Data-driven two-dimensional bimetal chalcogenide carbon dioxide reduction photocatalyst material design method, system and medium

Abstract

The invention relates to a two-dimensional bimetal chalcogenide carbon dioxide reduction photocatalyst material design method and system based on data driving, and a medium. The design method comprises the following steps: S1, establishing an initial database; s2, cleaning and preprocessing the initial data, and determining machine learning problem attributes of different target variables; s3, feature engineering and model training; s4, designing a novel two-dimensional photocatalyst material, and predicting target attributes based on the model in S3; s5, pre-screening a photocatalyst candidate material based on the target attribute predicted in S4; and S6, carrying out DFT verification on the candidate material. Compared with the prior art, the method has the advantages that by learning the known target variable data of the two-dimensional material, the expected two-dimensional photocatalyst material can be quickly given while the influence trend of each feature on the target variable can be provided, so that the number of experiments for finding the two-dimensional photocatalyst is reduced, and the experiment efficiency is improved. The preparation process of the carbon dioxide reduction photocatalyst is accelerated.

Description

Technical Field

[0001] The present invention relates to the field of solar photocatalysis, and in particular to a data-driven two-dimensional bimetallic oxygen compound carbon dioxide reduction photocatalyst material design method, system and medium. Background Art

[0002] The large-scale combustion of fossil fuels and industrial production processes will produce a large amount of greenhouse gases, accelerating global warming and causing major changes in the earth's climate. Carbon dioxide is a major greenhouse gas, and finding suitable catalysts to convert it into chemicals (such as CO, CH3OH, CH4, etc.) is the key to solving this problem. Among various conversion methods, photocatalysis is an important method that uses clean, safe and renewable solar-driven catalysts for carbon dioxide conversion.

[0003] Two-dimensional materials have attracted much attention in the field of photocatalysis due to their excellent stability, unique light absorption properties and high surface catalytic activity. As a bimetallic compound, A2B2X6 has a distinct two-dimensional layered structure, each layer consisting of A, B and X atoms, and stacked together through van der Waals interactions. The two-dimensional layered structure provides a larger specific surface area, allowing more reactants to contact the catalyst surface, thereby improving the reaction efficiency. Van der Waals interactions lead to a weakening of the interlayer binding force, making it easier for electrons and holes to migrate between layers, reducing the chance of carrier recombination. These characteristics fully demonstrate that the A2B2X6 bimetallic compound with a two-dimensional structure has the potential to be a photocatalyst for carbon dioxide reduction.

[0004] Although there are various methods for synthesizing new photocatalytic materials in the laboratory, such as sol-gel method, hydrothermal synthesis, etc., these methods are often time-consuming, expensive, and have a very low trial-and-error rate. Blindly conducting experiments may not meet the needs of large-scale catalyst synthesis.

[0005] The introduction of density functional theory provides researchers with a more effective method to simulate and screen new photocatalytic materials. However, density functional theory research is often too computationally expensive, too slow, and too inefficient when dealing with large-scale systems and complex materials. In recent years, with the development of materials informatics, the combination of machine learning calculations and first-principles calculations has developed rapidly in various fields and has been proven to be an effective way to accelerate the material design process.

[0006] In material design, how to predict the photocatalytic performance of candidate materials with the help of machine learning methods and screen out suitable photocatalysts with the help of the prediction results has become one of the problems that technicians in this field want to actively solve. Summary of the invention

[0007] The purpose of the present invention is to overcome the defects of the above-mentioned prior art, combine machine learning algorithms and first principles calculations, establish an efficient and accurate method to explore new two-dimensional bimetallic oxygen family compound carbon dioxide reduction photocatalysts, and provide a data-driven two-dimensional bimetallic oxygen family compound carbon dioxide reduction photocatalyst material design method, system, and medium.

[0008] The purpose of the present invention can be achieved by the following technical solutions:

[0009] The first aspect of the present invention provides a data-driven two-dimensional bimetallic oxygen family compound carbon dioxide reduction photocatalyst material design method. The design method is implemented by combining a machine learning algorithm and a first principle calculation, and specifically includes the following steps:

[0010] S1, obtaining information of a two-dimensional photocatalyst material system of interest, obtaining two-dimensional material data corresponding to the system information, wherein the two-dimensional material data includes stability information and energy band structure information of the two-dimensional material, and obtaining input features of the two-dimensional material to establish an initial data set;

[0011] S2, cleaning and preprocessing the initial data set to obtain a modeling data set for machine learning, wherein the modeling data set includes input features, stability, and band structure information of the two-dimensional material, taking the input features as variables, taking the stability and band structure information as target variables, and determining the problem attributes of machine learning according to different target variables;

[0012] S3, screen the input features of the modeling data set to obtain the best feature subset, train and evaluate the machine learning model on the best feature subset, obtain the machine learning model, and perform interpretability analysis on the machine learning prediction model;

[0013] S4, creating a theoretical two-dimensional carbon dioxide reduction photocatalyst data set by limiting each site element, using the theoretical two-dimensional carbon dioxide reduction photocatalyst data set as an input of the machine learning model obtained in S3 to obtain a predicted value of the target variable;

[0014] S5, screening out candidate photocatalyst materials based on the predicted value of the target variable;

[0015] S6, performing DFT verification on the candidate photocatalyst materials to screen out materials that meet the conditions for photocatalytic carbon dioxide reduction.

[0016] Furthermore, in S1, the process of establishing the initial database includes the following sub-steps:

[0017] S1.1, obtain the two-dimensional material system of interest, and collect the stability and band structure information of known two-dimensional materials from literature and public material databases, wherein the stability information includes formation energy information and convex hull energy information, and the band structure information includes PBE band gap information, HSE band gap information, VBM at the HSE level, and CBM at the HSE level;

[0018] S1.2, obtaining the input characteristics of the two-dimensional material, specifically including: (1) obtaining the space group of the material; (2) generating stoichiometric characteristics, elemental property statistical characteristics, electronic structure property characteristics, and ion component property characteristics through the Magpie method;

[0019] S1.3, input characteristics and stability and band structure information of two-dimensional materials to establish an initial data set.

[0020] Furthermore, S2 specifically includes the following sub-steps:

[0021] S2.1, based on machine learning, the target variables of the initial data set are processed for missing values, and the input features are processed for outliers to obtain a data set for machine learning modeling. The modeling data set includes input features, formation energy, convex hull energy, PBE band gap, HSE band gap, VBM at the HSE level, and CBM at the HSE level;

[0022] S2.2, determine the problem attributes of each target variable, where the convex hull energy is used as the target variable for the classification problem, and a threshold of 0.2eV is used for convex hull energy classification. Materials with convex hull energy below 0.2eV are stable and marked as 1; otherwise, they are marked as 0. Formation energy, PBE band gap, HSE band gap, VBM at HSE level, and CBM at HSE level are used as target variables for the regression problem.

[0023] Furthermore, in S2.1, the upper bound of the outlier is Q3+1.5×(Q3-Q1), and the lower bound of the outlier is Q1+1.5×(Q3-Q1), where Q1 is the first quartile and Q3 is the third quartile.

[0024] Furthermore, S3 specifically includes the following sub-steps:

[0025] S3.1, perform Pierce correlation calculation on the features of the data set obtained in S2, filter out the features with high correlation, obtain a feature set with low collinearity, and use the RFE method based on machine learning to perform feature screening on the feature set with low collinearity to obtain the best feature subset;

[0026] S3.2, for the convex hull classification problem, an automatic ML tool TPOT was used to perform an extensive search for the best feature subset and convex hull;

[0027] S3.3, for the formation energy problem, CrabNet is used as a machine learning model to predict the formation energy;

[0028] S3.4, for the energy band regression problem, two regression models were established: one for predicting the HSE band gap and the other for predicting the VBM, using the model stacking technique, using the PBE band gap as one of the input features for the HSE band gap regression model, and the HSE band gap as one of the input features for the VBM regression model;

[0029] S3.5, for the above classification and regression problems, the optuna software package is used to perform Bayesian parameter optimization, and the SHAP method is used to perform interpretability analysis on the features of the machine learning prediction model, so as to improve the model interpretability and optimize the model.

[0030] Furthermore, S3.4 specifically includes the following sub-steps:

[0031] S3.4.1, based on the best feature subset obtained in S3, a PBE band gap regression model based on the GGA function is trained, and the PBE band gap of the two-dimensional material data set is predicted based on the PBE model to obtain a new PBE band gap value;

[0032] S3.4.2, based on the best feature subset obtained in S3 and S3.4.1, a new PBE band gap value is obtained, a model superposition technique is used to train an HSE band gap regression model, and the HSE band gap of the two-dimensional material data set is predicted based on the HSE model to obtain a new HSE band gap value;

[0033] S3.4.3, based on the best feature subset obtained in S3 and the new HSE band gap value obtained in S3.4.3, the model superposition technology is used to train the VBM regression model at the HSE level.

[0034] Furthermore, S4 specifically includes the following sub-steps:

[0035] S4.1, determine the element selection of the A, B, and X sites of A2B2X6;

[0036] S4.2, generate A2B2X6 candidates by permutation, combination, and charge neutrality of the compound, where the B position is replaced by a combination of two different metal elements;

[0037] S4.3, using the theoretical two-dimensional carbon dioxide reduction photocatalyst dataset as input to the machine learning model obtained in S3 to obtain the predicted value of the target variable of the dataset.

[0038] Furthermore, S5 specifically includes the following sub-steps:

[0039] S5.1, stability screening, screening indicators include formation energy less than 0, convex hull energy less than 0.2;

[0040] S5.2, light absorption and reduction potential matching screening, the screening indicators include HSE band gap value between 1.5 and 3.2, valence band value less than -3.89, conduction band value greater than -3.89;

[0041] S5.3, environmental screening of materials, screening out candidates that do not contain heavy metals, precious metals, or toxic substances.

[0042] Furthermore, S6 specifically includes the following sub-steps:

[0043] S6.1, construct the crystal structure of the candidate material;

[0044] S6.2, optimize the crystal structure of candidate materials;

[0045] S6.3, perform PBE self-consistent calculation on the optimized crystal structure;

[0046] S6.4, HSE self-consistent calculation based on the crystal structure obtained in S6.3;

[0047] S6.5, based on the crystal structure obtained in S6.4, HSE non-self-consistent calculations are performed, including HSE band gap, VBM at HSE level, CBM at HSE level, Fermi level and dos state density, to screen out materials that meet the conditions for photocatalytic carbon dioxide reduction, thereby completing the entire photocatalyst material design process.

[0048] The second aspect of the present invention provides a data-driven two-dimensional bimetallic oxygen family compound carbon dioxide reduction photocatalyst material design system, comprising:

[0049] An initial database establishment module is used to obtain the information of the two-dimensional photocatalyst material system of interest, obtain the two-dimensional material data corresponding to the system information, the two-dimensional material data including the stability information and energy band structure information of the two-dimensional material, and obtain the input characteristics of the two-dimensional material to establish an initial data set;

[0050] A data preprocessing module cleans and preprocesses the initial data set to obtain a modeling data set for machine learning, wherein the modeling data set includes input features, stability, and band structure information of the two-dimensional material, takes the input features as variables, and takes the stability and band structure information as target variables, and determines the problem attributes of machine learning according to different target variables;

[0051] The feature engineering and model acquisition module screens the input features of the modeling data set to obtain the best feature subset, trains and evaluates the machine learning model on the best feature subset, obtains the machine learning model, and performs interpretability analysis on the machine learning prediction model;

[0052] The two-dimensional photocatalyst design module creates a theoretical two-dimensional carbon dioxide reduction photocatalyst dataset by limiting each site element, and uses the theoretical two-dimensional carbon dioxide reduction photocatalyst dataset as the input of the machine learning model to obtain the predicted value of the target variable;

[0053] A two-dimensional photocatalyst pre-screening module, which screens out candidate photocatalyst materials based on the predicted value of the target variable;

[0054] The two-dimensional photocatalyst DFT verification module performs DFT verification on the candidate photocatalyst materials to screen out materials that meet the conditions for photocatalytic carbon dioxide reduction.

[0055] A third aspect of the present invention provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, is used to execute the data-driven two-dimensional bimetallic oxygen family compound carbon dioxide reduction photocatalyst material design method as described above.

[0056] Compared with the prior art, the present invention has the following technical advantages:

[0057] 1) The present invention establishes a data-driven two-dimensional bimetallic oxygen compound carbon dioxide reduction photocatalyst material design method, which provides an exploration direction for identifying two-dimensional photocatalysts with carbon dioxide reduction potential.

[0058] 2) The present invention comprehensively considers the stability, band structure, and potential requirements of carbon dioxide reduction photocatalyst materials, and combines machine learning methods with first-principles calculations to design a rapid screening tool.

[0059] 3) By learning the target variable data of known two-dimensional materials, the present invention can not only provide the influence trend of each characteristic on the target variable, but also quickly give the desired two-dimensional photocatalyst material, so as to reduce the number of experiments in searching for two-dimensional photocatalysts and accelerate the production process of carbon dioxide reduction photocatalysts. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a flow chart of the photocatalyst material design method in Example 1 of the present invention;

[0061] Figure 2 This is a flow chart of step 2 of photocatalyst material design in Example 1 of the present invention;

[0062] Figure 3 This is a flow chart of step 3 of photocatalyst material design in Example 1 of the present invention;

[0063] Figure 4This is a flow chart of step 4 of photocatalyst material design in Example 1 of the present invention;

[0064] Figure 5 This is a flow chart of step 5 of photocatalyst material design in Example 1 of the present invention;

[0065] Figure 6 This is a flow chart of step 6 of photocatalyst material design in Example 1 of the present invention;

[0066] Figure 7 is a model performance diagram of the convex hull classification model in the present invention;

[0067] Figure 8 is a model performance diagram of the HSE bandgap regression model in the present invention;

[0068] Fig. 9 is a model performance diagram of the valence band regression model at the HSE level in the present invention;

[0069] Fig.10 This is a site element selection diagram for the two-dimensional bimetallic oxodiol compound of the present invention. DETAILED DESCRIPTION

[0070] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. Component models, material names, connection structures, control methods, algorithms and other features not clearly described in this technical solution are all considered to be common technical features disclosed in the prior art.

[0071] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments; the technical features designed in different implementation modes of the present invention described below can be combined with each other as long as they do not conflict with each other; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0072] Example 1

[0073] Figure 1 This is a flow chart of the photocatalyst material design method in Example 1 of the present invention;

[0074] like Figure 1 As shown, this embodiment provides a data-driven two-dimensional bimetallic oxygen family compound carbon dioxide reduction photocatalyst material design method, comprising the following steps:

[0075] Step 1: Based on the two-dimensional photocatalyst material system under study, collect known two-dimensional material data, which includes the stability and band structure information of the two-dimensional material, obtain the input characteristics of the two-dimensional material and the corresponding input characteristic parameters, and establish an initial data set.

[0076] Specifically, the process of establishing a complete initial database includes the following sub-steps:

[0077] Step 1.1, based on the two-dimensional material system under study, obtain the stability and band structure information of more than 1000 materials from the C2DB two-dimensional material database. The stability information includes formation energy and convex hull energy. The band structure information includes PBE band gap, HSE band gap, VBM at HSE level and CBM at HSE level.

[0078] Step 1.2, the input characteristics of the material include: (1) the space group of the material; (2) the stoichiometric characteristics, elemental property statistical characteristics, electronic structure property characteristics, and ion component property characteristics generated by the Magpie method;

[0079] In step 1.3, the characteristics and stability and band structure information of the two-dimensional material are input to establish the initial data set.

[0080] Step 2: Based on machine learning, the initial data set is cleaned and preprocessed to obtain a modeling data set for machine learning. The modeling data set includes the input characteristics, stability, and band structure information of the two-dimensional material. The input characteristics are used as variables, and the stability and band structure information are used as target variables. The problem attributes of machine learning are determined according to different target variables.

[0081] Figure 2 is a flow chart of step 2 of photocatalyst material design in Example 1 of the present invention;

[0082] like Figure 2 As shown, step 2 includes the following sub-steps:

[0083] Step 2.1, based on machine learning, the target variables of the initial data set are processed for missing values, and the input features are processed for outliers to obtain a data set for machine learning modeling. The modeling data set includes input features, formation energy, convex hull energy, PBE band gap, HSE band gap, VBM at the HSE level, and CBM at the HSE level. The upper bound of the outlier is Q3+1.5×(Q3-Q1), and the lower bound of the outlier is Q1+1.5×(Q3-Q1), where Q1 is the first quartile and Q3 is the third quartile.

[0084] Step 2.2, determine the problem attributes of each target variable, among which the convex hull energy is used as the target variable for the classification problem. A threshold of 0.2eV is used for convex hull energy classification. Materials with convex hull energy below 0.2eV are stable and marked as 1; otherwise, they are marked as 0. Formation energy, PBE band gap, HSE band gap, VBM at HSE level, and CBM at HSE level are used as target variables for regression problems.

[0085] Step 3: Filter the input features of the data set to obtain the best feature subset, perform model training and evaluation on the best feature subset, use machine learning algorithms to improve the model prediction capability, obtain the machine learning model, and perform interpretability analysis on the machine learning prediction model.

[0086] Figure 3 This is a flow chart of step 3 of photocatalyst material design in Example 1 of the present invention;

[0087] like Figure 3 As shown, step 3 includes the following sub-steps:

[0088] Step 3.1, perform Pierce correlation calculation on the features of the data set obtained in step 2, filter out the features with high correlation, obtain a feature set with low collinearity, and use the RFE method based on machine learning to perform feature screening on the feature set with low collinearity to obtain the best feature subset;

[0089] Step 3.2, for the convex hull classification problem, use the automatic ML tool TPOT to conduct an extensive search for the best feature subset and convex hull;

[0090] Step 3.3, for the formation energy problem, use CrabNet as a machine learning model to predict the formation energy;

[0091] Step 3.4, for the energy band regression problem, two regression models were established: one for predicting the HSE band gap and the other for predicting the VBM. Using the model stacking technique, the PBE band gap was used as one of the input features of the HSE band gap regression model, while the HSE band gap was used as one of the input features of the VBM regression model;

[0092] In step 3.5, for the above classification and regression problems, the optuna software package is used to perform Bayesian parameter optimization, and the SHAP method is used to perform interpretability analysis on the features of the machine learning prediction model to improve the model interpretability and optimize the model.

[0093] like Figure 7 As shown, the convex hull classification model is analyzed as follows: (1) the importance of model features is analyzed; (2) the confusion matrix is ​​drawn and the F1 score is calculated to be 94.39%. The F1 calculation formula is: Where Precision is the accuracy, and the calculation formula is: Recall is the recall rate, and the calculation formula is: (3) Draw the AUC curve and calculate the area under the line.

[0094] like Figure 8 As shown in the figure, the following analysis is performed on the HSE bandgap regression model: (1) the shap value of the model is output, and the importance of the model features is output; (2) the accuracy, root mean square error, and mean absolute error of the model are calculated.

[0095] like Fig. 9 As shown in the figure, the comprehensive evaluation of the valence band regression model at the HSE level includes but is not limited to the following methods: (1) analyzing the importance of model features; (2) calculating the accuracy and mean absolute error of the model.

[0096] Step 4, by limiting each site element, a theoretical two-dimensional carbon dioxide reduction photocatalyst database is created, and the data set is used as the input of the machine learning model obtained in step 3 to obtain the predicted value of the target variable of the data set;

[0097] Figure 4 This is a flow chart of step 4 of photocatalyst material design in Example 1 of the present invention;

[0098] like Figure 4 As shown, step 4 includes the following sub-steps:

[0099] Step 4.1, determine the element selection of the A, B and X sites of A2B2X6.

[0100] like Fig.10 As shown, alkali metals, alkaline earth metals, transition metals, main group metals and metalloids are used as potential cations at the A and B positions, and chalcogens are used as potential anions at the x position;

[0101] Step 4.2, generating A2B2X6 candidates by permutation, combination, and charge neutrality of the compound, wherein the B position is replaced by a combination of two different metal elements;

[0102] Step 4.3, using the data set as the input of the machine learning model obtained in step 3 to obtain the predicted value of the target variable of the data set;

[0103] Step 5, screening, based on the predicted value of the target variable, screening out candidate photocatalyst materials;

[0104] Figure 5 This is a flow chart of step 5 of photocatalyst material design in Example 1 of the present invention;

[0105] like Figure 5 As shown, step 5 includes the following sub-steps:

[0106] Step 5.1, stability screening, including formation energy less than 0 and convex hull energy less than 0.2;

[0107] Step 5.2, light absorption and reduction potential matching screening, HSE band gap value is between 1.5 and 3.2, valence band value is less than -3.89, and conduction band value is greater than -3.89;

[0108] Step 5.3, environmental screening of materials, screening out candidates that do not contain heavy metals, precious metals, or toxic substances.

[0109] Step 6, performing DFT verification on the candidate photocatalyst materials, screening out materials that meet the conditions for photocatalytic carbon dioxide reduction, and completing the entire photocatalyst material design process.

[0110] Figure 6 This is a flow chart of step 6 of photocatalyst material design in Example 1 of the present invention;

[0111] like Figure 6 As shown, step 6 includes the following sub-steps:

[0112] Step 6.1, constructing the crystal structure of the candidate material;

[0113] Step 6.2, optimizing the crystal structure of the candidate material;

[0114] Step 6.3, perform PBE self-consistent calculation on the optimized crystal structure;

[0115] Step 6.4, perform HSE self-consistent calculation based on the crystal structure obtained in step 6.3;

[0116] Step 6.5, based on the crystal structure obtained in step 6.4, perform HSE non-self-consistent calculations, including HSE band gap, VBM at HSE level, CBM at HSE level, Fermi level and dos state density, to screen out materials that meet the conditions for photocatalytic carbon dioxide reduction and complete the entire photocatalyst material design process.

[0117] This embodiment also provides a data-driven two-dimensional bimetallic oxygen family compound carbon dioxide reduction photocatalyst material design method, using the data-driven two-dimensional bimetallic oxygen family compound carbon dioxide reduction photocatalyst material design system of the above-mentioned embodiment 1, including an initial database establishment module, a data preprocessing module, a feature engineering and model acquisition module, a two-dimensional photocatalyst design module, a two-dimensional photocatalyst pre-screening module, and a two-dimensional photocatalyst DFT verification module.

[0118] The initial database establishment module collects known two-dimensional material data based on the two-dimensional photocatalyst material system under study, including the stability and band structure information of the two-dimensional material, obtains the input characteristics of the two-dimensional material and the corresponding input characteristic parameters, and establishes the initial data set;

[0119] The data preprocessing module cleans and preprocesses the initial data set based on machine learning to obtain a modeling data set for machine learning. The modeling data set includes the input characteristics, stability, and band structure information of the two-dimensional material. The input characteristics are used as variables, and the stability and band structure information are used as target variables. The problem attributes of machine learning are determined according to different target variables.

[0120] The feature engineering and model acquisition module screens the input features of the data set to obtain the best feature subset, performs model training and evaluation on the best feature subset, and uses machine learning algorithms to improve the model's prediction capabilities, obtain a machine learning model, and perform interpretability analysis on the machine learning prediction model;

[0121] The two-dimensional photocatalyst design module creates a theoretical two-dimensional carbon dioxide reduction photocatalyst database by defining each site element, and uses the data set as the input of the machine learning model obtained in step 3 to obtain the predicted value of the target variable of the data set;

[0122] A two-dimensional photocatalyst pre-screening module is used to screen candidate photocatalyst materials based on the predicted value of the target variable;

[0123] The two-dimensional photocatalyst DFT verification module performs DFT verification on the candidate photocatalyst materials, screens out materials that meet the conditions for photocatalytic carbon dioxide reduction, and completes the entire photocatalyst material design process.

[0124] It should be understood that the modules of the data-driven two-dimensional bimetallic oxygen-based carbon dioxide reduction photocatalyst material design system described in this embodiment 2 can correspond to the various steps of the photocatalyst material design method described in embodiment 1. Therefore, the operations, features and advantages described above for each step based on the method are also applicable to each module of the system. For the sake of brevity, some operations, features and advantages are not repeated here.

[0125] This embodiment also proposes a computer-readable storage medium, wherein the storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned data-driven two-dimensional bimetallic oxygen compound carbon dioxide reduction photocatalyst material design method. The storage medium can be an electronic medium, a magnetic medium, an optical medium, an electromagnetic medium, an infrared medium or a semiconductor system or a propagation medium. The storage medium can also include a semiconductor or solid-state memory, a magnetic tape, a removable computer disk, a random access memory (RAM), a read-only memory (ROM), a hard disk, and an optical disk. The optical disk can include a compact disk-read only memory (CD-ROM), a compact disk-read and write (CD-RW) and a DVD.

[0126] As can be seen from the examples, the present invention establishes a data-driven two-dimensional bimetallic oxygen compound carbon dioxide reduction photocatalyst material design method, which provides an exploration direction for identifying two-dimensional photocatalysts with carbon dioxide reduction potential.

[0127] As can be seen from the examples, the present invention comprehensively considers the stability, band structure, and potential requirements of carbon dioxide reduction photocatalyst materials, and combines machine learning methods with first-principles calculations to design a rapid screening tool.

[0128] It can be seen from the embodiments that the present invention, by learning the target variable data of known two-dimensional materials, can provide the influence trend of each characteristic on the target variable, and can also quickly give the desired two-dimensional photocatalyst material, so as to reduce the number of experiments in searching for two-dimensional photocatalysts and accelerate the production process of carbon dioxide reduction photocatalysts.

[0129] The above description of the embodiments is to facilitate the understanding and use of the invention by those skilled in the art. It is obvious that those skilled in the art can easily make various modifications to these embodiments and apply the general principles described herein to other embodiments without creative work. Therefore, the present invention is not limited to the above embodiments, and improvements and modifications made by those skilled in the art based on the disclosure of the present invention without departing from the scope of the present invention should be within the scope of protection of the present invention.

Claims

1. A data-driven two-dimensional bimetallic oxygen-based compound carbon dioxide reduction photocatalyst material design method, characterized in that: The design method is implemented by combining machine learning algorithms and first principle calculations, and specifically includes the following steps: S1, obtaining information of a two-dimensional photocatalyst material system of interest, obtaining two-dimensional material data corresponding to the system information, wherein the two-dimensional material data includes stability information and energy band structure information of the two-dimensional material, and obtaining input features of the two-dimensional material to establish an initial data set; S2, cleaning and preprocessing the initial data set to obtain a modeling data set for machine learning, wherein the modeling data set includes input features, stability, and band structure information of the two-dimensional material, taking the input features as variables, taking the stability and band structure information as target variables, and determining the problem attributes of machine learning according to different target variables; S3, screen the input features of the modeling data set to obtain the best feature subset, train and evaluate the machine learning model on the best feature subset, obtain the machine learning model, and perform interpretability analysis on the machine learning prediction model; S4, creating a theoretical two-dimensional carbon dioxide reduction photocatalyst data set by limiting each site element, using the theoretical two-dimensional carbon dioxide reduction photocatalyst data set as an input of the machine learning model obtained in S3 to obtain a predicted value of the target variable; S5, screening out candidate photocatalyst materials based on the predicted value of the target variable; S6, performing DFT verification on the candidate photocatalyst materials to screen out materials that meet the conditions for photocatalytic carbon dioxide reduction.

2. The data-driven two-dimensional bimetallic oxygen-based carbon dioxide reduction photocatalyst material design method according to claim 1, characterized in that: In S1, the process of establishing the initial database includes the following sub-steps: S1.1, obtain the two-dimensional material system of interest, and collect the stability and band structure information of known two-dimensional materials from literature and public material databases, wherein the stability information includes formation energy information and convex hull energy information, and the band structure information includes PBE band gap information, HSE band gap information, VBM at the HSE level, and CBM at the HSE level; S1.2, obtaining input characteristics of two-dimensional materials, specifically including: (1) obtaining the space group of the material; (2) Generate stoichiometric characteristics, elemental property statistical characteristics, electronic structure property characteristics, and ion component property characteristics through the Magpie method; S1.3, input characteristics and stability and band structure information of two-dimensional materials to establish an initial data set.

3. The data-driven two-dimensional bimetallic oxygen-based carbon dioxide reduction photocatalyst material design method according to claim 2, characterized in that: S2 specifically includes the following sub-steps: S2.1, based on machine learning, the target variables of the initial data set are processed for missing values, and the input features are processed for outliers to obtain a data set for machine learning modeling. The modeling data set includes input features, formation energy, convex hull energy, PBE band gap, HSE band gap, VBM at the HSE level, and CBM at the HSE level; S2.2, determine the problem attributes of each target variable, where the convex hull energy is used as the target variable for the classification problem, and a threshold of 0.2 eV is used for convex hull energy classification, forming energy, PBE band gap, HSE band gap, VBM at the HSE level, and CBM at the HSE level as the target variables for the regression problem; In S2.1, the upper bound of the outlier is Q3+1.5×(Q3-Q1), and the lower bound of the outlier is Q1-1.5×(Q3-Q1), where Q1 is the first quartile and Q3 is the third quartile.

4. The data-driven two-dimensional bimetallic oxygen-based carbon dioxide reduction photocatalyst material design method according to claim 3, characterized in that: S3 specifically includes the following sub-steps: S3.1, perform Pierce correlation calculation on the features of the data set obtained in S2, filter out the features with high correlation, obtain a feature set with low collinearity, and use the RFE method based on machine learning to perform feature screening on the feature set with low collinearity to obtain the best feature subset; S3.2, for the convex hull classification problem, an automatic ML tool TPOT was used to perform an extensive search for the best feature subset and convex hull; S3.3, for the formation energy problem, CrabNet is used as a machine learning model to predict the formation energy; S3.4, for the energy band regression problem, two regression models were established: one for predicting the HSE band gap and the other for predicting the VBM, using the model stacking technique, using the PBE band gap as one of the input features for the HSE band gap regression model, and the HSE band gap as one of the input features for the VBM regression model; S3.5, for the above classification and regression problems, the optuna software package is used to perform Bayesian parameter optimization, and the SHAP method is used to perform interpretability analysis on the features of the machine learning prediction model, so as to improve the model interpretability and optimize the model.

5. The data-driven two-dimensional bimetallic oxygen-based carbon dioxide reduction photocatalyst material design method according to claim 4, characterized in that: S3.4 specifically includes the following sub-steps: S3.4.1, based on the best feature subset obtained in S3, a PBE band gap regression model based on the GGA function is trained, and the PBE band gap of the two-dimensional material data set is predicted based on the PBE model to obtain a new PBE band gap value; S3.4.2, based on the best feature subset obtained in S3 and S3.4.1, a new PBE band gap value is obtained, a model superposition technique is used to train an HSE band gap regression model, and the HSE band gap of the two-dimensional material data set is predicted based on the HSE model to obtain a new HSE band gap value; S3.4.3, based on the best feature subset obtained in S3 and the new HSE band gap value obtained in S3.4.3, the model superposition technology is used to train the VBM regression model at the HSE level.

6. The data-driven two-dimensional bimetallic oxygen-based carbon dioxide reduction photocatalyst material design method according to claim 1 is characterized in that: S4 specifically includes the following sub-steps: S4.1, determine the element selection of the A, B, and X sites of A2B2X6; S4.2, generate A2B2X6 candidates by permutation, combination, and charge neutrality of the compound, where the B position is replaced by a combination of two different metal elements; S4.3, using the theoretical two-dimensional carbon dioxide reduction photocatalyst dataset as input to the machine learning model obtained in S3 to obtain the predicted value of the target variable of the dataset.

7. The data-driven two-dimensional bimetallic oxygen-based carbon dioxide reduction photocatalyst material design method according to claim 1, characterized in that: S5 specifically includes the following sub-steps: S5.1, stability screening, screening indicators include formation energy less than 0, convex hull energy less than 0.2; S5.2, light absorption and reduction potential matching screening, the screening indicators include HSE band gap value between 1.5 and 3.2, valence band value less than -3.89, conduction band value greater than -3.89; S5.3, environmental screening of materials, screening out candidates that do not contain heavy metals, precious metals, or toxic substances.

8. The data-driven two-dimensional bimetallic oxygen-based compound carbon dioxide reduction photocatalyst material design method according to claim 7, characterized in that: S6 specifically includes the following sub-steps: S6.1, construct the crystal structure of the candidate material; S6.2, optimize the crystal structure of candidate materials; S6.3, perform PBE self-consistent calculation on the optimized crystal structure; S6.4, HSE self-consistent calculation based on the crystal structure obtained in S6.3; S6.5, based on the crystal structure obtained in S6.4, HSE non-self-consistent calculations are performed, including HSE band gap, VBM at HSE level, CBM at HSE level, Fermi level and dos state density, to screen out materials that meet the conditions for photocatalytic carbon dioxide reduction, thereby completing the entire photocatalyst material design process.

9. A data-driven two-dimensional bimetallic oxygen-based compound carbon dioxide reduction photocatalyst material design system, characterized in that: include: An initial database establishment module is used to obtain the information of the two-dimensional photocatalyst material system of interest, obtain the two-dimensional material data corresponding to the system information, the two-dimensional material data including the stability information and energy band structure information of the two-dimensional material, and obtain the input characteristics of the two-dimensional material to establish an initial data set; A data preprocessing module cleans and preprocesses the initial data set to obtain a modeling data set for machine learning, wherein the modeling data set includes input features, stability, and band structure information of the two-dimensional material, takes the input features as variables, and takes the stability and band structure information as target variables, and determines the problem attributes of machine learning according to different target variables; The feature engineering and model acquisition module screens the input features of the modeling data set to obtain the best feature subset, trains and evaluates the machine learning model on the best feature subset, obtains the machine learning model, and performs interpretability analysis on the machine learning prediction model; The two-dimensional photocatalyst design module creates a theoretical two-dimensional carbon dioxide reduction photocatalyst dataset by limiting each site element, and uses the theoretical two-dimensional carbon dioxide reduction photocatalyst dataset as the input of the machine learning model to obtain the predicted value of the target variable; A two-dimensional photocatalyst pre-screening module, which screens out candidate photocatalyst materials based on the predicted value of the target variable; The two-dimensional photocatalyst DFT verification module performs DFT verification on the candidate photocatalyst materials to screen out materials that meet the conditions for photocatalytic carbon dioxide reduction.

10. A storage medium containing computer executable instructions, characterized in that: The storage medium of the computer executable instructions is used to execute the data-driven two-dimensional bimetallic oxyacetyl compound carbon dioxide reduction photocatalyst material design method as described in any one of claims 1 to 8 when executed by a computer processor.

Images