically in a semiconductor memory (e.g., an RFID tag).

[0053] It is conceivable that several plant protection products are specified which are / should be applied simultaneously or at different times.

[0054] It is also conceivable that the computer program product according to the invention is intended only for a single plant protection product, i.e., it can only calculate / predict the amount of a residue of a specific plant protection product. In such a case, the step "specifying a plant protection product" consists in a user selecting the corresponding computer program product to determine residue amounts of the plant protection product in a crop for which the computer program is intended.

[0055] Preferably, the device according to the invention and the system according to the invention are configured such that they make a preselection for the at least one plant protection agent based on the information on the cultivated crop and / or on the information on the geographical position of the field and / or on the cultivation conditions.The term "pre-selection" in the context of a plant protection product means that the device / system selects from a list of plant protection products and displays to the user those plant protection products that are commonly used on the specified crop and / or are commonly used to control pests that may occur on the specified crop, and / or those plant protection products that are effective against pests that may occur under the conditions prevailing at the geographical location of the specified field or greenhouse. A user can then select one (or more) of the pre-selected plant protection products for which a residue calculation is to be performed.It is also conceivable that only one pesticide could be considered during the pre-selection, which could then be displayed to a user.

[0056] Depending on the geographical location specified for the field, the list of preselected crop protection products can vary. Preferably, the device and system according to the invention are configured to preselect and display only those crop protection products for which there is official approval for application in the country in which the respective field is located. Corresponding information on official approvals can be stored in one or more databases, to which the computer system according to the invention can have access, e.g., via a network connection.

[0057] In a further step, the application of the plant protection product can be specified (in more detail), preferably based on application parameters. These application parameters include, for example, the type of treatment, the application rate, and at least one time or at least one period at which / in which the plant protection product is / should be and / or was applied in the specified amount. The earlier in the crop's growing season a treatment is carried out, the lower the amount of residues is usually.

[0058] It is conceivable that pesticides are applied multiple times (at different times or over different periods) during a growing season. In the case of multiple applications, the number of applications and the time interval between applications can be specified. The application rates can be the same or vary for multiple applications. The type of treatment and / or the pesticide used can also vary. The time period between the last application of a pesticide and the harvest is of great importance: pesticide residues are generally broken down over time; therefore, the longer the time since the last application, the lower the residue amount will generally be.

[0059] Preferably, the number of applications of the plant protection product and the amount applied in each case are specified. Preferably, the time intervals between the application(s) and the harvest time are specified.

[0060] The amount applied can be specified, for example, in the form of the application rate.

[0061] The "application rate" is the amount of a plant protection product required to control pests. This amount is usually expressed per area (when applied to the field), per volume unit (e.g., in a greenhouse), or per seed quantity (e.g., when seed dressing). The amount can be expressed in weight (e.g., kg) or volume (e.g., L). The amount can refer to the total amount of the plant protection product or to the active ingredient contained in the plant protection product. The larger the amount of active ingredient applied to an area, the higher the amount of residues in / on / at the crop tends to be.

[0062] If water is used to dilute a pesticide, the amount of water used can also be specified.

[0063] It is conceivable that the type of treatment of the crop with the plant protection product is specified. When specifying the type of treatment, it can be stated, for example, whether it is a treatment of the seed or of the plant at a defined stage of development. Treatments directly on the crop typically result in higher residue levels than, for example, seed treatments before sowing. Furthermore, it can be specified which plant parts are treated (e.g., leaves, fruits, and / or roots) or whether a soil treatment is taking place.

[0064] The application parameters can be entered by a user into the device or system according to the invention. Furthermore, the application parameters can be determined in whole or in part by the device or system according to the invention using the previously entered information on the crop, the geographical location of the field, the cultivation conditions, and / or the crop protection agent.

[0065] It is conceivable, for example, that the manufacturer or distributor of a plant protection product has provided information regarding when and in what quantities the plant protection product should be applied. This information can be stored in an internal or external data storage device that can be accessed by the device / system according to the invention. The device / system can therefore be configured to generate a suggestion based on the available information regarding when and in what quantities the plant protection product should be applied. The user can then accept or modify this suggestion. The accepted and / or modified data can then be used to calculate the residue quantity.

[0066] The times / periods at which / during which plant protection products are applied can, for example, also be based on the development stage of the crop. The development stage of a plant can, for example, be specified in the form of the so-called BBCH code. The abbreviation BBCH stands for B Federal Institute for Biology, the B Department of Agriculture and the CH emic industry. The extended BBCH scale for the uniform coding of the phenological development stages of monocotyledonous and dicotyledonous plants is a joint effort of the Federal Biological Research Center for Agriculture and Forestry (BBA), the Federal Plant Variety Office (BSA), the Agricultural Industry Association (IVA), and the Institute of Vegetable and Ornamental Plant Cultivation Großbeeren / Erfurt. It is conceivable that a user enters the (extended) BBCH code for the cultivated crop into the device / system. It is also conceivable that the device / system is configured to calculate the BBCH code itself. For example, it is conceivable that the user has entered the time of planting / sowing of the crop into the device / system, and the device / system calculates the BBCH code using the time of planting / sowing.

[0067] Further information used to calculate the residue amount is preferably information on the biomass of the crop present at the time of application(s) of the pesticide. If a defined application rate of a pesticide is applied, it is ideally distributed evenly across the available biomass. In other words: the more biomass there is for a defined application rate, the lower the proportion of pesticide per kilogram of crop (in the form of fruits and / or leaves and / or other plant components). To calculate the residue amount, it is therefore necessary to determine the number of crops present across which a specified amount of pesticide is distributed.

[0068] The information on the biomass of the crop present at the time of application(s) may be an indication of the actual mass of the crop present. However, it may also be information correlated with the biomass, such as the height of the crop at the time of application, the extent of the crop parallel to the soil surface, the size of plant parts such as leaves and / or fruits, the fruit mass, the diameter of fruits, and / or the like. The information on biomass is preferably average values, e.g., the arithmetic mean across a plant population in an area of ​​a field or a sub-area of ​​a field.

[0069] In a preferred embodiment, the information on the biomass of the crop plant is the average height of the crop plants in a plant stand. In a further preferred embodiment, the information on the biomass of the crop plant is the average diameter and / or volume of fruits in a plant stand. In a further preferred embodiment, the information on the biomass of the crop plant is the proportion of plants that, viewed from above (towards the center of the earth), cover the ground (e.g., a field). In a further preferred embodiment, the information on the biomass of the crop plant is the average size of the surface area of ​​the leaves of a plant stand. In a further preferred embodiment, the information on the biomass of the crop plant is a vegetation index, such as the standardized differentiated vegetation index (EN). normalized difference vegetation index or normalized density vegetation index NDVI). It is also conceivable that the information on the biomass of the crop is a combination of the above-mentioned and / or other variables / parameters.

[0070] It is also conceivable that the information on the biomass of the crop plant is specified based on the development stage of the crop plant. The development stage can be specified, for example, by a user or calculated by the device / computer system according to the invention, e.g., using a plant growth model. It is also conceivable that the information on the biomass of the crop plant is calculated directly using a plant growth model.

[0071] Such a plant growth model can, for example, be a mathematical model that describes the growth of a plant as a function of intrinsic (genetics) and / or extrinsic (environmental) factors. An overview of the creation of plant growth models is provided, for example, in the specialist books i) "Mathematical Modeling and Simulation" by Marco Günther and Kai Velten, published by Wiley-VCH Verlag in October 2014 (ISBN: 978-3-527-41217-4), and ii) " Working with Dynamic Crop Models" by Daniel Wallach, David Makowski, James W. Jones and Francois Brun., published in 2014 by Academic Press (Elsevier), USA.

[0072] Plant growth models exist for a wide variety of crops. The plant growth model typically simulates the growth of a crop population over a defined period of time. It is also conceivable to use a model based on a single plant, simulating the energy and material flows in the individual organs of the plant. Mixed models are also possible.

[0073] The growth of a cultivated plant is determined not only by the plant's genetic characteristics but also by the local weather conditions prevailing over the plant's lifetime (quantity and spectral distribution of incoming sunlight, temperature trends, precipitation amounts, wind input), the condition of the soil and the nutrient supply.

[0074] Cultivation measures already carried out (in the past) and any infestation with pests that may have occurred can also have an influence on plant growth and can be taken into account in the growth model.

[0075] The plant growth models are usually so-called dynamic process-based models (see "Working with Dynamic Crop Models" by Daniel Wallach, David Makowski, James W. Jones and Francois Brun., published in 2014 by Academic Press (Elsevier), USA), but can also be completely or partially rule-based or statistically or data-supported / empirical. The models are usually so-called point models. The models are usually calibrated so that the output reflects the spatial representation of the input. If the input is collected at a point in space or is interpolated or estimated for a point in space, it is usually assumed that the model output is valid for the entire adjacent field. The application of so-called point models calibrated at the field level to other, usually coarser scales is known (see, for example: H. Hoffmann et al.: Impact of spatial soil and climate input data aggregation on regional yield simulations. PLoS ONE 11(4): e0151782. doi:10.1371 / journal.pone.0151782).Applying these so-called point models to multiple points within a field enables site-specific modeling. However, this neglects spatial dependencies, such as those in the soil water balance. On the other hand, systems for temporally and spatially explicit modeling also exist. These systems take spatial dependencies into account.

[0076] Examples of dynamic, process-based plant growth models are Apsim, Lintul, Epic, Hermes, Monica, STICS, and others. A comparison of the models and relevant literature on the models can be found, for example, in the following publication and the references listed therein: H. Hoffmann et al.: Impact of spatial soil and climate input data aggregation on regional yield simulations. PLoS ONE 11(4): e0151782. doi: 10. 1371 / journal.pone.0151782.

[0077] The following parameters can be included in the modeling of plant growth: (a) Weather: daily precipitation totals, radiation totals, daily minimum and daily maximum air temperature as well as temperature near the ground and soil temperature, wind speed, etc. (b) Soil: soil type, soil texture, soil type, field capacity, permanent wilting point, organic carbon, mineral nitrogen content, bulk density, Van Genuchten parameters, etc. (c) Crop: species, variety, variety-specific parameters such as specific leaf area index, temperature totals, maximum root depth, etc. (d) Cultural measures: seed, sowing date, sowing density, sowing depth, fertilizer, fertilizer rate, number of fertilization dates, fertilization date, soil cultivation, crop residues, crop rotation, distance to the field of the same crop in the previous year, irrigation, etc.

[0078] With the help of a plant growth model, the amount of biomass present at a given time and / or the size of the leaf area and / or the amount of fruit (fruit mass) and / or the number of shoots present and / or the like can also be calculated. It is conceivable that a plant with more biomass and / or a larger leaf area requires a larger amount of crop protection agent than a plant with less biomass and / or a smaller leaf area. It is conceivable that the amount of biomass present - particularly in the form of fruit - at the time of application of a crop protection agent influences the amount of residue. In a preferred embodiment of the present invention, the amount of biomass of the cultivated crop present at a given time (particularly at the time of application of a crop protection agent) is therefore also included in the calculation of the amount of residue.

[0079] Remote sensing data can also be used to determine and / or predict the amount of biomass present and / or to optimize plant growth models. "Remote sensing data" is digital information obtained remotely from the Earth's surface, for example, by satellites. The use of aircraft (unmanned (drones) or manned) to collect remote sensing data is also conceivable. Remote sensing sensors generate digital images of areas of the Earth's surface from which information about the vegetation and / or environmental conditions prevailing there can be obtained (see, for example, M.S. Moran et al.: Opportunities and Limitations for Image-Based Remote Sensing in Precision Crop Management, Remote Sensing of Environment (1997) 61: 319-346). The data from these sensors is obtained via the interfaces provided by the provider and can be optical and electromagnetic (e.g.,Synthetic Aperture Radar (SAR) data sets from different processing levels.

[0080] Sensors can also be deployed in the field to determine the development stage and / or existing biomass of crops. The sensors can be positioned stationary in the field; it is also conceivable to equip agricultural machinery and / or robots moving through the field with corresponding sensors.

[0081] The times / periods at which / in which plant protection products are applied can be based on the development stages and / or the spread of pests. Prediction models are also available for the development and / or spread of pests (see, for example, WO2017 / 222722A1, WO2018 / 058821A1, US20020016676, US20180018414A1, WO2018 / 099220A1). Such models can be used to predict times at which there is a high risk of crop infestation by pests. Pest control with a plant protection product is preferably carried out when the (calculated) risk of infestation is particularly high (e.g., exceeds a defined threshold). The models for predicting infestation by a pest also typically use weather data and historical data.

[0082] In a preferred embodiment, the residue quantity is predicted on the basis of the following input information: cultivated crop, country or region in which the crop is cultivated or amount of biomass and / or fruit mass present in the cultivated crop at the time of application of the crop protection product (or a correlated value such as the diameter of a plant or fruit), crop protection product to be used or used, application rate of the crop protection product to be used or used and length of time between the time of application and the time of harvest. It is particularly advantageous if, in addition to the input information mentioned, one or more of the following additional input information relating to the weather during the cultivation phase is included in the calculation: solar radiation (e.g. in the form of hours of sunshine), humidity and / or temperature.

[0083] In a preferred embodiment, the residue quantity is calculated based on the following input information: cultivated crop plant protection product used number of applications with the crop protection product and amounts applied in each case time period between the last application and the time of harvest average air and / or soil temperature on the respective days of the applications average air humidity on the respective days of the applications accumulated radiant energy (solar radiation or artificial lighting) on ​​the respective days of the applications average diameter and / or average height of the cultivated crops on the respective days of application.

[0084] In a further preferred embodiment, the residue quantity is calculated based on the following input information: cultivated crop plant protection product used number of applications with the crop protection product and quantities applied in each case time period between the last application and the time of harvest geographical position of at least one point of the field on which the crop is grown or an indication of whether the crop is grown in a greenhouse optionally an indication of whether the crop is grown in a polytunnel average diameter and / or average height of the cultivated crops and / or average volume of fruit and / or average fruit mass on the respective application days.

[0085] The device and the system according to the invention are configured to calculate the amount of at least one residue of a plant protection agent in and / or on the crop or in and / or on a part of the crop, preferably at the time of harvest, based on the available information (input information, information derived (e.g., calculated) from the input information, and / or based on input information read from one or more data memories). If a significant reduction in the amount of residue still occurs after harvest (e.g., during storage, through washing, and / or the like), the amount of residue can (also) be calculated for a time other than the time of harvest and / or for a state following a specific treatment (e.g., washing, exposure to electromagnetic radiation, heat or cold treatment, and / or the like).

[0086] The calculation of the amount of at least one residue can be based, for example, on empirically determined data on the distribution of plant protection products in parts of the crop and on the degradation of plant protection products.

[0087] In a particularly preferred embodiment, the amount of at least one residue of a pesticide is calculated using hybrid modeling. This means that the degradation of the pesticide is based on a mathematical function whose parameters are determined using a machine learning model based on the input data. This approach is explained below using an example, without limiting the invention to this example.

[0088] As already mentioned, the degradation of many pesticides over time can be approximated by an exponential decay. Such an exponential decay can be described by the following mathematical equation: N t = N 0 ⋅ e − t τ

[0089] This is N (t) the second-dependent quantity of plant protection product in, on and / or in the parts of the crop intended for human and / or animal consumption, t indicates the time N 0 is the amount of pesticide at the time t =0 and τ is the time period in which the size N each drops to 1 / e-fold (about 37%).

[0090] If the parameters initial quantity N 0 and time constant τ known, can be determined for any point in time t the amount N ( t ) of plant protection products, e.g. for the time of harvest of the crop.

[0091] According to the present invention, the parameters of the mathematical function equation (in the present preferred example, initial set N 0 and time constant τ ) is determined using a machine learning model. This approach has the advantage that it does not require knowledge of how individual input information influences the residue quantity. Instead, a machine learning model is used that learns the relationships between the input information and the residue quantity based on numerous examples.

[0092] The machine learning model calculates the parameters of the mathematical function equation from the input information. The machine learning model can be used, for example, in a supervised learning process. supervised training ) are trained using training data to learn a relationship between the input information and the parameters of the mathematical function equation. The learned information can then be applied to new data for prediction purposes. The training data can be obtained empirically and includes pairs of input and output data. The input data represents the input information, usually in the form of a feature vector. The output data represents the parameters of the mathematical function equation, which can be determined from measured residue quantities.

[0093] In other words, it is possible to empirically determine the pesticide residue levels at harvest time, for example, for a wide variety of crops, cultivation conditions, environmental conditions, pesticides, and / or application conditions. From this empirically obtained data, the parameters of the mathematical function equation describing the temporal decay of the pesticide can be determined. Finally, the machine learning model is trained to map the input information (usually in the form of a feature vector) to the parameters of the mathematical function equation. It is not necessary to investigate and understand the specific influence of individual pieces of input information on the residue level.

[0094] In general, a feature vector (engl.: feature vector ) summarizes the (preferably numerically) parameterizable properties (features) of an object (in this case the input information) in a vectorial manner. Various features characteristic of the object form the different dimensions of this vector. The totality of all possible feature vectors is called the feature space. Many algorithms in machine learning require a numerical representation of objects, since such representations facilitate data processing and statistical analysis or even make it possible in the first place. The generation of the feature vector therefore serves to put the determined and / or received input information into a form that enables computer-assisted processing. Examples of the generation of feature vectors can be found in the state of the art (see, for example, J. Frochte: Machine Learning, 2nd ed., Hanser-Verlag 2019, ISBN: 978-3-446-45996-0).

[0095] The machine learning model can, for example, be an artificial neural network.

[0096] Such an artificial neural network comprises at least three layers of processing elements: a first layer with input neurons (nodes), an n-th layer with at least one output neuron (node) and n -2 inner layers, where n is a natural number and greater than 2.

[0097] The input neurons serve to receive the values ​​of the feature vector of the input information. In such a network, the at least one output neuron serves to output at least one parameter of the mathematical function equation. The processing elements of the layers between the input neurons and the at least one output neuron are connected to each other in a predetermined pattern with predetermined connection weights.

[0098] The neural network can be trained, for example, using a backpropagation method. The goal is to achieve the most reliable mapping possible from given input vectors to given output vectors. The quality of the mapping is described by an error function. The goal is to minimize the error function. With the backpropagation method, an artificial neural network is trained by changing the connection weights.

[0099] In the trained state, the connection weights between the processing elements contain information regarding the relationship between the input information (in the form of the feature vector) and the at least one parameter of the mathematical function equation describing the temporal decrease of the pesticide.

[0100] A cross-validation method can be used to split the data into training and validation sets. The training set is used in backpropagation training of the network weights. The validation set is used to determine the prediction accuracy of the trained network.

[0101] Details on the generation and training of artificial neural networks are described, for example, in: G. Ciaburro et al.: Neural Networks with R, Packt Publishing 2017, ISBN: 978-1-78839-787-2; T. Rashid: Make Your Own Neural Network, O'Reilly 2016, ISBN: 978-1530826605.

[0102] The determined residue quantity can be output to a user. The output occurs, for example, in the form of text and / or numbers and / or graphics on a monitor (screen) and / or printer of the device / system according to the invention.

[0103] In a preferred embodiment, the determined residue level is compared with one or more maximum levels. The at least one maximum level is, for example, an officially permitted maximum level of a residue in a crop for the respective plant protection product.

[0104] The at least one maximum quantity can also be a maximum residue level in a crop required by a dealer for the respective plant protection product. A "dealer" within the meaning of the present invention is preferably a natural or legal person who purchases crops or parts of crops from a producer or intermediary and resells them (e.g., to end customers (consumers)).

[0105] The minimum maximum quantity can also be a quantity defined by a user.

[0106] The at least one maximum quantity can be stored in one or more data storage devices which can be accessed by the device and the system according to the invention.

[0107] In a preferred embodiment, the user is shown the extent to which the determined residue quantity exceeds or falls below one or more maximum quantities. It is conceivable for the user to specify a country or region and the user is shown whether and / or the extent to which the determined residue quantity exceeds or falls below the maximum quantity permitted for the specified country or region. It is conceivable for the user to specify multiple countries / regions. It is conceivable for the user to specify a dealer and the user is shown whether and / or the extent to which the determined residue quantity exceeds or falls below the maximum quantity permitted by the specified dealer. It is conceivable for the user to specify multiple dealers.

[0108] In a preferred embodiment, the determined amount of the pesticide residue is output in the form of a percentage and / or in the form of a graphic representation of the percentage, wherein the percentage indicates the percentage share of the calculated residue amount in relation to a maximum residue amount, preferably one permitted by law or authorities and / or a maximum residue amount prescribed by a dealer. In a preferred embodiment, the user can select one or more countries / regions, and the user is shown how large the calculated residue amount is in relation to the maximum residue amount prescribed in the country / region. In a preferred embodiment, the user can select one or more dealers, and the user is shown how large the calculated residue amount is in relation to the maximum residue amount prescribed by the dealer.

[0109] In a preferred embodiment, the calculated residue level is adjusted to the maximum residue limit prescribed by an authority (" maximum residue limit ", " maximum residue level", The maximum residue limit (MRL) is the maximum permissible residue concentration. In the EU, for example, the European Medicines Agency (EMA) is responsible for recommending maximum residue levels, which, once adopted by the European Commission, become legally binding standards for food safety.

[0110] The maximum residue level is usually determined through repeated field trials (on the order of 10) in which the crop has been treated according to good agricultural practice (GAP) and an appropriate pre-harvest interval or residence time has elapsed. For many pesticides, the maximum residue level is at their detection limit (" limit of detection", LOD). The limit of quantification (" limit of quantification", LOQ) is used instead of the LOD. As a rule of thumb, the LOQ is approximately twice the LOD. For substances not included in any annex to the EU regulations, a default maximum residue level of 0.01 mg / kg normally applies (see e.g. https: / / ec.europa.eu / food / plant / pesticides / max_residue_levels_en). Instead of or in addition to the MRL, the calculated residue level can also be related to other common quantities, such as ARfD, ADI and / or TDI. The acute reference dose (" acute reference dose", ARfD) is an estimate of the amount of a substance in food or drinking water that can be ingested over a short period of time, usually during a meal or a day, without appreciable health risk to the consumer. The permissible daily intake (" acceptable daily intake", ADI) refers to the dose of a substance that is considered medically safe when taken daily throughout life. If there are unwanted contaminants, it is also referred to as a tolerated daily dose (" tolerable daily intake", TDI).

[0111] In a preferred embodiment, the device / system according to the invention is configured such that, at defined times or upon the occurrence of defined events, the residue amount calculation is updated to take into account a change in the cultivation conditions, the crop protection product, environmental conditions, and / or the application parameters. For example, an initial calculation of the residue amount can be based on a climate typical for the respective country or region in which the crop is grown. Over the course of the growing season, the calculation is then adapted to the actual prevailing weather conditions. Similarly, the calculation can be updated based on the actual applications of a crop protection product.Furthermore, an update can be based on sensor data (e.g., remote sensing data and / or field data), whereby the sensor data can, for example, provide information about the development stage of the crop and / or an expected harvest yield. Furthermore, it is conceivable that an initial calculation of the residue quantity is based on weather forecasts, while a subsequent (updated) calculation of the residue quantity is based on the actual weather.

[0112] In a preferred embodiment, the device / system according to the invention is configured so that the user can change the specified crop protection agent and / or the application parameters, whereupon the amount of a residue of the crop protection agent is recalculated and displayed. This enables the user to plan and evaluate how a change in the crop protection agent and / or the application parameters affects the amount of residue.

[0113] In a preferred embodiment, the device / system according to the invention is configured, in response to a user input for optimizing the residue amount, to modify the crop protection agent and / or the application parameters such that a minimum residue amount is achieved. During such an optimization, the user can decide, if necessary, which parameters are modifiable and which are unmodifiable. The device / system then modifies the modifiable parameters until a minimum residue amount is reached and outputs the modified parameters as well as the calculated (minimal) residue amount to the user. Methods for mathematical optimization can be found in the numerous textbooks on this topic (see, for example, Peter Gritzmann: Fundamentals of Mathematical Optimization, Springer Spektrum 2013, ISBN: 978-3-528-07290-2).

[0114] Fig. 1 shows, by way of example and schematically, an embodiment of the device according to the invention. The device (10) comprises an input unit (11), a control and calculation unit (12), and an output unit (13). A user can enter information and control commands into the device via the input unit (11). Information can be output to a user via the output unit (13), preferably displayed on a monitor. The control and calculation unit (12) is primarily used to control the components of the device (10), to process the information input and to be output, and to carry out calculations and logical operations.

[0115] The control and calculation unit (12) is configured, to cause the input unit to receive and / or determine the following input information: ∘ cultivated crop, ∘ plant protection product used, ∘ number of applications of the plant protection product and the quantities applied in each case, ∘ time periods between the application / applications and the time of harvest, ∘ information on the biomass of the crop that was present at the time of the application / applications of the plant protection product, ∘ environmental conditions during the cultivation of the crop, in particular during and / or after the application / applications of the plant protection product, to calculate a quantity of a residue of the plant protection product in and / or on the parts of the crop intended for human and / or animal consumption at the time of harvest of the crop on the basis of the input information, and to cause the output unit to output information on the quantity of the residue.

[0116] Fig. 2 shows, by way of example and schematically, a further embodiment of the device according to the invention. In addition to the input unit (11), the control and calculation unit (12) and the output unit (13) as in relation to Fig. 1 As described, the device (10) is connected, for example, via a network to a data storage device (30). The data storage device (30) can store, for example, information on crops (e.g. preferred growing conditions), on plant protection products (e.g. preferred application parameters), on the climate of a country or region, on the weather of a country or region, on the spread of pests in a country or region, and / or the like. The control and calculation unit (12) can be configured to access the information stored in the data storage device (30) and to use it to calculate the amount of residue of a plant protection product. Furthermore, the control and calculation unit (12) can be configured to store information in the data storage device (30). It is conceivable that the data storage device (30) comprises a plurality of data storage devices.Such a data storage may also contain one or more models that can be used to calculate residue levels, such as plant growth models, models for the degradation of pesticides and / or the like.

[0117] Fig. 3 shows an exemplary and schematic embodiment of the system according to the invention. The system (S) comprises a first computer system (10) and a second computer system (20). The first computer system (10) is preferably embodied as a desktop, laptop, or tablet computer, or as a smartphone. The second computer system (20) is preferably embodied as a server. The first computer system (10) is operated by a user. The first computer system (10) serves as a communication interface between the user and the system (S). The second computer system (20) serves to assume some functionalities that, in the device according to the invention, are executed by the control and calculation unit of the device. Reasons for shifting functionalities to a second computer system can be: Calculations require high computing power; these calculations are transferred to a server equipped with the appropriate computing power; calculations should always be based on the latest versions of models and current data; these latest versions of models and current data are provided via a server.

[0118] Typically, there are a plurality of first computer systems that are operated by different users, and only a second computer system or a smaller number (compared to the number of first computer systems) of second computer systems that provide / provide resources (computing power, data, models) for the plurality of first computer systems via a network or multiple networks.

[0119] The first computer system (10) comprises an input unit (11), a first control and calculation unit (12), an output unit (13), and a first transmitting and receiving unit (14). The second computer system (20) comprises a second control and calculation unit (22) and a second transmitting and receiving unit (24). The first computer system (10) and the second computer system (20) can exchange information via a network (represented by the dashed line between the first transmitting and receiving unit (14) of the first computer system (10) and the second transmitting and receiving unit (24) of the second computer system (20)). The network can comprise a mobile network, e.g., one based on the GSM, GPRS, 2G, 3G, LTE, 4G, 5G, or another standard.

[0120] The first control and calculation unit (12) is configured to receive the following input information from a user via the input unit (11): ∘ cultivated crop, ∘ plant protection product used, ∘ number of applications of the plant protection product and the quantities applied in each case, ∘ time intervals between the application(s) and the time of harvest, ∘ optional: information on the biomass of the crop that was present at the time of the application(s) of the plant protection product, ∘ optional: environmental conditions during the cultivation of the crop, in particular during and / or after the application(s) of the plant protection product,

[0121] The first control and calculation unit (12) is configured to cause the first transmitting and receiving unit (14) to transmit the input information to the second computer system (20) via the network.

[0122] The second control and calculation unit (22) is configured to cause the second transmitting and receiving unit (24) to receive the input information via the network.

[0123] The second control and calculation unit (22) is configured to determine the following information in case the information has not already been transmitted by the first computer system (10): ∘ Information on the biomass of the crop that was present at the time of application(s) of the plant protection product and / or ∘ Environmental conditions during cultivation of the crop, in particular during and / or after application(s) of the plant protection product,

[0124] This further input information can, for example, be read from one or more databases that can be connected to the second computer system (20) via a network connection and / or calculated on the basis of input information that has been transmitted by the first computer system (10) and / or on the basis of information from the one or more databases.

[0125] The second control and calculation unit (22) is configured to calculate an amount of a residue of the plant protection agent in and / or on the parts of the crop intended for human and / or animal consumption, preferably at the time of harvest, on the basis of the input information.

[0126] The second control and calculation unit (22) is configured to cause the second transmitting and receiving unit (24) to transmit the amount of residue to the first computer system (10) via the network.

[0127] The first control and calculation unit (12) is configured to cause the first transmitting and receiving unit (14) to receive the amount of residue via the network.

[0128] The first control and calculation unit (12) is configured to cause the output unit (13) to output the amount of the residue to the user.

[0129] The system (S) according to the invention can comprise one or more data storage devices. Such a data storage device can store information on crops (e.g., preferred cultivation conditions), on crop protection agents (e.g., preferred application parameters), on the climate of a country or region, on the weather of a country or region, on the spread of pests in a country or region, and the like. Such a data storage device can be a component of the first computer system (10), the second computer system (20), and / or a separate unit that can be connected to the first computer system (10) and / or the second computer system (20) via a network.

[0130] Fig. 4 shows an exemplary and schematic embodiment of the method according to the invention in the form of a flowchart. The method (100) comprises the steps: (110) Specifying a crop (120) Specifying cultivation parameters for cultivating the crop (130) Specifying a plant protection product (140) Specifying application parameters for applying the plant protection product (150) Calculating an amount of a residue of the plant protection product in and / or on the parts of the crop intended for human and / or animal consumption, preferably at the time of harvest (160) Displaying the amount of the residue to a user.

[0131] Fig. 5 shows, by way of example and schematically in the form of a flowchart, the steps executed by a computer system on which the computer program according to the invention is installed. The steps (200) include: (210) Receiving and / or determining the following information: ∘ cultivated crop, ∘ plant protection product used, ∘ number of applications of the plant protection product and the quantities applied in each case, ∘ time intervals between the application(s) and the time of harvest, ∘ information on the biomass of the crop that was present at the time of the application(s) of the plant protection product, ∘ environmental conditions during the cultivation of the crop, in particular during and / or after the application(s) of the plant protection product, (220) Calculating a quantity of a residue of the plant protection product in and / or on the parts of the crop intended for human and / or animal consumption, preferably at the time of harvest (230) Displaying the quantity of the residue to a user.

[0132] Fig. 6 shows, by way of example and schematically in the form of a flowchart, the steps executed by a computer system on which a preferred embodiment of the computer program according to the invention is installed. The steps (300) include: (310) Receiving the following input information from a user: ∘ cultivated crop, ∘ plant protection product used, ∘ number of applications of the plant protection product and the respective amounts applied, ∘ time periods between the application / applications and the time of harvest, ∘ optionally: information on the biomass of the crop that was present at the time of the application / applications of the plant protection product, ∘ optionally: environmental conditions during the cultivation of the crop, in particular during and / or after the application / applications of the plant protection product, (320) Transmitting the input information to a second computer system (330) Receiving an amount of a residue of the plant protection product in and / or on the parts of the crop intended for human and / or animal consumption from the second computer system, preferably at the time of harvest (340) Displaying the amount of the residue to a user.

[0133] Fig. 7 bis Fig. 20 show examples of displays of the computer program according to the invention on a screen of the device according to the invention or the system according to the invention.

[0134] Fig. 7 shows an example of an input mask through which a user can log in with his name (name of the user) and a password (password).

[0135] After the user has logged in, he or she may be asked to specify a field on which a crop is or will be grown. Fig. 8 shows a display of the computer program product according to the invention, indicating that no field has been specified yet ("No field created yet"). By clicking the virtual button with the ⊕ symbol, a user can start a process for specifying a new field. The process is illustrated by way of example in Fig. 9 bis Fig. 13 shown.

[0136] Fig. 9 shows an initial screen illustrating the process for specifying a new field. The name of a location (e.g., country, city, and / or street) can be entered into an input field ("Search for a location"). A section of the Earth's surface is shown on the display, either as an aerial photograph or in the form of a map. Entering the name of a location displays a section of the Earth's surface that encompasses the location. Using finger movements familiar from using smartphones, the user can pan, zoom in, or zoom out.

[0137] Furthermore, a virtual button ("Specify Point") can be used to specify a point that lies within the field or at the edge of the field. When the virtual button is clicked, such a point is placed in the center of the crosshairs. This is Fig. 10 shown. Fig. 10 shows the same display as Fig. 9 with the difference that now a first point of the field is specified.

[0138] Starting from the specified point, a user can now set (define) further points in the field. The points are connected by straight lines. This is shown in Fig. 11 und Fig. 12 shown.

[0139] The computer program can be configured to automatically calculate the size for a specified field. Fig. 13 shows the specified field and its calculated size ("0.453 hectares"). The user can assign a name to the field ("Field Name"); in this case, it is "Field D."

[0140] Fig. 14 shows another display of the computer program according to the invention. It shows that four fields named "Field A," "Field B," "Field C," and "Field D" have been created. The user can select the fields for which they would like to calculate a prediction of a pesticide residue. The virtual button with the ⊕ symbol indicates that additional fields can be specified (created in the computer program).

[0141] Fig. 15 shows another display of the computer program according to the invention. The computer program indicates to the user that no information on the cultivation of a crop and the application of a plant protection product has yet been specified ("You have no cultivation plans"). By pressing a virtual button ("Create cultivation plan"), the user can start a process for specifying the corresponding information. The process is illustrated in Fig. 16 shown.

[0142] Fig. 16 shows a display for creating a cultivation plan for a crop ("Cultivation Plan Details"). The display includes a series of input fields. In one input field, the user can give the respective cultivation plan a name ("Cultivation Plan Name"). In this case, the user has entered "Plan A" as the name. In another input field, the user can specify the crop ("Cultivation Plant"). In this case, this is done by selecting an entry from a list. In this case, the user has selected "Strawberry" as the crop. In another input field, the user can specify the crop variety ("Variety"). In this case, the user has selected "Fortuna" as the crop variety. In another input field, the user can specify the start of the cultivation period ("Start of the cultivation period"). This can be done by entering a date and / or by selecting a day in a virtual calendar.In this case, the user specified August 17, 2019, as the beginning of the growing season. In another input field, the user can specify the end of the growing season ("End of Growing Season"). This can be done by entering a date and / or selecting a day in a virtual calendar. In this case, the user specified March 30, 2020, as the end of the growing season. The end of the growing season is usually the time of harvest.

[0143] Fig. 17 shows a further display of the computer program according to the invention. Fig. 17 displays a cultivation plan named "Plan A" in an overview. The cultivation plan concerns the crop "Strawberry" of the variety "Fortuna." A field named "Field D" is specified where the crop is / should be grown. Before the computer program can calculate (predict) a residue amount of a pesticide, one or more "markets" and an "application program" for at least one pesticide ("Application Program") must be specified. By clicking the corresponding virtual button, the user can start a process for specifying a market ("Select Market") or a process for specifying an application program for at least one pesticide ("Create Application Program").

[0144] The process for specifying a market is exemplified in Fig. 18 The process for specifying an application program for at least one crop protection product is shown as an example in Fig. 19 shown.

[0145] In this example, the term "market" represents a combination of a retailer (or a retail chain) and a country. Fig. 18 shows an overview of markets sorted by country. In this case, retail chains for three countries are listed: for Germany, the retail chains "ALDI," "Schwarz-Lidl," and "Rossmann," for Poland, the retail chains "Lidl" and "Frischemarkt," and for Spain, the retail chains "Mercadona," "Lidl," and "ALDI." The user can select one or more retail chains by clicking. In this case, the user has selected the following combinations: Germany: "ALDI," Germany: "Schwarz-Lidl," Poland: "Frischemarkt," Spain: "Mercadona." The user can create additional markets by clicking the virtual button ("Create custom market").

[0146] Fig. 19 shows a display with several input fields for specifying an application program for at least one crop protection product. The crop protection product can be specified by entering a product name ("Product Name") in a first input field. In this case, the product name "Luna" was entered. In another input field, the user can enter and / or select the date of application with the crop protection product. In this case, the user specified November 17, 2019, as the date. In another input field, the user can enter the "Application Method." In this case, the user entered "Foliar Application" as the application method. In two further input fields, the user can enter the amount of crop protection product applied or to be applied ("Product Rate", "UOM" (= Unit of Measure)). In this case, the user entered a quantity of 0.75 L / ha.In another input field, the user can enter the amount of water applied ("Water rates"). In this case, the user entered a rate of 15 L / ha. In another input field, the user can enter the development stage of the crop (when applying the plant protection product) in the form of the BBCH code ("Development stage (BBCH)"). In this case, the user entered the BBCH code 1 ("Stand 1").

[0147] Fig. 20shows a display with the results of a prediction. The results are predicted for the crop "Strawberry" of the variety "Fortuna." The results are based on an application program ("Plan A") in which 0.5 L / ha of a plant protection product with the designation ("Prod. A") was applied together with 20 L / ha of water at two points in time (May 10, 2019, and July 10, 2019). As of May 10, 2019, the crop was / is at the development stage with the BBCH code 2 ("Stand 2"); as of July 10, 2019, the crop was / is at the development stage with the BBCH code 3 ("Stand 3").

[0148] The plant protection product, labeled "Prod. A," contains two active ingredients (fluopyram and trifloxystrobin). The forecast date is November 12, 2019 ("residue forecast on November 12, 2019"). The calculated (predicted) residue level for fluopyram is 0.82 mg / kg. The calculated (predicted) residue level for trifloxystrobin is 0.82 mg / kg. Both residue levels are above the MRL (0.67 mg / kg for fluopyram, 0.5 mg / kg for trifloxystrobin).

Claims

1. Device (10) comprising - an input unit (11) - a control and calculation unit (12) and - an output unit (13) wherein the control and calculation unit (12) is configured to trigger the input unit (11) to receive the following input information: - crop plant being grown, - crop protection product used, - number of applications of the crop protection product and amounts applied each time, - periods of time between the application(s) and harvesting time, - information relating to the biomass of the crop plant that was present on each application of the crop protection product, - environmental conditions during the growing of the crop plant, especially on and / or after the application(s) of the crop protection product, wherein the control and calculation unit (12) is configured to calculate an amount of a residue of the crop protection product in and / or on the parts of the crop plant intended for human and / or animal consumption at the harvesting time of the crop plant, using the input information, wherein the control and calculation unit (12) is configured to trigger the output unit (13) to output information relating to the amount of residue, wherein the amount of residue is calculated on the basis of a mathematical function relationship, wherein the mathematical function relationship describes the degradation of the crop protection product as a function of time, wherein the mathematical function equation has at least one parameter, wherein the at least one parameter is calculated with the aid of a machine learning model on the basis of input information.

2. Device (10) according to Claim 1, wherein the amount of the residue is calculated by means of an exponential function, wherein the exponential function has two parameters, a starting value and a time constant, wherein the two parameters are calculated with aid of a machine learning model based on the input information.

3. Device (10) according to either of Claims 1 and 2, wherein the machine learning model has been trained in a monitored learning method using training data to learn a correlation between the input information, preferably represented by a feature vector, and the at least one parameter of the mathematical function relationship.

4. Device (10) according to any of Claims 1 to 3, wherein the control and calculation unit (12) is configured to - ascertain a maximum amount of a residue of the crop protection product in the crop plant or parts thereof, - compare the calculated amount of the residue with the maximum amount ascertained, - trigger the output unit (13) to output the information as to whether and / or to what extent the calculated amount of the residue is above or below the maximum amount.

5. Device (10) according to any of Claims 1 to 4, wherein the control and calculation unit (12) is configured to - identify countries and / or regions for which the calculated amount of the residue does not exceed any officially approved upper limit for the residue in the crop plant or parts thereof and / or identify traders for which the calculated amount of residue does not exceed any stipulated upper limit for the residue in the crop plant or parts thereof, - trigger the output unit to output the information as to which countries and / or regions and / or traders have been identified.

6. Device (10) according to any of Claims 1 to 5, wherein the amount of the residue is displayed to a user as a proportion of a maximum amount stipulated by an official body and / or a trader.

7. Computer-implemented method comprising the steps of: - receiving and / or ascertaining input information by means of a computer system, wherein the input information includes: ∘ crop plant being grown, ∘ crop protection product used, ∘ number of applications of the crop protection product and amounts applied each time, ∘ periods of time between the application(s) and harvesting time, ∘ information relating to the biomass of the crop plant that was present on each application of the crop protection product, ∘ environmental conditions during the growing of the crop plant, especially on and / or after the application(s) of the crop protection product, - calculating an amount of a residue of the crop protection product in and / or on the parts of the crop plant intended for human and / or animal consumption, preferably at the time of harvesting, by means of the computer system, - outputting information relating to the amount of residue via an output unit of the computer system, wherein the amount of residue is calculated on the basis of a mathematical function relationship, wherein the mathematical function relationship describes the degradation of the crop protection product as a function of time, wherein the mathematical function equation has at least one parameter, wherein the at least one parameter is calculated with the aid of a machine learning model on the basis of input information.

8. Method according to Claim 7, wherein the amount of the residue is calculated by means of an exponential function, wherein the exponential function has two parameters, a starting value and a time constant, wherein the two parameters are calculated with aid of a machine learning model based on the input information.

9. Method according to Claim 7 or 8, wherein the machine learning model has been trained in a monitored learning method using training data to learn a correlation between the input information, preferably represented by a feature vector, and the at least one parameter of the mathematical function relationship.

10. System (S) comprising - a first computer system (10) comprising an input unit (11), a first control and calculation unit (12), a first transmitter and receiver unit (14) and an output unit (13), - a second computer system (20) comprising a second control and calculation unit (22) and a second transmitter and receiver unit (24), wherein the first control and calculation unit (12) is configured to trigger the input unit (11) to receive and / or ascertain the following input information: ∘ crop plant being grown, ∘ crop protection product used, ∘ number of applications of the crop protection product and amounts applied each time, ∘ periods of time between the application(s) and harvesting time, ∘ optionally: information relating to the biomass of the crop plant that was present on each application of the crop protection product, ∘ optionally: environmental conditions during the growing of the crop plant, especially on and / or after the application(s) of the crop protection product, wherein the first control and calculation unit (12) is configured to trigger the first transmitter and receiver unit (14) to transmit the input information via a network to the second computer system (20), wherein the second control and calculation unit (22) is configured to trigger the second transmitter and receiver unit (24) to receive the input information via the network, wherein the second control and calculation unit (22) is configured to ascertain the following information if the information has not already been transmitted by the first computer system (10): ∘ information relating to the biomass of the crop plant that was present on each application of the crop protection product and / or ∘ environmental conditions during the growing of the crop plant, especially on and / or after the application(s) of the crop protection product, wherein the second control and calculation unit (22) is configured to calculate an amount of a residue of the crop protection product in and / or on the parts of the crop plant intended for human and / or animal consumption, preferably at the time of harvesting, on the basis of the input information, wherein the amount of residue is calculated on the basis of a mathematical function relationship, wherein the mathematical function relationship describes the degradation of the crop protection product as a function of time, wherein the mathematical function equation has at least one parameter, wherein the at least one parameter is calculated with the aid of a machine learning model on the basis of input information, wherein the second control and calculation unit (22) is configured to trigger the second transmitter and receiver unit (24) to transmit the amount of the residue via the network to the first computer system (10), wherein the first control and calculation unit (12) is configured to trigger the first transmitter and receiver unit (14) to receive the amount of the residue via the network, wherein the first control and calculation unit (12) is configured to trigger the output unit (13) to output information relating to the amount of the residue to a user.

11. Computer program product comprising a data carrier and program code which is stored on the data carrier and which triggers a computer system, in the memory of which the program code has been loaded, to execute the following steps: - receiving and / or ascertaining the following input information: ∘ crop plant being grown, ∘ crop protection product used, ∘ number of applications of the crop protection product and amounts applied each time, ∘ periods of time between the application(s) and harvesting time, ∘ information relating to the biomass of the crop plant that was present on each application of the crop protection product, ∘ environmental conditions during the growing of the crop plant, especially on and / or after the application(s) of the crop protection product, - calculating an amount of a residue of the crop protection product in and / or on the parts of the crop plant intended for human and / or animal consumption, preferably at the time of harvesting of the crop plant, using the input information, - outputting information relating to the amount of the residue, wherein the amount of residue is calculated on the basis of a mathematical function relationship, preferably on the basis of an exponential function, wherein the mathematical function relationship describes the degradation of the crop protection product as a function of time, wherein the mathematical function equation has at least one parameter, wherein the at least one parameter is calculated with the aid of a machine learning model on the basis of input information.

12. Computer program product according to Claim 11, wherein the machine learning model has been trained in a monitored learning method using training data to learn a correlation between the input information, preferably represented by a feature vector, and the at least one parameter of the mathematical function relationship.