CN113808681A - ABO (abnormal noise) rapid prediction based on SHAP-Catboost3Method and system for specific surface area of perovskite material - Google Patents
ABO (abnormal noise) rapid prediction based on SHAP-Catboost3Method and system for specific surface area of perovskite material Download PDFInfo
- Publication number
- CN113808681A CN113808681A CN202111001723.XA CN202111001723A CN113808681A CN 113808681 A CN113808681 A CN 113808681A CN 202111001723 A CN202111001723 A CN 202111001723A CN 113808681 A CN113808681 A CN 113808681A
- Authority
- CN
- China
- Prior art keywords
- abo
- surface area
- specific surface
- shap
- catboost
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention discloses a method for predicting ABO based on SHAP-Catboost3Method and system for finding ABO synthesized based on sol-gel method from literature by using computer system3The chemical formula of the perovskite material, the corresponding specific surface area and the corresponding process parameter data; performing descriptor filling by using the collected chemical formula to generate characteristic variables; carrying out feature screening according to the SHAP feature importance; randomly dividing data into a training set and a testing set; modeling the training set by using a Catboost regression method; according to the established forecasting model, ABO is quickly forecasted3Specific surface area of perovskite-type material. The ABO established by the invention based on reliable literature data and SHAP-Catboost combined modeling method3The prediction model of the specific surface area of the perovskite material has the advantages of simplicity, rapidness, excellent performance, low cost and no pollution.
Description
Technical Field
The invention relates to an ABO3Application of perovskite material in field of catalytic performanceIn particular to a method for rapidly predicting ABO based on SHAP-Catboost3A method for forming the specific surface area of a perovskite material and a system thereof.
Background
ABO3The perovskite oxide is a novel functional material with excellent performance, wide application and great development potential at present. Has stable crystal structure, high thermal stability and good photocatalytic oxidation reduction characteristic, and is widely applied and researched by predecessors in the field of photocatalysis. ABO3The Specific Surface Area (SSA) of the perovskite type is one of important properties related to photocatalytic performance, and researches show that the large specific surface area can cause higher photocatalytic activity, so that ABO can be adjusted3The chemical composition of the perovskite type is used for increasing the specific surface area. Thus establishing ABO3The quantitative relation model of the specific surface area, the atomic parameters and the process parameters of the perovskite material is found, so that the ABO with higher specific surface area is found3The perovskite material has very important research significance.
ABO with higher specific surface area is developed by traditional trial and error method3The perovskite material has high cost and low efficiency. With the development of material genetic engineering, machine learning methods are successfully applied to the field of material design, but most models are black box models and lack interpretability. The ShapleyValue method may obtain the global interpretation by calculating the ShapleyValue of the variable in all samples, and taking the average of their absolute values as the importance value of the feature.
The Catboost is one of Boosting algorithms which are implemented by taking a symmetric decision tree (objective trees) as a base learner, have few parameters, support type variables and have high accuracy, and belongs to an improved implementation of GBDT. The method can efficiently and reasonably process the class-type characteristics; the problems of gradient deviation and prediction deviation are solved; therefore, the occurrence of overfitting is reduced, and the accuracy and generalization capability of the algorithm are improved. The Catboost has four main characteristics:
(1) a completely symmetrical binary tree is adopted as a base model;
(2) supporting the category type variable without preprocessing the non-numerical characteristic;
(3) the rapid and extensible GPU version can be realized by a gradient lifting algorithm based on a GPU to train a model, and multi-card parallel is supported;
(4) higher model quality can be obtained without parameter adjustment.
How to combine the SHAP method with the Catboost method can quickly and accurately predict ABO3The specific surface area of the perovskite-type material is enhanced, the model interpretability is enhanced, the technical problem which needs to be solved urgently is solved, and further exploration and research are needed.
Disclosure of Invention
In order to solve the problems in the prior art, the invention aims to overcome the defects in the prior art and provide a method for quickly predicting ABO based on SHAP-Catboost3The method and the system for predicting the perovskite material specific surface area are applied to overcoming the blindness of an experimental trial and error method and the un-interpretability of a model.
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
ABO (abnormal noise) rapid prediction based on SHAP-Catboost3The method for determining the specific surface area of the perovskite type material comprises the following steps:
1) searching documents by using a computer system, and searching the documents for ABO synthesized based on a sol-gel method3The chemical formula, the specific surface area and process parameter experimental data comprising the calcining temperature and the calcining time of the perovskite material;
2) performing descriptor filling by using the collected chemical formula to generate characteristic variables, wherein at least M descriptors including atom radius, electronegativity and boiling point are filled as the characteristic variables, and M is not less than 21;
3) taking the 2 process parameters of the calcining temperature and the calcining time collected in the step 1) and the descriptor in the step 2) as initial characteristic variables, adopting a SHAP method to carry out characteristic screening according to the importance of SHAP characteristics, and screening at least 7 characteristic variables from the 2+ M initial characteristic variables as independent variables;
4) randomly dividing the data subjected to characteristic variable screening into a training set and a testing set, wherein the proportion of the training set to the testing set is 80% and the proportion of the testing set to the training set is 20%;
5) establishing ABO according to the training set in the step 4) by adopting a Catboost regression algorithm3A Catboost rapid prediction model of the specific surface area of the perovskite material and predicting the effect of the model on the test set in the step 4);
6) rapidly predicting ABO according to the Catboost rapid prediction model established in the step 5)3Specific surface area of perovskite-type material.
Preferably, in the step 2), the filled descriptor refers to an atomic parameter filled according to the perovskite chemical composition.
Preferably, in step 3), the feature importance of the SHAP is measured by averaging the absolute values of the sharey Value, wherein the calculation formula of the sharey Value of the ith feature variable is as follows:
wherein N is the set of all features, the number of features is N, S is a subset of N, | S | is the number of features in the feature set S, V (S) is the contribution of the features in the evaluation feature set S, and V (S ueq { i }) is the contribution of the overall features after the feature i is added on the basis of the feature set S.
Preferably, in the step 5), the Catboost algorithm adopts a GBDT improving method based on a symmetric decision tree. The method is implemented by using a symmetrical decision tree (objective trees) as a base learning machine with few parameters, is one of Boosting algorithms supporting class-type variables and high in accuracy, and belongs to an improved algorithm of GBDT.
ABO implementation rapid prediction3The system for quickly predicting ABO based on SHAP-Catboost algorithm in the invention3A method for forming a perovskite material with a specific surface area, comprising:
an input module: search for ABO synthesized based on sol-gel method from published literature3The chemical formula, the specific surface area and process parameter experimental data including the calcining temperature and the calcining time of the perovskite material are used as input data;
a data analysis module: performing rapid ABO prediction based on SHAP-Catboost algorithm by using data obtained by input module3Method for quickly predicting ABO (anaerobic-anoxic-oxic) specific surface area of perovskite material3Specific surface area of type perovskite material;
an output module: ABO (ethylene-propylene-oxide copolymer)3And outputting the specific surface area data of the perovskite material.
Compared with the prior art, the invention has the following obvious and prominent substantive characteristics and remarkable advantages:
1. the method overcomes the blindness of an experimental trial-and-error method, can quickly and accurately predict the specific surface area of the perovskite material, and can more efficiently predict the specific surface area of the perovskite material only by inputting the chemical components and process parameters of the perovskite material;
2. the model of the method has high interpretability, provides a calculation formula of a Shapley Value to calculate the SHAP characteristic importance of each characteristic variable, can clearly reflect the influence of process parameters and atomic parameters on the specific surface area, and is helpful for guiding the synthesis of the perovskite material with high specific surface area;
3. the method is energy-saving and environment-friendly, chemical products are not used in the whole modeling process, and no pollution is caused to the environment.
Drawings
Fig. 1 is a diagram illustrating the result of ranking the importance of three SHAP features according to an embodiment of the present invention.
FIG. 2 shows an embodiment of the invention in the form of a four ABO3Modeling result graphs of regression models of the specific surface areas of the perovskite materials.
FIG. 3 shows an embodiment of the invention in the form of a four ABO310-fold cross validation result chart of regression model of specific surface area of type perovskite material.
FIG. 4 shows an embodiment of the present invention as a five ABO3Regression model independent measurement of specific surface area of perovskite materialAnd (6) trying to obtain a fruit map.
Detailed Description
The above-described scheme is further illustrated below with reference to specific embodiments, which are detailed below:
the first embodiment is as follows:
in the embodiment, the ABO is quickly predicted based on SHAP-Catboost3The method for determining the specific surface area of the perovskite type material comprises the following steps:
1) searching documents by using a computer system, and searching the documents for ABO synthesized based on a sol-gel method3The chemical formula, the specific surface area and process parameter experimental data comprising the calcining temperature and the calcining time of the perovskite material;
2) performing descriptor filling by using the collected chemical formula to generate characteristic variables, wherein at least M descriptors including atom radius, electronegativity and boiling point are filled as the characteristic variables, and M is not less than 21;
3) taking the 2 process parameters of the calcining temperature and the calcining time collected in the step 1) and the descriptor in the step 2) as initial characteristic variables, adopting a SHAP method to carry out characteristic screening according to the importance of SHAP characteristics, and screening at least 7 characteristic variables from the 2+ M initial characteristic variables as independent variables;
4) randomly dividing the data subjected to characteristic variable screening into a training set and a testing set, wherein the proportion of the training set to the testing set is 80% and the proportion of the testing set to the training set is 20%;
5) establishing ABO according to the training set in the step 4) by adopting a Catboost regression algorithm3A Catboost rapid prediction model of the specific surface area of the perovskite material and predicting the effect of the model on the test set in the step 4);
6) rapidly predicting ABO according to the Catboost rapid prediction model established in the step 5)3Specific surface area of perovskite-type material.
The method for forecasting the specific surface area of the perovskite is simple and rapid, and the predicted value of the specific surface area of the perovskite material can be obtained only by inputting the components of the perovskite material and the calcining temperature and the calcining time in the preparation process; the model of the method of the invention has high interpretability, provides SHAP characteristic importance for characteristic screening, and improves the interpretability of the model.
Example two
This embodiment is substantially the same as the first embodiment, and is characterized in that:
in this embodiment, in step 2), the descriptor of the filling refers to the atomic parameters of the filling according to the perovskite chemical composition.
In this embodiment, in step 3), the feature importance of the SHAP is measured by the average of the absolute values of the sharey Value, wherein the calculation formula of the sharey Value of the ith feature variable is as follows:
wherein N is the set of all features, the number of features is N, S is a subset of N, | S | is the number of features in the feature set S, V (S) is the contribution of the features in the evaluation feature set S, and V (S ueq { i }) is the contribution of the overall features after the feature i is added on the basis of the feature set S.
In this embodiment, in the step 5), the castboost algorithm adopts a GBDT improvement method based on a symmetric decision tree.
This example is based on SHAP-Catboost fast prediction ABO3The method for the specific surface area of the perovskite material is applied to overcoming the blindness of an experimental trial and error method and the unexplainable property of a model, can quickly and accurately predict the specific surface area of the perovskite, is beneficial to guiding the synthesis of the perovskite material with high specific surface area, and has low cost, easy operation and no pollution.
EXAMPLE III
This embodiment is substantially the same as the above embodiment, and is characterized in that:
in the embodiment, ABO is quickly predicted based on SHAP-Catboost machine learning algorithm3A method of specific surface area of a perovskite-type material, comprising the steps of:
1) by investigating the literature, a search 78 was made from the literatureComprises ABO3The 2 process parameter data of the chemical formula, the specific surface area, the calcination temperature and the calcination time of the perovskite-type material are used as an initial sample set. Some data are shown in table 1:
TABLE 1 ABO3Partial data set table of perovskite material
2) Using the chemical formula in the initial sample set to generate 21 atomic parameters as characteristic variables, part of the characteristic variable data is shown in table 2:
TABLE 2 partial atom parameters data sheet
3) Taking the process parameters obtained in the step 1) and the 21 atomic parameters obtained in the step 2 as initial characteristic variables, calculating SHAP characteristic importance by adopting a SHAP method, wherein the importance sequence is shown in figure 1, and selecting the first 7 characteristic variables as independent variables;
the selected 7 characteristic variables are respectively as follows:
CT: the calcination temperature;
AH: calcining time;
b _ Tm: melting point of B site element;
mass: molecular mass;
b _ Hvus: melting enthalpy of B site element;
rc: a critical radius;
b _ aff: electron affinity of the B site element;
4) randomly dividing 78 samples subjected to characteristic variable screening in the step 3) into a training set and a testing set, wherein the proportion of the training set to the testing set is 80% and 20% respectively.
5) Establishing an ABO based on a Catboost regression algorithm according to the training set data in the step 4)3Model and model for quickly forecasting specific surface area of perovskite materialThe type parameters are as follows: tree depth (depth) of 6; the learning rate (learning _ rate) is 0.06; the maximum tree number (iterations) is 900.
6) Rapidly predicting ABO according to the Catboost prediction model established in the step 5)3Specific surface area of perovskite-type material.
This example predicts ABO based on SHAP-Catboost3The method for determining the specific surface area of perovskite material utilizes a computer system to search ABO synthesized based on a sol-gel method from the literature3The chemical formula of the perovskite material and corresponding process parameter data of specific surface area, calcination temperature and calcination time; performing descriptor filling by using the collected chemical formula to generate characteristic variables; carrying out feature screening according to the SHAP feature importance; randomly dividing data into a training set and a testing set; modeling the training set by using a Catboost regression method; according to the established forecasting model, ABO is quickly forecasted3Specific surface area of perovskite-type material. The embodiment is based on reliable literature data and a SHAP-Catboost combined modeling method, and the established ABO3The prediction model of the specific surface area of the perovskite material has the advantages of simplicity, rapidness, excellent performance, low cost and no pollution.
Example four
This embodiment is substantially the same as the above embodiment, and is characterized in that:
in this example, the established ABO was based on 62 samples by Catboost regression3The results of modeling the prediction model of the specific surface area of the perovskite-type material are shown in fig. 2. The correlation coefficient R between the model predicted value and the literature experimental value of the specific surface area is 0.9965, and the root mean square error RMSE is 0.5890.
In this embodiment, 10-fold cross validation is performed on the castboost quantitative prediction model of the perovskite specific surface area established by 62 sample data, and the result is shown in fig. 3, where the correlation coefficient between the model prediction value and the literature true value is 0.8030, and the root mean square error RMSE is 4.2304.
The embodiment can clearly reflect the influence of the process parameters and the atomic parameters on the specific surface area, and is helpful for guiding the high specific surface area ABO3And (4) synthesizing the perovskite material.
EXAMPLE five
This embodiment is substantially the same as the above embodiment, and is characterized in that:
in this embodiment, the specific surface area of the test set sample is quickly predicted according to the established perovskite specific surface area quick prediction model. The prediction result is shown in fig. 4, the correlation coefficient between the model prediction value and the literature true value is 0.9128, and the root mean square error RMSE is 3.0867.
The embodiment can quickly and accurately predict the specific surface area of the perovskite material, and the specific surface area of the perovskite material can be predicted more efficiently only by inputting the chemical components and the process parameters of the perovskite material.
EXAMPLE six
This embodiment is substantially the same as the above embodiment, and is characterized in that:
in this embodiment, an implementation of fast prediction ABO3System for model perovskite material specific surface area, implementation of the above embodiment and based on SHAP-Catboost algorithm for fast prediction of ABO3A method for forming a perovskite material with a specific surface area, comprising:
an input module: search for ABO synthesized based on sol-gel method from published literature3The chemical formula, the specific surface area and process parameter experimental data including the calcining temperature and the calcining time of the perovskite material are used as input data;
a data analysis module: performing rapid ABO prediction based on SHAP-Catboost algorithm by using data obtained by input module3Method for quickly predicting ABO (anaerobic-anoxic-oxic) specific surface area of perovskite material3Specific surface area of type perovskite material;
an output module: ABO (ethylene-propylene-oxide copolymer)3And outputting the specific surface area data of the perovskite material.
The system of the embodiment combines the SHAP method and the Catboost method, and can quickly and accurately predict ABO3While enhancing the model interpretability of the model while the specific surface area of the perovskite material is increased, the program in the system of the embodiment executes SHAP-Catboost to quickly predict ABO3A method for determining the specific surface area of the perovskite material. The method can rapidly and accurately predict calciumThe titanium ore has specific surface area, is helpful for guiding the synthesis of perovskite material with high specific surface area, and has low cost, easy operation and no pollution.
In summary, the above embodiments are based on the SHAP-Catboost regression algorithm to quickly predict ABO3The specific surface area of the perovskite type material comprises the following steps: ABO is collected from literature using a computer system3Specific surface area of the perovskite material, preparation process parameter data (calcining temperature and calcining time) and chemical formula; using the collected 2 process parameters and 21 atomic parameters generated by using a chemical formula as initial characteristic variables; calculating the importance of SHAP characteristics according to a SHAP method, and screening out 7 characteristics according to the importance of the SHAP characteristics; randomly dividing a data set subjected to feature screening into a training set and a testing set, wherein the sample number ratio of the training set to the testing set is 4: 1; with collected ABO3The specific surface area of the perovskite material is taken as a target variable, and 7 screened characteristic variables are taken as independent variables; establishing ABO by adopting CatBOost algorithm3And (3) rapidly forecasting the specific surface area of the perovskite material, and testing the effect of the model on a test set. The prediction ABO established by the invention is based on reliable and real literature data and the latest modeling method3The model of the specific surface area of the perovskite material has the advantages of simplicity, convenience, rapidness, low cost, no pollution, high accuracy and the like. In addition, as the SHAP feature importance is adopted to screen out the feature variables with large contribution to the model, the overall interpretability of the model is improved.
The embodiments of the present invention have been described with reference to the accompanying drawings, but the present invention is not limited to the embodiments, and various changes and modifications can be made according to the purpose of the invention, and any changes, modifications, substitutions, combinations or simplifications made according to the spirit and principle of the technical solution of the present invention shall be equivalent substitutions, as long as the purpose of the present invention is met, and the present invention shall fall within the protection scope of the present invention without departing from the technical principle and inventive concept of the present invention.
Claims (5)
1.ABO (abnormal noise) rapid prediction based on SHAP-Catboost3Method for preparing specific surface area of type perovskite materialThe method is characterized by comprising the following steps:
1) searching documents by using a computer system, and searching the documents for ABO synthesized based on a sol-gel method3The chemical formula, the specific surface area and process parameter experimental data comprising the calcining temperature and the calcining time of the perovskite material;
2) performing descriptor filling by using the collected chemical formula to generate characteristic variables, wherein at least M descriptors including atom radius, electronegativity and boiling point are filled as the characteristic variables, and M is not less than 21;
3) taking the 2 process parameters of the calcining temperature and the calcining time collected in the step 1) and the descriptor in the step 2) as initial characteristic variables, adopting a SHAP method to carry out characteristic screening according to the importance of SHAP characteristics, and screening at least 7 characteristic variables from the 2+ M initial characteristic variables as independent variables;
4) randomly dividing the data subjected to characteristic variable screening into a training set and a testing set, wherein the proportion of the training set to the testing set is 80% and the proportion of the testing set to the training set is 20%;
5) establishing ABO according to the training set in the step 4) by adopting a Catboost regression algorithm3A Catboost rapid prediction model of the specific surface area of the perovskite material and predicting the effect of the model on the test set in the step 4);
6) rapidly predicting ABO according to the Catboost rapid prediction model established in the step 5)3Specific surface area of perovskite-type material.
2. The method of claim 1 for fast predicting ABO based on SHAP-Catboost algorithm3The method for determining the specific surface area of the perovskite material is characterized in that in the step 2), the filled descriptors refer to atomic parameters filled according to the chemical composition of the perovskite.
3. The method of claim 1 for fast predicting ABO based on SHAP-Catboost algorithm3Method for determining the specific surface area of perovskite-type materials, characterized in that, in step 3), the characteristic importance of SHAP is measured by the mean of the absolute values of Shapley ValueThe calculation formula of sharley Value of the ith characteristic variable is as follows:
wherein N is the set of all features, the number of features is N, S is a subset of N, | S | is the number of features in the feature set S, V (S) is the contribution of the features in the evaluation feature set S, and V (S ueq { i }) is the contribution of the overall features after the feature i is added on the basis of the feature set S.
4. The method of claim 1 for fast predicting ABO based on SHAP-Catboost algorithm3The method for determining the specific surface area of the perovskite material is characterized by comprising the following steps: in the step 5), the Catboost algorithm adopts a GBDT improving method based on a symmetric decision tree.
5. ABO implementation rapid prediction3System for the rapid prediction of ABO based on the SHAP-Catboost algorithm, in particular for the surface area of perovskite materials, according to any of claims 1 to 4, carried out3The method for determining the specific surface area of the perovskite material is characterized by comprising the following steps:
an input module: search for ABO synthesized based on sol-gel method from published literature3The chemical formula, the specific surface area and process parameter experimental data including the calcining temperature and the calcining time of the perovskite material are used as input data;
a data analysis module: performing rapid ABO prediction based on SHAP-Catboost algorithm by using data obtained by input module3Method for quickly predicting ABO (anaerobic-anoxic-oxic) specific surface area of perovskite material3Specific surface area of type perovskite material;
an output module: ABO (ethylene-propylene-oxide copolymer)3And outputting the specific surface area data of the perovskite material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111001723.XA CN113808681A (en) | 2021-08-30 | 2021-08-30 | ABO (abnormal noise) rapid prediction based on SHAP-Catboost3Method and system for specific surface area of perovskite material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111001723.XA CN113808681A (en) | 2021-08-30 | 2021-08-30 | ABO (abnormal noise) rapid prediction based on SHAP-Catboost3Method and system for specific surface area of perovskite material |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113808681A true CN113808681A (en) | 2021-12-17 |
Family
ID=78894314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111001723.XA Pending CN113808681A (en) | 2021-08-30 | 2021-08-30 | ABO (abnormal noise) rapid prediction based on SHAP-Catboost3Method and system for specific surface area of perovskite material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113808681A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114444986A (en) * | 2022-04-11 | 2022-05-06 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
| CN117275634A (en) * | 2023-11-20 | 2023-12-22 | 桑若(厦门)光伏产业有限公司 | Perovskite solar cell design method and device based on machine learning |
| CN117275634B (en) * | 2023-11-20 | 2024-05-28 | 桑若(厦门)光伏产业有限公司 | Perovskite solar cell design method and device based on machine learning |
-
2021
- 2021-08-30 CN CN202111001723.XA patent/CN113808681A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114444986A (en) * | 2022-04-11 | 2022-05-06 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
| CN114444986B (en) * | 2022-04-11 | 2022-06-03 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
| CN117275634A (en) * | 2023-11-20 | 2023-12-22 | 桑若(厦门)光伏产业有限公司 | Perovskite solar cell design method and device based on machine learning |
| CN117275634B (en) * | 2023-11-20 | 2024-05-28 | 桑若(厦门)光伏产业有限公司 | Perovskite solar cell design method and device based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Szymanski et al. | Probabilistic deep learning approach to automate the interpretation of multi-phase diffraction spectra | |
| CN112382352B (en) | Method for quickly evaluating structural characteristics of metal organic framework material based on machine learning | |
| CN110442666B (en) | Mineral resource prediction method and system based on neural network model | |
| JP4780554B2 (en) | Constituent material information search method for new material and constituent material information search system for new material | |
| CN106815643A (en) | Infrared spectrum Model Transfer method based on random forest transfer learning | |
| CN112927769B (en) | MOFs material defect structure prediction method based on pore size distribution curve | |
| CN112613536A (en) | Near infrared spectrum diesel grade identification method based on SMOTE and deep learning | |
| CN111126511A (en) | Vegetation index fusion-based LAI quantitative model establishment method | |
| CN112289391A (en) | Anode aluminum foil performance prediction system based on machine learning | |
| CN113808681A (en) | ABO (abnormal noise) rapid prediction based on SHAP-Catboost3Method and system for specific surface area of perovskite material | |
| Baird et al. | DiSCoVeR: a materials discovery screening tool for high performance, unique chemical compositions | |
| CN114416707A (en) | Method and device for automated feature engineering of industrial time series data | |
| CN107016416B (en) | Data classification prediction method based on neighborhood rough set and PCA fusion | |
| CN114334025A (en) | Construction and verification method of cement clinker calcination environment variable | |
| CN109960146A (en) | The method for improving soft measuring instrument model prediction accuracy | |
| CN113380345A (en) | Organic chemical coupling reaction yield prediction and analysis method based on deep forest | |
| CN106529680B (en) | A kind of multiple dimensioned extreme learning machine integrated modelling approach based on empirical mode decomposition | |
| CN111832748A (en) | Electronic nose width learning method for performing regression prediction on concentration of mixed gas | |
| CN117093890A (en) | Comprehensive evaluation method for ecological environment of energy resource development area | |
| CN111274123A (en) | Automatic generation method and framework of safety protection software test set based on software genes | |
| CN111914009B (en) | Pyspark-based energy storage data calculation and analysis method | |
| CN114818493A (en) | Method for quantitatively evaluating integrity degree of tunnel rock mass | |
| CN113835964A (en) | Cloud data center server energy consumption prediction method based on small sample learning | |
| CN112116091A (en) | On-line forecasting method for rapidly forecasting band gap of organic-inorganic hybrid perovskite based on machine learning | |
| Ouyang et al. | Significant Wave Height Forecasting Based on EMD-TimesNet Networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |