Stable adsorption configuration global search method based on similar distribution and active learning

Abstract

The embodiment of the invention discloses a stable adsorption configuration global search method based on similarity distribution and active learning. The method comprises the following steps: S1, constructing a knowledge-embedded high-throughput adsorption structure model; s2, constructing an adsorption structure small sample data set based on clustering stratified sampling; s3, in combination with the adsorption structure small sample data set and the Gaussian process regression model, establishing an adsorption energy prediction-oriented proxy model; and S4, training the proxy model, and searching a stable adsorption configuration. The embodiment of the invention discloses a stable adsorption configuration global search method based on similar distribution and active learning. By means of catalytic configuration high-throughput modeling containing knowledge embedding, small sample data set construction based on clustering stratified sampling, a small sample recommendation model based on Gaussian process regression and hybrid convergence criteria considering data distribution and agent model prediction, efficient searching of a stable adsorption configuration in a large structure space is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of computational chemistry, and in particular relates to a global search method for stable adsorption configurations based on similarity distribution and active learning. Background Art

[0002] Computational catalysis research based on knowledge and first-principles methods has great potential in exploring large material spaces at low cost and accelerating high-cost, long-term trial-and-error experimental research. It plays a leading role in the development of catalysts in the third scientific paradigm based on computational simulation, and has further become the cornerstone of data-driven catalytic research in the fourth research paradigm. In the theoretical study of heterogeneous catalysis, the absorption energy calculation and stable adsorption structure identification of key species are the basis for explaining the mechanism and structure-activity relationship of catalytic reactions and rationally designing and screening new catalytic systems. In actual research, high-throughput calculations are usually used to determine the optimal binding configuration of adsorbates such as molecules or atoms on specific crystal faces in complex surface chemical environments, but this brings about huge consumption of computing resources and costs, occupying most of the computing resource requirements in high-throughput research on catalytic mechanisms and machine learning research. Therefore, how to search for stable adsorption configurations in a huge structural space composed of all surface binding configurations of adsorbates at low cost and high efficiency is the key to reducing the cost of theoretical design and development of catalysts.

[0003] Combining the potential energy surface fitting of first-principle calculations or machine learning with the search scheme of basin jumping or minimum jumping algorithms can effectively reduce the number of calculated configurations and reduce research costs compared to enumeration-based calculation studies. However, the potential energy surface fitting data and multiple calculation iterations still inevitably require a large amount of computing resources. Summary of the invention

[0004] In view of this, the embodiment of the present invention discloses a global search method for stable adsorption configuration based on similarity distribution and active learning, comprising the steps of:

[0005] S1. Construct a high-throughput adsorption structure model with knowledge embedding; specifically including:

[0006] Enumerate all potential surface sites or site combinations in the adsorption system;

[0007] Combine domain knowledge of the adsorbate on the specific catalytic surface of the adsorption system to remove clearly unstable sites or site combinations;

[0008] Automatically construct an adsorption model of the adsorbate surface binding to the catalytic crystal surface site based on the selected site or site combination;

[0009] S2. Construct a small sample data set of adsorption structure based on clustering and stratified sampling; specifically including:

[0010] Combined with the physical property information of the surface atoms of the catalytic configuration, candidate features describing the adsorption structure are constructed;

[0011] Cluster analysis was performed on all candidate adsorption structures using clustering methods;

[0012] The proportion of adsorption structures in different clusters is obtained based on clustering, and the farthest point sampling is used to extract the corresponding number of adsorption structures from each cluster;

[0013] High-throughput calculation of the binding energy of adsorbates on selected adsorption structures to construct a small sample data set of adsorption structures with similar data distribution to the large candidate space;

[0014] S3. Combining the adsorption structure small sample data set and Gaussian process regression model, a proxy model for adsorption energy prediction is established;

[0015] S4. Training the agent model to search for stable adsorption configurations; specifically including:

[0016] According to the predicted value and uncertainty output by the proxy model, the acquisition function value of all adsorption structure samples is calculated, that is, the probability of improvement relative to the optimal value of the small sample of adsorption structure, or the expected improvement value;

[0017] Select the candidate adsorption structure with the largest improvement value as the search result, calculate the binding energy of the adsorbate on the candidate adsorption structure, and update the small sample data set of the adsorption structure;

[0018] Determine whether the hybrid convergence criterion is met. If so, stop the iteration, and the optimal structure in the small sample data set of adsorption structure is the global optimal adsorption structure, which is determined as the stable adsorption configuration; if not, retrain the proxy model and conduct the next search.

[0019] Furthermore, in some embodiments of the global search method for stable adsorption configuration based on similarity distribution and active learning, in step S4, the hybrid convergence criterion is the union of the first criterion and the second criterion; wherein the first criterion is a criterion based on similarity distribution, and the second criterion is a criterion based on the prediction results of the proxy model.

[0020] In some embodiments, the global search method for stable adsorption configuration based on similarity distribution and active learning is disclosed, wherein the first criterion is a criterion for directly determining the global optimal value based on Gaussian distribution; specifically, the method comprises:

[0021] Fitting a Gaussian distribution to the binding energy data of a small sample data set of adsorption structures;

[0022] Determine whether the optimal adsorption energy of a small sample data set of adsorption structures is in the area to the left of the mean value of the Gaussian distribution minus two times the standard deviation;

[0023] If it is satisfied, the optimal adsorption structure of the small sample data set is determined to be the global most stable adsorption structure of the large candidate space; if it is not satisfied, the optimal adsorption structure of the small sample data set is determined not to be the global most stable adsorption structure of the large candidate space.

[0024] In some embodiments of the global search method for stable adsorption configurations based on similarity distribution and active learning, the second criterion is a criterion for determining the uncertainty change of the binding energy of the global optimal structure predicted by the proxy model; specifically, it includes:

[0025] It is determined whether the uncertainty change of the binding energy of the global optimal structure predicted by the proxy model is less than the set threshold. If it is satisfied, the proxy model stops iterating and determines that the predicted current global optimal structure is the global most stable adsorption structure; if it is not satisfied, the proxy model continues to iterate.

[0026] In the global search method for stable adsorption configurations based on similarity distribution and active learning disclosed in some embodiments, the threshold for the uncertainty change of the binding energy is set according to the calculation accuracy of the density functional theory.

[0027] In the global search method for stable adsorption configurations based on similarity distribution and active learning disclosed in some embodiments, the threshold value for the uncertainty change of binding energy is set to 0.025 eV.

[0028] Some embodiments disclose a global search method for stable adsorption configurations based on similarity distribution and active learning. For an alloy system, a site or site combination containing at least two elements among the surface atoms bound by the adsorbate is selected as a potential surface site or site combination.

[0029] Some embodiments disclose a global search method for stable adsorption configurations based on similarity distribution and active learning. For co-adsorption configurations, a site combination whose distance between adsorbates satisfies a set range is selected as a potential site combination.

[0030] In the global search method for stable adsorption configurations based on similarity distribution and active learning disclosed in some embodiments, in step S4, multiple candidate adsorption structures with the largest improvement values ​​are selected as search results.

[0031] In some embodiments of the global search method for stable adsorption configurations based on similarity distribution and active learning, in step S4, two candidate adsorption structures with the largest improvement values ​​are selected as search results.

[0032] The global search method for stable adsorption configurations based on similarity distribution and active learning disclosed in an embodiment of the present invention realizes efficient search for stable adsorption configurations from a large structure space through high-throughput modeling of catalytic configurations including knowledge embedding, construction of a small sample data set based on clustering and stratified sampling, a small sample recommendation model based on Gaussian process regression, and a hybrid convergence criterion considering data distribution and proxy model prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 , a flow chart of the global search method for stable adsorption configuration based on similarity distribution and active learning in Example 1;

[0034] Figure 2 , schematic diagram of the co-adsorption model of NH and OH on the Cu diatomic configuration on the Pt(111) crystal plane in Example 1;

[0035] Figure 3 , the performance of the NH_OH adsorption configuration binding energy prediction model in Example 1;

[0036] Figure 4 , the search results based on the initial small samples derived from different random numbers in Example 1;

[0037] Figure 5 , the active learning search results in Example 1 based on small sample data sets of different sizes (20, 30 and 40) and different sampling strategies. DETAILED DESCRIPTION

[0038] The word "embodiment" used herein as an "exemplary" does not necessarily mean that any embodiment described is superior or better than other embodiments. Performance index tests in the embodiments of the present invention are performed using conventional test methods in the art unless otherwise specified. It should be understood that the terms described in the embodiments of the present invention are only used to describe specific implementation methods and are not intended to limit the contents disclosed in the embodiments of the present invention.

[0039] Unless otherwise specified, the technical and scientific terms used herein have the same meanings as commonly understood by ordinary technicians in the technical field to which the embodiments of the present invention belong; other experimental methods and technical means not specifically specified in the embodiments of the present invention refer to experimental methods and technical means commonly used by ordinary technicians in the field.

[0040] The terms "substantially" and "approximately" used herein are used to describe small fluctuations. For example, they can refer to less than or equal to ±5%, such as less than or equal to ±2%, such as less than or equal to ±1%, such as less than or equal to ±0.5%, such as less than or equal to ±0.2%, such as less than or equal to ±0.1%, such as less than or equal to ±0.05%. The numerical data represented or presented in the range format herein are used only for convenience and brevity, and should therefore be flexibly interpreted as including not only the values ​​clearly listed as the limits of the range, but also all independent values ​​or sub-ranges contained in the range. For example, the numerical range of "1-5%" should be interpreted as including not only the clearly listed values ​​of 1% to 5%, but also the independent values ​​and sub-ranges within the range shown. Therefore, independent values ​​such as 2%, 3.5% and 4% and sub-ranges such as 1%-3%, 2%-4% and 3%-5% are included in this numerical range. This principle also applies to the range of only one numerical value. In addition, such an interpretation applies regardless of the width of the range or the characteristics described.

[0041] In this document, including in the claims, transitional words such as "comprises," "includes," "with," "having," "containing," "involving," "accommodating," etc. are understood to be open-ended, i.e., meaning "including but not limited to." Only the transitional words "consisting of" and "composed of" are closed transitional words.

[0042] In order to better illustrate the present invention, numerous specific details are provided in the specific examples below. It should be understood by those skilled in the art that the present invention can be implemented without certain specific details. In the embodiments, some methods, means, instruments, equipment, etc. well known to those skilled in the art are not described in detail in order to highlight the gist of the present invention.

[0043] Under the premise of no conflict, the technical features disclosed in the embodiments of the present invention may be arbitrarily combined, and the resulting technical solutions belong to the contents disclosed in the embodiments of the present invention.

[0044] Generally, the large structure space refers to the structure space composed of all possible structures that contain the optimal structure. Global search refers to the method of trying to consider the entire search space of the problem to ensure that the global optimal solution is found. It is a professional term relative to local search; local search starts from an initial solution and gradually finds the optimal solution through continuous small steps of improvement. It is easy to fall into local optimality, that is, the optimal solution obtained may only be in the current neighborhood, not necessarily in the entire search space.

[0045] In some embodiments, the global search method for stable adsorption configurations based on similarity distribution and active learning comprises the steps of:

[0046] S1. Construct a high-throughput adsorption structure model with knowledge embedding; specifically including:

[0047] Enumerate all potential surface sites or site combinations in the adsorption system;

[0048] Combine domain knowledge of the adsorbate on the specific catalytic surface of the adsorption system to remove clearly unstable sites or site combinations;

[0049] Automatically construct an adsorption model of the adsorbate surface binding to the catalytic crystal surface site based on the selected site or site combination;

[0050] S2. Construct a small sample data set of adsorption structure based on clustering and stratification; specifically including:

[0051] Combined with the electronegativity, atomic mass, valence electrons and other physical properties of the surface atoms of the catalytic configuration, candidate features describing the adsorption structure are constructed, such as the average electronegativity, atomic mass, valence electrons of surface atoms, the average electronegativity, atomic mass, valence electrons of subsurface atoms, and the average electronegativity, atomic mass, valence electrons of atoms of the adsorbed substance;

[0052] Cluster analysis is performed on all candidate adsorption structures using clustering methods; clustering methods usually include K-means clustering algorithm, etc.

[0053] According to the proportion of adsorption structures in different clusters obtained by clustering, the farthest point sampling is used to extract the corresponding number of adsorption structures from each cluster;

[0054] High-throughput calculation of the binding energy of adsorbates on selected adsorption structures to construct a small sample data set of adsorption structures with similar data distribution to the large candidate space;

[0055] S3. Combining the adsorption structure small sample data set and Gaussian process regression model, a proxy model for adsorption energy prediction is established;

[0056] S4. Training the agent model to search for stable adsorption configurations; specifically including:

[0057] According to the predicted value and uncertainty output by the proxy model, the acquisition function value of all adsorption structure samples is calculated, that is, the probability of improvement (PI) or expected improvement (EI) relative to the optimal value of the small sample of adsorption structure.

[0058] The candidate adsorption structure with the largest lift value is selected as the search result, the binding energy of the adsorbate on the candidate adsorption structure is calculated, and the small sample data set of the adsorption structure is updated; usually, one or more candidate adsorption structures with the largest lift value can be selected; multiple candidate structures with the largest lift value usually refer to sorting by the expected lift value size, and the required number of candidate adsorption structures are selected in the order of ranking position.

[0059] Determine whether the hybrid convergence criterion is met. If so, stop the iteration, and the optimal structure in the small sample data set of adsorption structure is the global optimal adsorption structure, which is determined as the stable adsorption configuration; if not, retrain the proxy model and conduct the next search.

[0060] In some embodiments of the global search method for stable adsorption configuration based on similarity distribution and active learning, in step S4, the hybrid convergence criterion is the union of the first criterion and the second criterion; wherein the first criterion is a criterion based on similarity distribution, and the second criterion is a criterion based on the prediction result of the proxy model. Generally, the union of the first criterion and the second criterion is used as the hybrid convergence criterion, which usually means that the first criterion and the second criterion are satisfied at the same time, and then the optimal structure determined to be searched is the global optimal adsorption structure, that is, the most stable adsorption configuration.

[0061] Usually, in the hybrid convergence criterion, the first criterion based on similar distribution can determine the optimal structure without iteration or with fewer iterations; the second criterion based on the prediction results of the surrogate model can stop the model iteration in time when the search model reaches a certain accuracy, avoiding the deviation of small samples and candidate spatial data distribution caused by excessive search in the potential optimal area of ​​active learning, which in turn leads to search failure. The combination of the two can ensure that the model searches for the global optimal structure with fewer iterations. The hybrid convergence criterion based on similar distribution and surrogate model suppresses excessive model iterations and distribution deviations while determining the global optimal value, effectively balancing efficiency and accuracy.

[0062] In some embodiments, the stable adsorption configuration search method based on similarity distribution and active learning realizes efficient search for the global optimum in a large space based on a small initial sample of less than 10% and a small number of iterations of less than 2.

[0063] In some embodiments, the first criterion is a criterion for directly determining the global optimal value based on the Gaussian distribution; specifically, it includes: fitting the binding energy data of the adsorption structure small sample data set to a Gaussian distribution; judging whether the optimal adsorption energy of the adsorption structure small sample data set is in the left area of ​​the mean value of the Gaussian distribution minus two times the standard deviation; that is, judging whether the optimal adsorption energy satisfies the following conditions:

[0064] E min ≤μ-2σ;

[0065] Among them, E min is the optimal adsorption energy of the small sample data set, μ is the mean of the Gaussian distribution, and σ is the standard deviation;

[0066] If it is satisfied, the optimal adsorption structure of the small sample data set is determined to be the global most stable adsorption structure of the large candidate space; if it is not satisfied, the optimal adsorption structure of the small sample data set is determined not to be the global most stable adsorption structure of the large candidate space.

[0067] In some embodiments, the second criterion is a criterion for determining the uncertainty change of the binding energy of the global optimal structure predicted by the proxy model; specifically comprising:

[0068] It is determined whether the uncertainty change of the binding energy of the global optimal structure predicted by the proxy model is less than the set threshold. If it is satisfied, the proxy model stops iterating and determines that the current predicted global optimal structure is the most stable adsorption structure in the world; if it is not satisfied, the proxy model continues to iterate. The threshold of the uncertainty change of the binding energy is set to 0.025eV according to the density functional calculation accuracy.

[0069] The technical details are further illustrated below in conjunction with embodiments.

[0070] Example 1

[0071] In Example 1, the search for stable adsorption configurations of NH and OH groups co-adsorbed on Cu diatomic configurations on Pt (111) crystal plane is taken as an example to illustrate the global search method for stable adsorption configurations based on similarity distribution and active learning; Figure 2 As shown; Figure 2 Here, 1 represents Cu atom, 2 represents N and 3 represents OH;

[0072] A global search method for stable adsorption configurations of NH and OH co-adsorbed (NH_OH) diatomic Cu on Pt(111) crystal surface, such as Figure 1 As shown, including:

[0073] S1. Construct a knowledge-embedded high-throughput adsorption structure model; specifically, enumerate all potential surface sites or site combinations on the Pt(111) crystal surface; remove clearly unstable sites or site combinations by combining the domain knowledge of adsorbate NH and OH double groups on the Pt(111) crystal surface; automatically construct an adsorption model of the adsorbate surface bound to the catalytic crystal surface site based on the selected site or site combination;

[0074] S2. Construct a small sample data set of adsorption structures based on clustering and stratification; specifically, it includes: combining the physical property information of the surface atoms of the catalytic configuration to construct candidate features describing the adsorption structure; using clustering methods to perform cluster analysis on all candidate adsorption structures; according to the number ratio of adsorption structures in different clusters, using farthest point sampling to extract the corresponding number of adsorption structures from each cluster; high-throughput calculation of the binding energy of the adsorbate on the selected adsorption structure to construct a small sample data set of adsorption structures with similar data distribution to the large candidate space;

[0075] S3. Combining the adsorption structure small sample data set and Gaussian process regression model, a proxy model for adsorption energy prediction is established;

[0076] S4. Training the agent model to search for stable adsorption configurations; specifically including:

[0077] According to the predicted value and uncertainty output by the proxy model, the improvement probability or expected improvement value of all adsorption structure samples relative to the optimal value of the adsorption structure small sample is calculated;

[0078] Select the candidate adsorption structure with the largest improvement value as the search result, calculate the binding energy of the adsorbate on the candidate adsorption structure, and update the small sample data set of the adsorption structure;

[0079] Determine whether the hybrid convergence criterion is met. If so, stop the iteration, and the optimal structure in the small sample data set of adsorption structure is the global optimal adsorption structure, which is determined as the stable adsorption configuration; if not, retrain the proxy model and conduct the next search.

[0080] In Example 1, a high-throughput adsorption structure model based on knowledge embedding was constructed, and a large data set of 405 NH_OH co-adsorption structure models was constructed;

[0081] Combining K-means clustering, farthest point sampling and high-throughput calculation, a small sample data set of adsorption configuration containing 30 samples was constructed, and a Gaussian distribution was fitted to the small sample data set of adsorption configuration to determine the 95% confidence interval boundary of the distribution.

[0082] Based on Gaussian process regression and a small sample data set of adsorption configurations, a prediction model for the binding energy of NH_OH adsorption configurations was trained.

[0083] Predict the binding energy of the system in a large material space and the uncertainty of the minimum value in the predicted value. 5-fold cross validation is used to calculate the mean absolute error (MAE) and root mean square error (RMSE) of the training set and the test set. Figure 3 As shown, it shows that the prediction model based on small samples has better accuracy;

[0084] The sampling effect is evaluated by combining the hybrid convergence criterion. If the hybrid convergence criterion is met, the iteration is stopped. Otherwise, active learning based on Bayesian optimization is used to search for new data points from the large material space, adjust the distribution of the small sample data set and optimize the prediction model: the binding energy corresponding to all adsorption structure models in the large data set is calculated by combining the prediction model, and the expected improvement value of each adsorption configuration is evaluated by combining the Expected Improvement (EI) acquisition function, and the two adsorption configurations with the largest improvement value are recommended and the corresponding binding energy is calculated. The small sample data set of adsorption configuration is added, and the hybrid criterion is used again to evaluate whether the model recommends the global optimal adsorption configuration. Repeat the above process until the model converges.

[0085] The search results based on the initial small sample obtained using different random numbers are as follows Figure 4 As shown, considering the calculation error, the binding energy results of -6.942 and -6.944 eV correspond to the same NH_OH adsorption structure. It can be found that in Example 1, the global optimal value, that is, the most stable NH_OH adsorption structure, can be determined in less than 2 iterations, indicating that the global search method based on active learning and similar distribution has excellent robustness.

[0086] The search performance of the global search method is further evaluated by combining small sample datasets of adsorption configurations of different sizes and different sampling strategies, e.g. Figure 5 As shown. The results show that compared with random sampling and farthest point sampling, active learning search based on the composite sampling strategy of clustering and farthest point sampling can achieve the determination of the global optimal configuration with few or no active learning iterations, and has the highest sampling efficiency. On the other hand, Figure 5 As shown in Figure c, the active learning framework can achieve non-iterative search for the global optimum in small sample data sets containing 20, 30, and 40 data points, indicating that the active learning framework of the global search method has strong robustness.

[0087] The global search method for stable adsorption configurations based on similarity distribution and active learning disclosed in an embodiment of the present invention realizes efficient search for stable adsorption configurations from a large structure space through high-throughput modeling of catalytic configurations including knowledge embedding, construction of a small sample data set based on clustering and stratified sampling, a small sample recommendation model based on Gaussian process regression, and a hybrid convergence criterion considering data distribution and proxy model prediction.

[0088] The technical solutions disclosed in the embodiments of the present invention and the technical details disclosed in the embodiments are merely illustrative of the inventive concept of the present invention and do not constitute a limitation on the technical solutions of the embodiments of the present invention. Any conventional changes, replacements or combinations of the technical details disclosed in the embodiments of the present invention have the same inventive concept as the present invention and are within the protection scope of the claims of the present invention.

Claims

1. A global search method for stable adsorption configurations based on similarity distribution and active learning, characterized in that: Includes steps: S1. Construct a high-throughput adsorption structure model with knowledge embedding; specifically including: Enumerate all potential surface sites or site combinations in the adsorption system; Combine domain knowledge of the adsorbate on the specific catalytic surface of the adsorption system to remove clearly unstable sites or site combinations; Automatically construct an adsorption model of the adsorbate surface binding to the catalytic crystal surface site based on the selected site or site combination; S2. Construct a small sample data set of adsorption structure based on clustering and stratified sampling; specifically including: Combined with the physical property information of the surface atoms of the catalytic configuration, candidate features describing the adsorption structure are constructed; Cluster analysis was performed on all candidate adsorption structures using clustering methods; The proportion of adsorption structures in different clusters is obtained based on clustering, and the farthest point sampling is used to extract the corresponding number of adsorption structures from each cluster; High-throughput calculation of the binding energy of adsorbates on selected adsorption structures to construct a small sample data set of adsorption structures with similar data distribution to the large candidate space; S3. Combining the adsorption structure small sample data set and Gaussian process regression model, a proxy model for adsorption energy prediction is established; S4. Training the agent model to search for stable adsorption configurations; specifically including: According to the predicted value and uncertainty output by the proxy model, the acquisition function value of all adsorption structure samples is calculated, that is, the probability of improvement or the expected improvement value relative to the optimal value of the small sample of adsorption structure; Select the candidate adsorption structure with the largest improvement value as the search result, calculate the binding energy of the adsorbate on the candidate adsorption structure, and update the small sample data set of the adsorption structure; Determine whether the hybrid convergence criterion is met. If so, stop the iteration, and the optimal structure in the small sample data set of adsorption structure is the global optimal adsorption structure, which is determined as the stable adsorption configuration; if not, retrain the proxy model and perform the next search result.

2. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 1, characterized in that: In step S4, the hybrid convergence criterion is the union of the first criterion and the second criterion; wherein the first criterion is a criterion based on similar distribution, and the second criterion is a criterion based on the prediction result of the proxy model.

3. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 2, characterized in that: The first criterion is a criterion for directly determining the global optimal value based on Gaussian distribution; specifically, it includes: Fitting a Gaussian distribution to the binding energy data of a small sample data set of adsorption structures; Determine whether the optimal adsorption energy of a small sample data set of adsorption structures is in the area to the left of the mean value of the Gaussian distribution minus two times the standard deviation; If it is satisfied, the optimal adsorption structure of the small sample data set is determined to be the global most stable adsorption structure of the large candidate space; if it is not satisfied, the optimal adsorption structure of the small sample data set is determined not to be the global most stable adsorption structure of the large candidate space.

4. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 2, characterized in that: The second criterion is a criterion for determining the uncertainty change of the binding energy of the global optimal structure predicted by the proxy model; specifically, it includes: It is determined whether the uncertainty change of the binding energy of the global optimal structure predicted by the proxy model is less than the set threshold. If it is satisfied, the proxy model stops iterating and determines that the predicted current global optimal structure is the global most stable adsorption structure; if it is not satisfied, the proxy model continues to iterate.

5. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 1, characterized in that: For the alloy system, sites or site combinations containing at least two elements among the surface atoms to which the adsorbate binds are selected as potential surface sites or site combinations.

6. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 1, characterized in that: For the co-adsorption configuration, the site combination whose distance between the adsorbates satisfies the set range is selected as the potential site combination.

7. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 1, characterized in that: In step S4, a plurality of candidate adsorption structures with the largest lift values ​​are selected as the push search results.

8. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 1, characterized in that: In step S4, two candidate adsorption structures with the largest improvement values ​​are selected as search results.

9. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 4, characterized in that: The threshold for the uncertainty change in the binding energy is set according to the density functional calculation accuracy.

10. The global search method for stable adsorption configuration based on similarity distribution and active learning according to claim 9, characterized in that: The threshold for uncertainty change in binding energy was set to 0.025 eV.

Images