Method and device for predicting solubility of carbon dioxide in ionic solution and electronic equipment

Abstract

The invention provides a method and device for predicting the solubility of carbon dioxide in an ionic solution and electronic equipment, and relates to the technical field of carbon capture, utilization and storage. The method comprises the following steps: acquiring a target domain data set corresponding to a first ion solution of which the carbon dioxide solubility is to be predicted; and inputting the target domain data set into a carbon dioxide solubility prediction model to obtain a predicted value of the carbon dioxide solubility of the first ion solution under a target working condition parameter, the carbon dioxide solubility prediction model being obtained by performing domain adversarial training on a constructed transfer learning model based on the source domain data set and the target domain data set, the characteristics learned by the carbon dioxide solubility prediction model are related to the carbon dioxide solubility and are irrelevant to the data domain type, and the carbon dioxide solubility corresponding to the second ion solution is migrated to the first ion solution, so that the carbon dioxide solubility can be accurately predicted based on the carbon dioxide solubility prediction model. And the reliability of the prediction result is obviously improved.

Description

Technical Field

[0001] The present application relates to the technical field of carbon capture, utilization and storage, and in particular to a method, device and electronic equipment for predicting the solubility of carbon dioxide in an ionic solution. Background Art

[0002] As global climate change intensifies, reducing greenhouse gas emissions has become a crucial environmental governance task. Carbon dioxide (CO2), a major greenhouse gas, is being captured and stored (CCS) as a key approach to climate change mitigation. The performance of the absorbent directly impacts both capture efficiency and economic viability during CO2 capture. Traditional CO2 absorbents (such as alcoholamine solutions) suffer from volatilization, strong degradation, and high energy consumption. Ionic liquids (ILs) have emerged as promising alternative absorbents due to their unique physicochemical properties, including high thermal stability, low volatility, designability, and high CO2 solubility. To identify ILs with high CO2 absorption efficiency, systematic studies of their CO2 solubility under various conditions (such as temperature, pressure, and ionic solution structure) are necessary. Currently, CO2 solubility measurements rely primarily on experimental measurements, but these methods are time-consuming, costly, and limited in their ability to cover a wide range of ionic solution types and operating conditions. Therefore, computational modeling has become an important tool to supplement experimental studies.

[0003] In the related art, a model for predicting the carbon dioxide solubility of ionic solutions of known carbon dioxide solubility is typically trained using a training dataset of ionic solutions with known carbon dioxide solubility. This training dataset contains training samples corresponding to the same type of ionic solution. However, when using this model to predict the carbon dioxide solubility of other types of ionic solutions, the prediction results are unreliable. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, and electronic device for predicting the solubility of carbon dioxide in an ionic solution, which are used to improve the problem of unreliable prediction results when using models to predict the solubility of carbon dioxide in other types of ionic solutions in related technologies.

[0005] In a first aspect, embodiments of the present application provide a method for predicting the solubility of carbon dioxide in an ionic solution, comprising:

[0006] Obtaining a target domain data set corresponding to a first ion solution for which carbon dioxide solubility is to be predicted, the target domain data set including physical and chemical property data and target operating condition parameters corresponding to the first ion solution;

[0007] The target domain dataset is input into the carbon dioxide solubility prediction model to predict the carbon dioxide solubility, and the predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters is obtained. The carbon dioxide solubility prediction model is obtained by domain adversarial training of the constructed transfer learning model based on the source domain dataset and the target domain dataset. The features learned by the carbon dioxide solubility prediction model are related to the carbon dioxide solubility and are independent of the data domain type. The source domain dataset contains the physical and chemical property data corresponding to the second ion solution with known carbon dioxide solubility and the carbon dioxide solubility under different operating parameters. The type of the second ion solution is different from that of the first ion solution.

[0008] In one possible embodiment, the transfer learning model includes a feature extraction module, a domain discrimination module, and a prediction module, and the carbon dioxide solubility prediction model is trained in the following manner: the transfer learning model is iteratively trained until an iteration termination condition is met, wherein each round of training includes: batch data extracted from a source domain dataset constitutes a first training sample, and based on the first training sample, the parameters of the feature extraction module and the prediction module are updated so that the feature extraction module learns features related to carbon dioxide solubility; batch data extracted from the source domain dataset and batch data extracted from the target domain dataset constitute a second training sample, and based on the second training sample, the parameters of the feature extraction module and the domain discrimination module are updated so that the feature extraction module learns features that are independent of the data domain type.

[0009] In one possible embodiment, updating parameters of a feature extraction module and a prediction module based on a first training sample includes: extracting a first feature related to carbon dioxide solubility in the first training sample based on the feature extraction module; predicting the carbon dioxide solubility in the first training sample using the prediction module based on the first feature to obtain a first predicted value corresponding to the first training sample; determining a solubility loss value based on the first predicted value and the carbon dioxide solubility corresponding to the first training sample; and updating parameters of the feature extraction module and the prediction module through back propagation based on the solubility loss value to optimize the feature extraction module's ability to extract features related to carbon dioxide solubility.

[0010] In a possible implementation, determining a solubility loss value based on the first predicted value and the carbon dioxide solubility corresponding to the first training sample includes: determining a mean square error between the first predicted value and the carbon dioxide solubility corresponding to the first training sample; and determining the mean square error as the solubility loss value.

[0011] In one possible implementation, the second training sample includes a data domain type label that identifies the source of the data, and the parameters of the feature extraction module and the domain discrimination module are updated based on the second training sample, including: extracting a second feature related to the data domain type in the second training sample based on the feature extraction module; predicting the data domain type based on the second feature using the domain discrimination module to obtain a second prediction value corresponding to the second training sample; determining a data domain classification loss value based on the second prediction value and the data domain type label corresponding to the second training sample; and updating the parameters of the feature extraction module and the domain discrimination module through back propagation based on the data domain classification loss value to weaken the feature extraction module's ability to extract features related to the data domain type.

[0012] In one possible implementation, the domain discrimination module includes a gradient reversal layer, and based on the data domain classification loss value, updates the parameters of the feature extraction module and the domain discrimination module through back propagation, including: using the gradient reversal layer to invert the domain classification loss gradient corresponding to the data domain classification loss value to obtain a reverse gradient; returning the reverse gradient to the feature extraction module to update the extraction parameters of the feature extraction module so that the feature extraction module extracts features that are difficult for the domain discrimination module to distinguish; returning the domain classification loss gradient to the domain discrimination module to update the domain discrimination parameters corresponding to the domain discrimination module to improve the domain discrimination ability of the domain discrimination module.

[0013] In one possible implementation, determining a data domain classification loss value based on the data domain type label corresponding to the second prediction value and the second training sample includes: determining a cross entropy loss value corresponding to the data domain type label corresponding to the second prediction value and the second training sample; and determining the cross entropy loss value as a data domain classification loss value.

[0014] In a second aspect, an embodiment of the present application provides a device for predicting the solubility of carbon dioxide in an ionic solution, comprising:

[0015] An acquisition module is used to acquire a target domain data set corresponding to a first ion solution for which carbon dioxide solubility is to be predicted, wherein the target domain data set includes physical and chemical property data and target operating condition parameters corresponding to the first ion solution;

[0016] A processing module is used to input the target domain dataset into the carbon dioxide solubility prediction model to predict the carbon dioxide solubility, and obtain the predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters. The carbon dioxide solubility prediction model is obtained by performing domain adversarial training on the constructed transfer learning model based on the source domain dataset and the target domain dataset. The features learned by the carbon dioxide solubility prediction model are related to the carbon dioxide solubility and are independent of the data domain type. The source domain dataset contains the physical and chemical property data corresponding to the second ion solution with known carbon dioxide solubility and the carbon dioxide solubility under different operating parameters. The type of the second ion solution is different from the type of the first ion solution.

[0017] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0018] Memory for storing computer-executable instructions;

[0019] A processor is configured to execute computer-executable instructions stored in a memory to implement the method described in any one of the first aspects.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed, they are used to implement any of the methods described in the first aspect.

[0021] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which implements the method described in any one of the first aspects when executed.

[0022] The embodiments of the present application provide a method, device, and electronic device for predicting the solubility of carbon dioxide in an ionic solution. The method obtains a target domain dataset corresponding to a first ionic solution for which the solubility of carbon dioxide is to be predicted, wherein the target domain dataset includes physical and chemical property data and target operating parameters corresponding to the first ionic solution. The target domain dataset is input into a carbon dioxide solubility prediction model to predict the solubility of carbon dioxide, and a predicted value of the solubility of carbon dioxide under the target operating parameters corresponding to the first ionic solution is obtained. The carbon dioxide solubility prediction model is obtained by performing domain adversarial training on a constructed transfer learning model based on a source domain dataset and a target domain dataset. The features learned by the carbon dioxide solubility prediction model are related to the solubility of carbon dioxide and are independent of the data domain type. The source domain dataset includes physical and chemical property data corresponding to a second ionic solution with known carbon dioxide solubility and the solubility of carbon dioxide under different operating parameters. The type of the second ionic solution is different from that of the first ionic solution. In this process, a transfer learning model was constructed by using a transfer learning algorithm, and domain adversarial training was used to train the transfer learning model to obtain a trained carbon dioxide solubility prediction model. The carbon dioxide solubility prediction model learns features related to carbon dioxide solubility and independent of the data domain type, and realizes the migration of the carbon dioxide solubility corresponding to the second ion solution with known carbon dioxide solubility to the first ion solution (i.e., the new type of ion solution). Therefore, the carbon dioxide solubility in the first ion solution can be accurately predicted based on the carbon dioxide solubility prediction model, significantly improving the reliability of the carbon dioxide solubility prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0024] Figure 1 A schematic diagram of an application scenario of a method for predicting the solubility of carbon dioxide in an ionic solution provided by an exemplary embodiment of the present application;

[0025] Figure 2 A schematic flow chart of a method for predicting the solubility of carbon dioxide in an ionic solution provided by an exemplary embodiment of the present application;

[0026] Figure 3 A schematic diagram of a transfer learning model provided by an exemplary embodiment of the present application;

[0027] Figure 4 Another schematic flow chart of a method for predicting the solubility of carbon dioxide in an ionic solution provided by an exemplary embodiment of the present application;

[0028] Figure 5 A schematic diagram comparing prediction results corresponding to different models provided in an exemplary embodiment of the present application;

[0029] Figure 6 A schematic structural diagram of a device for predicting the solubility of carbon dioxide in an ionic solution provided by an exemplary embodiment of the present application;

[0030] Figure 7 A schematic structural diagram of an electronic device provided as an exemplary embodiment of the present application.

[0031] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0032] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0033] The terms "first", "second" etc. in the specification and claims of the present application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable in appropriate circumstances, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, system, product or equipment comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, products or equipment.

[0034] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and corresponding operation entrances must be provided for users to choose to authorize or refuse.

[0035] First, let’s explain the terms involved in this application:

[0036] Transfer learning: It is an important branch of machine learning and has received widespread attention in image recognition and natural language processing. Its goal is to transfer the knowledge learned from one or more tasks to another task to solve different but related problems.

[0037] Domain adaptation is a method within transfer learning that is applicable in scenarios where there are two data domains: a source domain and a target domain. The source domain has a large amount of labeled data, while the target domain has no labeled data. The source and target domains share common features and categories, but their feature distributions differ. Domain adaptation aims to learn models using the information-rich source domain data and apply them to the target domain. The most common approach to domain adaptation is to map the data from the source and target domains into the same feature space, aligning their feature distributions as closely as possible. This allows information learned from the source domain to be applied to the target domain.

[0038] In the related art, when a training data set of ionic solutions with known carbon dioxide solubility is used to train a carbon dioxide solubility prediction model, since the training data only covers a specific type of ionic solution, the features and rules learned by the model are limited to the range of this type of ionic solution, and it is difficult to cover the complex influencing factors and changing rules of carbon dioxide solubility in other types of ionic solutions. Therefore, when the model faces a new type of ionic solution that is significantly different from the training data, it is unable to effectively transfer the learned knowledge and thus cannot accurately predict its carbon dioxide solubility, resulting in unreliable prediction results. In addition, the inventors found during the research process that in recent years, many carbon dioxide solubility prediction models have been proposed, and according to the design principles, there are also two other categories: 1) methods based on thermodynamic models, such as PSRK (Predictive Soave-Redlich-Kwong) or statistical correlation fluid theory based on group contribution, etc., but these methods only consider some of the influencing factors, resulting in low accuracy of the prediction results, affecting their reliability; 2) methods based on quantitative structure-property relationships (Quantitative Structure-Property Relationships). Relationships (QSPR), such as the Group Contribution (GC) method, assumes that the carbon dioxide solubility of an ionic solution is equal to the sum of the carbon dioxide solubility contributions of all its groups, and that the group contribution to carbon dioxide remains unchanged in any ionic solution. By establishing a linear relationship between the molecular groups and the properties of ionic solutions, these methods are widely used to predict the physical and chemical properties of ionic solutions, such as heat capacity, viscosity, and carbon dioxide solubility. However, due to the complexity of ionic interactions in ionic solutions, there are cases where the prediction results are unreliable.

[0039] Based on the above, an embodiment of the present application provides a solution for predicting the solubility of carbon dioxide in an ionic solution, obtains a target domain data set of a first ionic solution to be predicted, and uses a source domain data set (including data of a second ionic solution with known carbon dioxide solubility) and a target domain data set. Based on transfer learning and a neural network algorithm, a carbon dioxide solubility prediction model is obtained through domain adversarial training, so that the model can learn features related to carbon dioxide solubility and unrelated to the data domain type, thereby achieving the purpose of migrating the carbon dioxide solubility information of the second ionic solution with known carbon dioxide solubility to the first ionic solution to be predicted, thereby achieving accurate prediction of the carbon dioxide solubility in the first ionic solution based on the carbon dioxide solubility prediction model, significantly improving the reliability of the carbon dioxide solubility prediction results.

[0040] Figure 1 Schematic diagram of the application scenario of the method for predicting the solubility of carbon dioxide in ionic solution provided by the exemplary embodiment of this application. Figure 1As shown, the application scenario includes a client 11 and a server 12, wherein the number of clients 11 can be at least one. In practical applications, for example, after researchers and other relevant personnel obtain a target domain dataset corresponding to a first ion solution whose carbon dioxide solubility is to be predicted, they send the target domain dataset to the server 12 through the client 11; when the server 12 detects the target domain dataset sent by the user through the client 11, it executes the carbon dioxide solubility prediction method in the ion solution provided in the present application, obtains a predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters, and sends the predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters to the client 11, thereby allowing relevant personnel to obtain the predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters.

[0041] It should be noted that the server 12 may also be replaced by a server cluster or other computing devices with a certain computing power. The client 11 may be a mobile phone, a computer, a notebook or a personal digital assistant (PDA).

[0042] The following combination Figure 1 For application scenarios, refer to Figure 2 To describe the method for predicting the solubility of carbon dioxide in ionic solution according to an exemplary embodiment of the present application. It should be noted that the above application scenario is only shown to facilitate understanding of the spirit and principle of the present application, and the embodiments of the present application are not affected by Figure 1 Limitations of the application scenario shown.

[0043] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0044] Figure 2 A flow chart of a method for predicting the solubility of carbon dioxide in an ionic solution provided by an exemplary embodiment of the present application. Figure 2 As shown, the method for predicting the solubility of carbon dioxide in an ionic solution in an embodiment of the present application includes the following steps:

[0045] S201 : Acquire a target domain data set corresponding to a first ion solution whose carbon dioxide solubility is to be predicted, where the target domain data set includes physical and chemical property data and target operating condition parameters corresponding to the first ion solution.

[0046] For example, assuming the first ion solution for which carbon dioxide solubility is to be predicted is [C2mim][Tf2N], a target domain dataset corresponding to [C2mim][Tf2N] is obtained. The physicochemical property data in the target domain dataset include, but are not limited to, group type, group number, surface tension, density, critical temperature, and critical pressure. The target operating parameters in the target domain dataset include, but are not limited to, target temperature and target pressure.

[0047] S202. Input the target domain dataset into the carbon dioxide solubility prediction model to predict the carbon dioxide solubility, and obtain the predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters. The carbon dioxide solubility prediction model is obtained by performing domain adversarial training on the constructed transfer learning model based on the source domain dataset and the target domain dataset. The features learned by the carbon dioxide solubility prediction model are related to the carbon dioxide solubility and are independent of the data domain type. The source domain dataset contains physical and chemical property data corresponding to a second ion solution with known carbon dioxide solubility and the carbon dioxide solubility under different operating parameters. The type of the second ion solution is different from the type of the first ion solution.

[0048] Among them, Domain Adversarial Training (DAT) is a transfer learning technology that aims to enable the model to learn features that are independent of the data domain type, thereby achieving knowledge transfer and generalization between different but related data domains (such as source domain and target domain).

[0049] For example, assuming the second ionic solution contains three types: [bmmim][Tf2N], [BMP][Tf2N], and [C8mim][TfO], the corresponding physicochemical property data for each ionic solution and the CO2 solubility under different operating parameters constitute the source domain dataset corresponding to the second ionic solution. Accordingly, a pre-built transfer learning model is trained on the source and target domain datasets through domain adversarial training to obtain a trained CO2 solubility prediction model. The features learned by the CO2 solubility prediction model are related to CO2 solubility and are independent of the data domain type. Correspondingly, the target domain dataset is input into the CO2 solubility prediction model to perform CO2 solubility prediction, obtaining a predicted CO2 solubility value for the first ionic solution under the target operating parameters.

[0050] Optionally, before performing domain adversarial training on the pre-built transfer learning model, the method further includes: performing preprocessing operations on the source domain dataset and the target domain dataset respectively, and the preprocessing operations include but are not limited to data cleaning and standardization. For example, in the data cleaning stage, the source domain dataset and the target domain dataset are checked and corrected to eliminate outliers, missing values ​​and other potential data quality issues. Outliers may be caused by errors in the data collection process or extreme conditions in specific scenarios, while missing values ​​may be caused by incomplete data records or certain special conditions. By effectively identifying and processing these outliers and missing values, the quality of the data can be significantly improved, laying a solid foundation for subsequent model training; accordingly, in the standardization stage, the features in the source domain dataset and the target domain dataset are uniformly scaled to ensure that the contribution of each feature in the model is relatively balanced. Standardization can eliminate the potential impact of scale differences between different features on model performance, allowing the model to focus more on the intrinsic correlation and laws between features, thereby improving the accuracy and stability of predictions.

[0051] The present invention provides a method for predicting the solubility of carbon dioxide in ionic solutions. The method uses a transfer learning algorithm to construct a transfer learning model and uses domain adversarial training to train the transfer learning model to obtain a trained carbon dioxide solubility prediction model. The model learns features related to carbon dioxide solubility and independent of the data domain type, thereby transferring the carbon dioxide solubility corresponding to a second ionic solution with known carbon dioxide solubility to a first ionic solution (i.e., a new type of ionic solution). This method enables accurate prediction of the carbon dioxide solubility in the first ionic solution based on the carbon dioxide solubility prediction model, significantly improving the reliability of the carbon dioxide solubility prediction results. In addition, this prediction method fills the current gap in the field of effective prediction of carbon dioxide solubility in new types of ionic solutions, effectively expanding the application scope of computational models and making the application of computational models more practical and feasible. Furthermore, the carbon dioxide solubility prediction model obtained in this manner can serve as an important tool for finding efficient carbon dioxide absorption solutions. It can help experimenters quickly obtain predicted carbon dioxide solubility values ​​for new types of ionic solutions under various working conditions, significantly accelerating the design and development process of new types of ionic solutions, which has positive significance for promoting the development of carbon capture, utilization, and storage technologies.

[0052] In some embodiments, the transfer learning model includes a feature extraction module, a domain discrimination module, and a prediction module, and the carbon dioxide solubility prediction model is trained in the following manner: the transfer learning model is iteratively trained until an iteration termination condition is met, wherein each round of training includes: batch data extracted from a source domain dataset constitutes a first training sample, and based on the first training sample, the parameters of the feature extraction module and the prediction module are updated so that the feature extraction module learns features related to carbon dioxide solubility; batch data extracted from the source domain dataset and batch data extracted from the target domain dataset constitute a second training sample, and based on the second training sample, the parameters of the feature extraction module and the domain discrimination module are updated so that the feature extraction module learns features that are independent of the data domain type.

[0053] For example, Figure 3 A schematic diagram of a transfer learning model provided by an exemplary embodiment of this application. Figure 3 As shown, the transfer learning model 30 includes a feature extraction module 31, a domain discrimination module 32 and a prediction module 33, wherein:

[0054] a feature extraction module 31 for learning and extracting features related to carbon dioxide solubility from input sample data;

[0055] The domain discrimination module 32 is used to determine whether the input sample data belongs to the source domain or the target domain, so as to assist the model in learning domain-invariant features;

[0056] The prediction module 33 is configured to output a predicted value of carbon dioxide solubility corresponding to the input sample based on the features extracted by the feature extraction module.

[0057] For example, the parameters of the feature extraction module 31, the domain discrimination module 32 and the prediction module 33 are initialized, for example, random initialization or pre-trained weight initialization can be used; and the iteration termination conditions are set, such as setting the maximum number of iterations, the performance index of the model reaches a preset threshold, or the loss function value no longer decreases significantly, etc. as the iteration termination conditions; further, the transfer learning model is iteratively trained. Among them, each round of training includes the following steps: batch data extracted from the source domain dataset constitutes the first training sample, and the parameters of the feature extraction module and the prediction module are updated based on the first training sample, so that the feature extraction module learns features related to carbon dioxide solubility; batch data extracted from the source domain dataset and batch data extracted from the target domain dataset constitute the second training sample, and the parameters of the feature extraction module and the domain discrimination module are updated based on the second training sample, so that the feature extraction module learns features that are not related to the data domain type; after each round of training, check whether the preset iteration termination condition is met; if so, stop training, save the parameters of the current transfer learning model as the final parameters of the carbon dioxide solubility prediction model, and output the carbon dioxide solubility prediction model: use the carbon dioxide solubility prediction model to predict carbon dioxide solubility for samples in the target domain dataset; if not, continue training until the preset iteration termination condition is met.

[0058] In some embodiments, updating the parameters of the feature extraction module and the prediction module based on the first training sample includes: extracting a first feature related to the solubility of carbon dioxide in the first training sample based on the feature extraction module; predicting the solubility of carbon dioxide in the first training sample based on the first feature using the prediction module to obtain a first prediction value corresponding to the first training sample; determining a solubility loss value based on the first prediction value and the solubility of carbon dioxide corresponding to the first training sample; and updating the parameters of the feature extraction module and the prediction module through back propagation based on the solubility loss value to optimize the feature extraction module's ability to extract features related to carbon dioxide solubility.

[0059] For example, a first training sample is input into the transfer learning model. The feature extraction module receives the input data and extracts features related to carbon dioxide solubility through a fully connected layer to obtain a first feature. For example, the function form of the fully connected layer in the feature extraction module can be expressed as:

[0060]

[0061]

[0062] in, Is the output, for example, output the first feature f(.) is the Rectified Linear Unit (ReLU) activation function, W is the weight, b is the bias, and x is the input. The feature extraction module also includes a regularization layer, which adjusts the distribution of activation values ​​in each layer to ensure appropriate breadth. This facilitates rapid learning of the transfer learning model without excessive reliance on initial values, thus mitigating the risk of overfitting.

[0063] Accordingly, the first feature extracted Input to the prediction module, which contains a fully connected layer of neurons. The function form corresponding to the fully connected layer can be expressed as:

[0064]

[0065] in, is the output, corresponding to the predicted value of carbon dioxide solubility; based on the predicted value of carbon dioxide solubility and the carbon dioxide solubility corresponding to the first training sample, the solubility loss value is determined; further, based on the solubility loss value, the parameters of the feature extraction module and the prediction module are updated through back propagation to optimize the feature extraction module's ability to extract features related to carbon dioxide solubility. For example, if temperature and pressure have a greater impact on solubility, after the parameters are updated, the feature extraction module may pay more attention to the extraction of these features. Through multiple iterations, the transfer learning model gradually extracts features that are highly correlated with solubility, such as temperature-pressure interaction features.

[0066] In the embodiment of the present application, by calculating the solubility loss value and back-propagating the updated parameters, the transfer learning model can gradually optimize the feature extraction module's ability to extract features related to carbon dioxide solubility, thereby significantly improving the performance of the transfer learning model.

[0067] In some embodiments, determining a solubility loss value based on the first predicted value and the carbon dioxide solubility corresponding to the first training sample includes: determining a mean square error between the first predicted value and the carbon dioxide solubility corresponding to the first training sample; and determining the mean square error as the solubility loss value.

[0068] For example, the solubility loss value satisfies the following formula:

[0069]

[0070] Where n is the total number of samples, is the actual value of carbon dioxide solubility corresponding to the i-th sample, is the predicted value of carbon dioxide solubility corresponding to the i-th sample, is the solubility loss value.

[0071] In the embodiment of the present application, by adopting the mean square error as the calculation formula for the solubility loss value, the degree of deviation between the predicted value and the true value can be intuitively quantified, providing a clear optimization direction for model training; in addition, its square penalty mechanism can effectively suppress abnormal error interference, help enhance the stability of the model under complex data, and improve the accuracy and reliability of carbon dioxide solubility prediction.

[0072] Based on the above embodiments, in some embodiments, the second training sample includes a data domain type label that identifies the source of the data, and the parameters of the feature extraction module and the domain discrimination module are updated based on the second training sample, including: extracting a second feature related to the data domain type in the second training sample based on the feature extraction module; based on the second feature, using the domain discrimination module to predict the data domain type to obtain a second prediction value corresponding to the second training sample; determining a data domain classification loss value based on the second prediction value and the data domain type label corresponding to the second training sample; based on the data domain classification loss value, updating the parameters of the feature extraction module and the domain discrimination module through back propagation to weaken the feature extraction module's ability to extract features related to the data domain type.

[0073] For example, the second training sample contains a data domain type label that identifies the source of the data. For example, the data domain type label corresponding to each sample from the source domain dataset is 0, indicating that the sample originates from the source domain dataset; the data domain type label corresponding to each sample from the target domain dataset is 1, indicating that the sample originates from the target domain dataset. When training the model, the second training sample of each round contains N1 samples from the source domain dataset and N2 samples from the target domain dataset, where N1=N2. Correspondingly, the second training sample is input into the transfer learning model. The feature extraction module receives the input second training sample and extracts features related to the data domain type through the fully connected layer to obtain the second feature. ; Accordingly, the second feature The data is input into the domain discrimination module, and the domain discrimination module outputs the data domain type prediction value corresponding to the second training sample through a fully connected layer containing two neurons (the functional form is the same as the carbon dioxide solubility output layer); based on the data domain type prediction value and the data domain type label corresponding to the second training sample, the data domain classification loss value is determined; further, based on the data domain classification loss value, the parameters of the feature extraction module and the domain discrimination module are updated through back propagation. Specifically, during the training process, by dynamically adjusting the adversarial learning objectives of the feature extraction module and the domain discrimination module, the feature extraction module is guided to gradually weaken the ability to extract features related to the data domain type, while enhancing the sensitivity of the domain discrimination module to data domain differences.

[0074] The domain label output layer for outputting data domain type labels is a fully connected layer containing two neurons, and its function representation is, for example, the same as that of the carbon dioxide solubility output layer.

[0075] In an embodiment of the present application, by using a second training sample with a data domain type label to update the parameters of the feature extraction module and the domain discrimination module, the model can dynamically strip off redundant features that are strongly related to the data source (such as differences in experimental equipment or sampling bias, etc.), while strengthening the ability to extract task-related features that are common across domains (such as physical and chemical factors affecting solubility). This adversarial training mechanism reversely constrains the feature extraction module through the classification pressure of the domain discrimination module, so that the model reduces its sensitivity to the data domain while improving the generalization performance of the target task (such as solubility prediction), further enhancing the stability and prediction accuracy of the model in unseen data domains.

[0076] In some embodiments, the domain discrimination module includes a gradient reversal layer, which updates the parameters of the feature extraction module and the domain discrimination module through back propagation based on the data domain classification loss value, including: using the gradient reversal layer to invert the domain classification loss gradient corresponding to the data domain classification loss value to obtain a reverse gradient; returning the reverse gradient to the feature extraction module to update the extraction parameters of the feature extraction module so that the feature extraction module extracts features that are difficult for the domain discrimination module to distinguish; returning the domain classification loss gradient to the domain discrimination module to update the domain discrimination parameters corresponding to the domain discrimination module to improve the domain discrimination ability of the domain discrimination module.

[0077] For example, adversarial feature alignment can be achieved by using a gradient reversal layer in the domain discrimination module. Specifically, during the forward propagation phase, the gradient reversal layer does not transform the input data, ensuring lossless feature transfer. During the backward propagation phase, the gradient reversal layer multiplies the gradient from the domain discrimination module by a negative hyperparameter, thereby reversing the gradient direction. Without the gradient reversal layer, over training iterations, the feature extraction module gradually learns features that distinguish the source and target domains (such as device noise and sampling patterns), resulting in a model that is highly sensitive to the data domain and difficult to generalize to new data domains. However, with the gradient reversal layer, the gradient direction is reversed, forcing the feature extraction module to learn features that cannot be effectively distinguished by the domain discrimination module. During model training, the feature extraction module learns features related to CO2 solubility while also learning features unrelated to the data domain type, gradually aligning the feature distributions of the source and target domains. Ultimately, the model is able to extract features that are strongly correlated with CO2 solubility but unrelated to the data domain type, maintaining stable prediction performance in cross-domain scenarios.

[0078] Accordingly, the corresponding function can be expressed as:

[0079]

[0080] in, is the output during forward propagation; is the input; α is a hyperparameter; during back propagation, the gradient I is multiplied by -α to obtain the reverse gradient .

[0081] Correspondingly, the reverse gradient Back to the feature extraction module, update its parameters, so that the feature extraction module can extract features that are difficult for the domain discrimination module to distinguish; and the original domain classification loss gradient The data is sent back to the domain discrimination module to update its parameters to improve the domain discrimination ability of the domain discrimination module.

[0082] In the embodiment of the present application, by introducing a gradient reversal layer, during back propagation, the feature extraction module receives the inverted gradient, prompting it to generate features that confuse the domain discriminator and weaken the data domain-related features, while the domain discriminator is updated normally to improve the discrimination ability; this dynamic confrontation forces the model to gradually strip away data domain-specific features and strengthen the extraction of general features that are not related to the data domain, thereby effectively improving the generalization performance of the model on new data domains.

[0083] In some embodiments, determining a data domain classification loss value based on the data domain type label corresponding to the second prediction value and the second training sample includes: determining a cross entropy loss value corresponding to the data domain type label corresponding to the second prediction value and the second training sample; and determining the cross entropy loss value as a data domain classification loss value.

[0084] For example, the cross entropy loss value satisfies the following formula:

[0085]

[0086] Where y is the data domain type label, which takes a value of 0 or 1; It is the data domain type prediction value, that is, the second prediction value, which ranges from (0, 1). The closer it is to 1, the greater the probability that the corresponding sample is derived from the target domain dataset. The closer it is to 0, the greater the probability that the corresponding sample is derived from the source domain dataset.

[0087] Figure 4 Another flow chart of the method for predicting the solubility of carbon dioxide in an ionic solution provided by an exemplary embodiment of the present application. Figure 4 As shown, the method for predicting the solubility of carbon dioxide in an ionic solution in an embodiment of the present application includes the following steps:

[0088] S401 : Acquire a target domain data set corresponding to a first ion solution whose carbon dioxide solubility is to be predicted, where the target domain data set includes physical and chemical property data and target operating condition parameters corresponding to the first ion solution.

[0089] S402 : Acquire a source domain data set corresponding to a second ionic solution with known carbon dioxide solubility, where the source domain data set includes physical and chemical property data of the second ionic solution and carbon dioxide solubility under different operating parameters.

[0090] The type of the second ion solution is different from the type of the first ion solution.

[0091] S403: Perform domain adversarial training on the constructed transfer learning model based on the source domain dataset and the target domain dataset.

[0092] For example, the transfer learning model is iteratively trained, wherein each round of training includes: batch data extracted from the source domain dataset constitutes a first training sample, and based on the first training sample, the parameters of the feature extraction module and the prediction module are updated so that the feature extraction module learns features related to the solubility of carbon dioxide; batch data extracted from the source domain dataset and batch data extracted from the target domain dataset constitute a second training sample, and based on the second training sample, the parameters of the feature extraction module and the domain discrimination module are updated so that the feature extraction module learns features that are independent of the data domain type.

[0093] S404: Determine whether the iteration termination condition is met.

[0094] The iteration termination conditions include but are not limited to reaching the maximum number of iterations, the performance index of the model reaching a preset threshold, or the loss function value no longer decreasing significantly.

[0095] If yes, execute S405;

[0096] If not, execute S403.

[0097] S405 , inputting the target domain data set into a carbon dioxide solubility prediction model to perform carbon dioxide solubility prediction, and obtaining a predicted value of carbon dioxide solubility of the first ion solution under target operating parameters.

[0098] For example, assuming that the first ion solution for which the carbon dioxide solubility is to be predicted is [bmmim][Tf2N], its corresponding physicochemical property data and target operating parameters constitute the target domain data set; 19 other types of ion solution data such as [BMP][Tf2N], [C2mim][Tf2N], [C2mim][TfO] and [C3mpy][Tf2N] are used as the second ion solution for which the carbon dioxide solubility is known, and the physicochemical property data corresponding to the second ion solution and the carbon dioxide solubility under different operating parameters constitute the source domain data set; based on the source domain data set and the target domain data set, the carbon dioxide solubility prediction model proposed in this application is trained, for example, Figure 5The model named Ours in the paper. To prove the effectiveness of the carbon dioxide solubility prediction model, the same data was used to train the Bayesian Ridge Regression model (BR), Support Vector Regression model (SVR), Gradient Boosting Regression model (GB), Random Forest Regression model (RF) and Neural Network model (NN) without transfer learning module, and used them to predict the carbon dioxide solubility corresponding to the target domain data set, and the mean square error was used as the evaluation index of each prediction result. The smaller the error, the more accurate the prediction result of the model. Figure 5 As shown, the mean square error corresponding to the model named Ours is the smallest, indicating that the prediction result obtained by using the carbon dioxide solubility prediction model in the above embodiment is more accurate, and the reliability of the carbon dioxide solubility prediction result is significantly improved.

[0099] In summary, this application has at least the following advantages:

[0100] First, by using a transfer learning algorithm to construct a transfer learning model and training it using domain adversarial learning, a trained CO2 solubility prediction model is obtained. This model learns features related to CO2 solubility that are independent of the data domain type, enabling the CO2 solubility corresponding to a second ion solution with known CO2 solubility to be transferred to a first ion solution (i.e., a new type of ion solution). This allows for accurate prediction of CO2 solubility in the first ion solution based on the CO2 solubility prediction model, significantly improving the reliability of the CO2 solubility prediction results. Furthermore, this prediction method fills the current gap in the field of effective CO2 solubility prediction in new types of ion solutions, effectively expanding the application scope of computational models and making their application more practical and feasible. Furthermore, the CO2 solubility prediction model obtained in this way can serve as an important tool for finding efficient CO2 absorption solutions. It can help experimenters quickly obtain predicted CO2 solubility values ​​for new types of ion solutions under various working conditions, significantly accelerating the design and development process of new types of ion solutions, which has positive significance for promoting the development of carbon capture, utilization, and storage technologies.

[0101] Second, by calculating the solubility loss value and backpropagating the updated parameters, the transfer learning model can gradually optimize the feature extraction module's ability to extract features related to carbon dioxide solubility, thereby significantly improving the performance of the transfer learning model. In addition, by using the mean square error as the calculation formula for the solubility loss value, the degree of deviation between the predicted value and the true value can be intuitively quantified, providing a clear optimization direction for model training. In addition, its square penalty mechanism can effectively suppress abnormal error interference, help enhance the stability of the model under complex data, and improve the accuracy and reliability of carbon dioxide solubility prediction.

[0102] Third, by using the second training sample with the data domain type label to update the parameters of the feature extraction module and the domain discrimination module, the model can dynamically remove redundant features that are strongly related to the data source (such as differences in experimental equipment or sampling bias, etc.), while strengthening the ability to extract task-related features that are common across domains (such as physicochemical factors affecting solubility). This adversarial training mechanism reversely constrains the feature extraction module through the classification pressure of the domain discrimination module, so that the model can reduce its sensitivity to the data domain while improving the generalization performance of the target task (such as solubility prediction), further enhancing the stability and prediction accuracy of the model in unseen data domains.

[0103] Fourth, by introducing the gradient reversal layer, during backpropagation, the feature extraction module receives the inverted gradient, prompting it to generate features that confuse the domain discriminator and weaken the data domain-related features, while the domain discriminator is updated normally to improve the discrimination ability; this dynamic adversarial model forces the model to gradually strip away data domain-specific features and strengthen the extraction of general features that are unrelated to the data domain, thereby effectively improving the generalization performance of the model on new data domains.

[0104] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0105] Figure 6 A schematic diagram of a device for predicting the solubility of carbon dioxide in an ionic solution provided by an exemplary embodiment of the present application. Figure 6 As shown, the device 60 for predicting the solubility of carbon dioxide in an ionic solution includes an acquisition module 61 and a processing module 62, wherein:

[0106] An acquisition module 61 is configured to acquire a target domain data set corresponding to a first ion solution for which carbon dioxide solubility is to be predicted, wherein the target domain data set includes physical and chemical property data and target operating condition parameters corresponding to the first ion solution;

[0107] Processing module 62 is used to input the target domain dataset into the carbon dioxide solubility prediction model to predict the carbon dioxide solubility, and obtain a predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters. The carbon dioxide solubility prediction model is obtained by performing domain adversarial training on the constructed transfer learning model based on the source domain dataset and the target domain dataset. The features learned by the carbon dioxide solubility prediction model are related to the carbon dioxide solubility and are independent of the data domain type. The source domain dataset contains physical and chemical property data corresponding to a second ion solution with known carbon dioxide solubility and carbon dioxide solubility under different operating parameters. The type of the second ion solution is different from the type of the first ion solution.

[0108] In one possible implementation, the transfer learning model includes a feature extraction module, a domain discrimination module, and a prediction module, and the carbon dioxide solubility prediction model is trained in the following manner: the transfer learning model is iteratively trained until an iteration termination condition is met, wherein each round of training includes: batch data extracted from a source domain dataset constitutes a first training sample, and based on the first training sample, the parameters of the feature extraction module and the prediction module are updated so that the feature extraction module learns features related to carbon dioxide solubility; batch data extracted from the source domain dataset and batch data extracted from the target domain dataset constitute a second training sample, and based on the second training sample, the parameters of the feature extraction module and the domain discrimination module are updated so that the feature extraction module learns features that are independent of the data domain type.

[0109] In one possible embodiment, the processing module 62 can be specifically used to: extract a first feature related to the solubility of carbon dioxide in the first training sample based on the feature extraction module; based on the first feature, use the prediction module to predict the solubility of carbon dioxide in the first training sample to obtain a first prediction value corresponding to the first training sample; determine a solubility loss value based on the first prediction value and the solubility of carbon dioxide corresponding to the first training sample; based on the solubility loss value, update the parameters of the feature extraction module and the prediction module through back propagation to optimize the feature extraction module's ability to extract features related to carbon dioxide solubility.

[0110] In a possible implementation, the processing module 62 may further be configured to: determine a mean square error between the first prediction value and the carbon dioxide solubility corresponding to the first training sample; and determine the mean square error as a solubility loss value.

[0111] In one possible implementation, the second training sample includes a data domain type label that identifies the data source, and the processing module 62 can also be used to: extract a second feature related to the data domain type in the second training sample based on the feature extraction module; based on the second feature, use the domain discrimination module to predict the data domain type to obtain a second prediction value corresponding to the second training sample; determine the data domain classification loss value based on the second prediction value and the data domain type label corresponding to the second training sample; based on the data domain classification loss value, update the parameters of the feature extraction module and the domain discrimination module through back propagation to weaken the feature extraction module's ability to extract features related to the data domain type.

[0112] In one possible implementation, the domain discrimination module includes a gradient reversal layer, and the processing module 62 can also be used to: use the gradient reversal layer to invert the domain classification loss gradient corresponding to the data domain classification loss value to obtain a reverse gradient; return the reverse gradient to the feature extraction module to update the extraction parameters of the feature extraction module so that the feature extraction module extracts features that are difficult for the domain discrimination module to distinguish; return the domain classification loss gradient to the domain discrimination module to update the domain discrimination parameters corresponding to the domain discrimination module to improve the domain discrimination ability of the domain discrimination module.

[0113] In a possible implementation, the processing module 62 may also be used to: determine a cross entropy loss value corresponding to the second prediction value and the data domain type label corresponding to the second training sample; and determine the cross entropy loss value as the data domain classification loss value.

[0114] The device for predicting the solubility of carbon dioxide in ionic solution provided in the embodiment of the present application can implement the technical solution shown in the above-mentioned embodiment of the method for predicting the solubility of carbon dioxide in ionic solution. Its implementation principle and beneficial effects are similar and will not be repeated here.

[0115] It should be noted that it should be understood that the division of the various modules of the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software called by a processing element; or they can all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the processing module can be a separately established processing element, or it can be integrated into a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called by a processing element of the above device to perform the functions of the above processing module. The implementation of other modules is similar. In addition, these modules can all or partly be integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or by instructions in the form of software.

[0116] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0117] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. Available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, Digital Video Discs (DVDs)), or semiconductor media (eg, solid state disks (SSDs)).

[0118] Figure 7 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. Figure 7 As shown, the electronic device 70 of this embodiment includes:

[0119] At least one processor 71; and a memory 72 communicatively connected to the at least one processor;

[0120] The memory 72 stores instructions that can be executed by the at least one processor 71 , and the instructions are executed by the at least one processor 71 to enable the electronic device to execute the method as described in any of the above embodiments.

[0121] Optionally, the memory 72 can be independent or integrated with the processor 71.

[0122] The memory 72 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0123] Processor 71 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. Specifically, when implementing the model training method or VSP wavefield separation method described in the aforementioned method embodiments, the electronic device may be, for example, an electronic device with processing capabilities, such as a server.

[0124] Optionally, the electronic device may further include a communication interface 73. In a specific implementation, if the communication interface 73, memory 72, and processor 71 are implemented independently, the communication interface 73, memory 72, and processor 71 may be interconnected via a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, control buses, and so on, but this does not necessarily mean that there is only one bus or only one type of bus.

[0125] Optionally, in a specific implementation, if the communication interface 73, the memory 72 and the processor 71 are integrated on a chip, the communication interface 73, the memory 72 and the processor 71 can complete communication through an internal interface.

[0126] The implementation principle and technical effects of the electronic device provided in this embodiment can be found in the aforementioned embodiments and will not be described in detail here.

[0127] An embodiment of the present application also provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed, they are used to implement the method steps in the above method embodiment. The specific implementation method and technical effects are similar and will not be repeated here.

[0128] The computer-readable storage medium described above can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The computer-readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0129] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Alternatively, the readable storage medium may be a component of the processor. The processor and the readable storage medium may be located in an application-specific integrated circuit. Alternatively, the processor and the readable storage medium may be discrete components within the device for predicting the solubility of carbon dioxide in an ionic solution.

[0130] An embodiment of the present application also provides a computer program product, including a computer program. When the computer program is executed, the method steps in the above method embodiment are implemented. The specific implementation method and technical effects are similar and will not be repeated here.

[0131] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0132] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for predicting the solubility of carbon dioxide in an ionic solution, characterized in that: include: Acquire a target domain data set corresponding to a first ion solution for which carbon dioxide solubility is to be predicted, the target domain data set comprising physical and chemical property data and target operating condition parameters corresponding to the first ion solution; The target domain dataset is input into a carbon dioxide solubility prediction model to perform carbon dioxide solubility prediction, and a predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters is obtained. The carbon dioxide solubility prediction model is obtained by performing domain adversarial training on a constructed transfer learning model based on a source domain dataset and the target domain dataset. The features learned by the carbon dioxide solubility prediction model are related to carbon dioxide solubility and are independent of the data domain type. The source domain dataset contains physical and chemical property data corresponding to a second ion solution with known carbon dioxide solubility and carbon dioxide solubility under different operating parameters. The type of the second ion solution is different from the type of the first ion solution.

2. The prediction method according to claim 1, characterized in that The transfer learning model includes a feature extraction module, a domain discrimination module, and a prediction module. The carbon dioxide solubility prediction model is trained in the following manner: The transfer learning model is iteratively trained until the iteration termination condition is met, wherein each round of training includes: The batch data extracted from the source domain dataset constitutes a first training sample, and based on the first training sample, the parameters of the feature extraction module and the prediction module are updated so that the feature extraction module learns features related to carbon dioxide solubility; The batch data extracted from the source domain dataset and the batch data extracted from the target domain dataset constitute a second training sample, and the parameters of the feature extraction module and the domain discrimination module are updated based on the second training sample so that the feature extraction module learns features that are independent of the data domain type.

3. The prediction method according to claim 2, characterized in that The updating of parameters of the feature extraction module and the prediction module based on the first training sample includes: extracting a first feature related to carbon dioxide solubility from the first training sample based on the feature extraction module; Based on the first feature, using the prediction module to predict the solubility of carbon dioxide in the first training sample to obtain a first predicted value corresponding to the first training sample; determining a solubility loss value based on the first predicted value and the carbon dioxide solubility corresponding to the first training sample; Based on the solubility loss value, parameters of the feature extraction module and the prediction module are updated through back propagation to optimize the feature extraction module's ability to extract features related to carbon dioxide solubility.

4. The prediction method according to claim 3, characterized in that The determining of the solubility loss value based on the first predicted value and the carbon dioxide solubility corresponding to the first training sample includes: determining a mean square error between the first predicted value and the carbon dioxide solubility corresponding to the first training sample; The mean square error is determined to be the solubility loss value.

5. The prediction method according to any one of claims 2 to 4, characterized in that: The second training sample includes a data domain type label identifying a data source, and updating parameters of the feature extraction module and the domain discrimination module based on the second training sample includes: extracting a second feature related to the data domain type from the second training sample based on the feature extraction module; Based on the second feature, using the domain discrimination module to predict the data domain type to obtain a second prediction value corresponding to the second training sample; Determining a data domain classification loss value based on the second predicted value and the data domain type label corresponding to the second training sample; Based on the data domain classification loss value, the parameters of the feature extraction module and the domain discrimination module are updated through back propagation to weaken the feature extraction module's ability to extract features related to the data domain type.

6. The prediction method according to claim 5, characterized in that The domain discrimination module includes a gradient reversal layer, and the parameters of the feature extraction module and the domain discrimination module are updated by back propagation based on the data domain classification loss value, including: Using the gradient reversal layer, the domain classification loss gradient corresponding to the data domain classification loss value is inverted to obtain a reverse gradient; Feeding the reverse gradient back to the feature extraction module, and updating the extraction parameters of the feature extraction module, so that the feature extraction module extracts features that are difficult for the domain discrimination module to distinguish; The domain classification loss gradient is fed back to the domain discrimination module to update the domain discrimination parameters corresponding to the domain discrimination module to improve the domain discrimination ability of the domain discrimination module.

7. The prediction method according to claim 5, characterized in that The determining of the data domain classification loss value based on the second predicted value and the data domain type label corresponding to the second training sample includes: Determine a cross entropy loss value corresponding to the second predicted value and the data domain type label corresponding to the second training sample; Determine the cross entropy loss value as the data domain classification loss value.

8. A device for predicting the solubility of carbon dioxide in an ionic solution, characterized in that: include: an acquisition module, configured to acquire a target domain data set corresponding to a first ion solution for which carbon dioxide solubility is to be predicted, wherein the target domain data set includes physical and chemical property data and target operating condition parameters corresponding to the first ion solution; A processing module is configured to input the target domain dataset into a carbon dioxide solubility prediction model to perform carbon dioxide solubility prediction, and obtain a predicted value of the carbon dioxide solubility of the first ion solution under the target operating parameters, wherein the carbon dioxide solubility prediction model is obtained by performing domain adversarial training on a constructed transfer learning model based on a source domain dataset and the target domain dataset, wherein features learned by the carbon dioxide solubility prediction model are related to carbon dioxide solubility and are independent of the data domain type, and wherein the source domain dataset includes physical and chemical property data corresponding to a second ion solution with known carbon dioxide solubility and carbon dioxide solubility under different operating parameters, and the type of the second ion solution is different from the type of the first ion solution.

9. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory is used to store computer-executable instructions; The processor is configured to execute the computer-executable instructions to implement the method for predicting the solubility of carbon dioxide in an ionic solution according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method for predicting the solubility of carbon dioxide in an ionic solution according to any one of claims 1 to 7.

Images