CN112132185A - Method for rapidly predicting band gap of double perovskite oxide based on data mining - Google Patents
Method for rapidly predicting band gap of double perovskite oxide based on data mining Download PDFInfo
- Publication number
- CN112132185A CN112132185A CN202010869907.7A CN202010869907A CN112132185A CN 112132185 A CN112132185 A CN 112132185A CN 202010869907 A CN202010869907 A CN 202010869907A CN 112132185 A CN112132185 A CN 112132185A
- Authority
- CN
- China
- Prior art keywords
- band gap
- perovskite oxide
- double perovskite
- data
- double
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for rapidly predicting a band gap of a double perovskite oxide based on data mining, which comprises the following steps: 1) searching A from the document by using a computer system2B′B″O6The band gap value and the chemical formula of the perovskite material; 2) generating corresponding descriptors as independent variables according to the chemical formula; 3) randomly dividing a data set into a training set and a testing set; 4) performing variable screening by combining maximum correlation minimum redundancy with a support vector machine leave-one-out method; 5) establishing a prediction model of the double perovskite oxide band gap by using the target variable, the screened independent variable and a support vector machine algorithm through a training set sample; 6) and (4) rapidly forecasting the band gap of the double perovskite oxide in the test set sample according to the established band gap model. The invention is based on reliable literature data and modeling method, and the constructed double perovskiteThe forecasting model of the oxide band gap has the advantages of simplicity, convenience, rapidness, low cost and no pollution.
Description
Technical Field
The invention relates to the field of electrical properties of double perovskite oxides, in particular to a method for rapidly predicting a band gap of a double perovskite oxide based on data mining.
Technical Field
Perovskite is one of the hottest materials at present, and the structure of perovskite is generally a simple perovskite structure, a double perovskite structure and a layered perovskite structure. Due to its stable crystal structure and unique physicochemical properties, perovskites can be used in a variety of fields such as solar cells, solid fuel cells, sensors, thermoelectricity, magnetic storage and catalysts.
The Band Gap (Band Gap) is the difference between the energies of the lowest point of the conduction Band and the highest point of the valence Band, and is also called energy Gap and forbidden Band width, and the symbol is Eg. In a solid, the energy band is discontinuous, and therefore the electron energy is also discontinuous, and only when free electrons or holes are present, the energy band has the property of conducting electricity. The band where free electrons exist becomes the conduction band and the band where free holes exist is called the valence band, and the bound electrons must gain enough energy to transition from the valence band to the conduction band, and the minimum value of this energy is the band gap. The band gap is an important characteristic parameter of a semiconductor, and the size of the band gap is mainly determined by the energy band structure of the semiconductor, namely, the size is related to the bonding property of a crystal structure and atoms and the like. The perovskite is a core material of a perovskite solar cell device, and the band gap of the perovskite is one of important influence factors of photoelectric conversion efficiency, so that the research on the band gap is of great significance.
The maximum correlation minimum redundancy (mRMR) is a classical argument selection algorithm based on information theory. The core idea of mRMR is to maximize the correlation between the independent variables and the target variables, and minimize the correlation between the independent variables and the independent variables.
A Support Vector Machine (SVM) is a new machine learning method established by mathematicians vladimix n. vapnik and the like on the basis of a Statistical Learning Theory (SLT), and includes a Support Vector Classification (SVC) algorithm and a Support Vector Regression (SVR) algorithm. The SVM is an effective method for solving the problems of nonlinear classification and regression, and is also a supervised learning algorithm. The method considers the balance between experience risks and expected risks, enables the calculation model to have good prediction and popularization performance, and is widely applied to various fields. The support vector machine can model a few small samples and obtain a model with better forecasting capability. However, the application of a support vector regression method to establish an oxide double perovskite band gap prediction model has not been reported in related literatures.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a method for rapidly predicting the band gap of double perovskite oxide based on data mining, and predicts A through theory and calculation2B′B″O6The band gap of the double perovskite material is calculated by combining maximum correlation minimum redundancy with support vector machine regression and rapidly obtaining a calculation result through a data mining method, and the method is free of experiment, convenient and rapid, saves manpower and is green and environment-friendly.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for rapidly predicting the band gap of a double perovskite oxide based on data mining comprises the following steps:
1) searching A from the document by using a computer system2B′B″O6The band gap value and the chemical formula of the double perovskite oxide material are used as data set samples;
2) generating corresponding atom parameter and process parameter descriptors according to the chemical formula by using the collected atom parameters and process parameters, and deleting the sample with the defect value in the descriptor generation process;
3) randomly dividing the data set samples obtained in the step 1) into a training set and a testing set;
4) taking the band gap value collected in the step 1) as a target variable, and taking the generated atomic parameter and process parameter in the step 2) as independent variables; carrying out independent variable screening on the training set by utilizing a maximum correlation minimum redundancy algorithm (mRMR) and combining a support vector machine one-out method to select a subset of the modeled optimal independent variables;
5) establishing a prediction model of the double perovskite oxide band gap by using the target variable and the independent variable screened in the step 4) and a support vector machine algorithm through the training set sample obtained in the step 3);
6) forecasting the band gap value of the double perovskite oxide in the test set sample obtained in the step 3) according to the forecasting model of the band gap of the double perovskite oxide established in the step 5).
The stability and reliability level of the data modeling method is preferably judged by the error of the predicted values and the experimental values.
Compared with the prior art, the invention has the following obvious and prominent substantive characteristics and remarkable advantages:
1. the invention overcomes the defects of the traditional test method, avoids the consumption of a large amount of resources and time due to continuous trial and error, and forecasts A through theory and calculation2B′B″O6The band gap of the type double perovskite oxide material; the method of the invention uses a support vector machine method to forecast the band gap, cross-verifies the result, generates descriptors by using collected atomic parameters and process parameters, and introduces the obtained descriptors into a model, so that the calculation result can be obtained in a few seconds, and the method is convenient and fast;
2. the method does not relate to experiments and chemical products in the whole process, does not generate chemical pollution, and accords with the concept of green environmental protection; the preparation method is simple, easy to realize and suitable for popularization and application;
3. the method can prejudge A in advance through model prediction2B′B″O6The band gap of the double perovskite oxide material is selected, samples meeting requirements are selected for experimental verification, the efficiency of finding new materials can be improved, a guiding effect is achieved, and blindness is avoided.
Description of the drawings:
FIG. 1 is a block diagram of the process of the present invention.
FIG. 2 is a graph of the modeling result of the support vector machine regression model of the double perovskite oxide band gap of the present invention.
FIG. 3 is a graph of the left-out cross validation result of the support vector machine regression model of the double perovskite oxide band gap of the present invention.
FIG. 4 is a diagram of the results of an independent test set of a support vector machine regression model for the band gap of a double perovskite oxide of the present invention.
The specific implementation mode is as follows:
the invention is described in detail below with reference to the drawings and preferred embodiments.
The first embodiment is as follows:
referring to fig. 1, a method for rapidly predicting a band gap of a double perovskite oxide based on data mining comprises the following steps:
1) searching A from experimental literature by using computer system2B′B″O6The band gap value and the chemical formula of the perovskite material are used as data set samples;
2) generating corresponding atom parameter and process parameter descriptors according to the chemical formula by using the collected atom parameters and process parameters, and deleting the sample with the defect value in the descriptor generation process;
3) randomly dividing the data set samples obtained in the step 1) into a training set and a testing set;
4) taking the band gap collected in the step 1) as a target variable, and taking the generated atomic parameter and process parameter descriptor in the step 2) as independent variables; performing variable screening on the training set by using a maximum correlation minimum redundancy algorithm (mRMR) in combination with a support vector machine one-out method, and selecting a subset of the modeled optimal independent variables;
5) establishing a prediction model of the double perovskite oxide band gap by using the target variable and the independent variable screened in the step 4) and a support vector machine algorithm through the training set sample obtained in the step 3);
6) forecasting the band gap value of the double perovskite oxide in the test set sample obtained in the step 3) according to the forecasting model of the band gap of the double perovskite oxide established in the step 5).
In the embodiment, the band gap of the double perovskite oxide is rapidly predicted based on data mining, and A is predicted through theory and calculation2B′B″O6The band gap of the double perovskite material is calculated by combining maximum correlation minimum redundancy with support vector machine regression and rapidly obtaining a calculation result through a data mining method, and the method is free of experiment, convenient and rapid, saves manpower and is green and environment-friendly.
Example two:
this embodiment is substantially the same as the first embodiment, and is characterized in that:
the experimental data is combined with a support vector machine to rapidly predict the band gap of the double perovskite oxide, and the method comprises the following steps:
1) search for A from the literature2B′B″O6The band gap value and the chemical formula of the double perovskite oxide are used as data set samples; the chemical formula and the band gap value are shown in table 1, and table 1 is a data sample set of the chemical formula and the band gap value of a part of double perovskite oxide:
TABLE 1 data sample set of partial double perovskite oxide chemical formula and band gap values
2) Generating corresponding atom parameter and process parameter descriptors according to the chemical formula by using the collected atom parameters and process parameters, and deleting samples with complete data, wherein the number of the samples is 77, and the chemical formula and the band gap value of the oxide double perovskite are shown in the table 1) in the step 1) in the descriptor generation process; and generating descriptors by using the collected atomic parameters and process parameters, wherein the descriptors are partially shown in the table 2:
TABLE 2 partial descriptor Table
3) Randomly dividing 77 data set samples obtained in the step 2) into a training set and a testing set in a ratio of 4:1, wherein the sample amount of the training set and the sample amount of the testing set are respectively 62 and 15;
4) taking the band gap collected in the step 1) as a target variable, and taking the generated atomic parameters and process parameters in the step 2) as independent variables; performing argument screening on a training set by using a maximum correlation minimum redundancy algorithm (mRMR) combined with a support vector machine one-out method for verification, selecting 14 optimal arguments as a subset of the modeled optimal arguments, wherein the selected optimal arguments are shown in Table 3; and finally, converting the independent variable data by adopting an equation to obtain 13 independent variables serving as the optimal independent variable subset for modeling, wherein the conversion equation is shown in a table 4. The partial data after conversion are shown in table 5. In the step, the variables with large noise are deleted, the optimal independent variable subset for modeling is selected, and the modeling precision is improved.
TABLE 3. optimal argument partial data selected by maximum correlation minimum redundancy
TABLE 4 data conversion equation
TABLE 5 partial autovariate datasets after dimension reduction by transformation
| P1 | P2 | P3 | P4 | P5 | P6 | P7 |
| 0.505688 | -1.40735 | 1.02343 | 0.407962 | 0.781202 | -0.424024 | 1.36229 |
| 1.10503 | -1.61269 | 1.05117 | 0.678705 | 0.019197 | 0.431063 | 1.6369 |
| -4.31619 | -2.80639 | 0.369882 | -1.21051 | 1.2407 | -0.200206 | -0.621336 |
| -4.69755 | -2.36748 | 0.22418 | -0.429655 | 1.22166 | -0.207919 | -1.07896 |
| 1.32835 | -1.12576 | 2.41792 | 0.833165 | 0.139178 | -1.16972 | 0.237114 |
| P8 | P9 | P10 | P11 | P12 | P13 | |
| 0.052195 | -0.061386 | 0.457171 | 0.017042 | -0.102027 | -0.165318 | |
| 0.325361 | 0.185842 | 0.25291 | 0.046041 | 0.098897 | -0.142413 | |
| -0.215917 | -0.067398 | -0.105985 | 0.115255 | 0.1128302 | 0.019613 | |
| -0.16837 | 0.7291638 | -0.095072 | 0.7204944 | 0.080854 | 0.046822 | |
| -0.61511 | -0.950371 | -0.007992 | 0.50779 | -0.265087 | -0.005111 |
5) Establishing a prediction model of the double perovskite oxide band gap by using the target variable and the independent variable screened in the step 4) and supporting a vector machine regression algorithm through the training set sample obtained in the step 3);
6) forecasting the band gap value of the double perovskite oxide in the test set sample obtained in the step 3) according to the forecasting model of the band gap of the double perovskite oxide established in the step 5).
In the present embodiment, the modeling result of the double perovskite oxide band gap quantitative prediction model established based on the training set in combination with the support vector machine is shown in fig. 2. In this embodiment, a support vector machine regression algorithm is used to model 62 samples of double perovskite oxide, and a quantitative prediction model of the band gap of the double perovskite oxide is established. The Pearson correlation coefficient (R) of the predicted value and the experimental value of the band gap model of the double perovskite oxide is 0.9838, and the root mean square error (RSME) is 0.1850. According to the method, an efficient and rapid forecasting model is established through sample data from experimental literature, and the method has the advantages of simplicity, rapidness, low cost, greenness and environmental friendliness.
In this embodiment, 62 samples in the training set are numbered a1，A2……A62. First step with A1，A2……A61For the training set, the same optimal independent variable subset as in the first embodiment is used, model 1 is established and model 1 is used to predict A62The band gap of (a). The second step is with A1，A2……A60，A62For the training set, the same optimal independent variable subset as in the first embodiment is used, model 2 is established and model 2 is used to predict A61The band gap of (a). By analogy, after 46 models are established, the stability and reliability of the data modeling method are judged through the error of the forecast value and the experimental value.
The leave-one-out internal cross validation result of the double perovskite oxide band gap prediction model established based on 62 double perovskite oxide samples and a support vector machine is shown in fig. 3.
In the method, a leave-one-out internal cross validation is performed on a double-perovskite oxide band gap support vector machine quantitative prediction model established by 62 sample data, the correlation coefficient (R) of the model prediction value and the experimental value of the double-perovskite oxide band gap in the leave-one-out internal cross validation method is 0.9053, and the root mean square error (RSME) is 0.4150. According to the method, the forecasting model of the one-out-of-one-training-set cross validation is established through the experimental sample data in the experimental literature, and the stability and the reliability of the data modeling method can be evaluated.
The method of the embodiment utilizes the established support vector machine regression model of the double perovskite oxide band gap to forecast 15 samples in the independent test set, and a better result is obtained. The Pearson correlation coefficient (R) for the model predicted and experimental values for the band gap of the double perovskite oxide is 0.8751, and the root mean square error (RSME) is 0.4907. The independent test set forecasts, as shown in FIG. 4.
The method of the embodiment overcomes the defects of the traditional test method, avoids the consumption of a large amount of resources and time due to continuous trial and error, and forecasts A through theory and calculation2B′B″O6The band gap of the type double perovskite oxide material; the method of the embodiment uses a support vector machine method to forecast the band gap, cross-verifies the result, generates descriptors by using collected atomic parameters and process parameters, and introduces the obtained descriptors into a model, so that the calculation result can be obtained in a few seconds, and the method is convenient and fast; the method does not relate to experiments and chemical products in the whole process, does not generate chemical pollution, and accords with the concept of green environmental protection; the preparation method is simple, easy to realize and suitable for popularization and application; the method of the embodiment can prejudge A in advance through model prediction2B′B″O6The band gap of the double perovskite oxide material is selected, samples meeting requirements are selected for experimental verification, the efficiency of finding new materials can be improved, a guiding effect is achieved, and blindness is avoided.
In summary, the above embodiments are based on a method for rapidly predicting the band gap of the double perovskite oxide by data mining, and a is searched from the literature by using a computer system2B′B″O6The band gap value and the chemical formula of the perovskite material; generating corresponding descriptors as independent variables according to the chemical formula; randomly dividing a data set into a training set and a testing set; performing variable screening by combining maximum correlation minimum redundancy with a support vector machine leave-one-out method; establishing a prediction model of the double perovskite oxide band gap by using the target variable, the screened independent variable and a support vector machine algorithm through a training set sample; and (4) rapidly forecasting the band gap of the double perovskite oxide in the test set sample according to the established band gap model. The embodiment is based on reliable literature data and a modeling method, and the built prediction model of the double perovskite oxide band gap is simple, convenient and quickQuick, low cost and no pollution.
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 (2)
1. A method for rapidly predicting the band gap of a double perovskite oxide based on data mining is characterized by comprising the following steps:
1) searching A from experimental literature by using computer system2B′B″O6The band gap value and the chemical formula of the perovskite material are used as data set samples;
2) generating corresponding atom parameter and process parameter descriptors according to the chemical formula by using the collected atom parameters and process parameters, and deleting the sample with the defect value in the descriptor generation process;
3) randomly dividing the data set samples obtained in the step 1) into a training set and a testing set;
4) taking the band gap collected in the step 1) as a target variable, and taking the generated atomic parameter and process parameter descriptor in the step 2) as independent variables; performing variable screening on the training set by using a maximum correlation minimum redundancy algorithm (mRMR) in combination with a support vector machine one-out method, and selecting a subset of the modeled optimal independent variables;
5) establishing a prediction model of the double perovskite oxide band gap by using the target variable and the independent variable screened in the step 4) and a support vector machine algorithm through the training set sample obtained in the step 3);
6) forecasting the band gap value of the double perovskite oxide in the test set sample obtained in the step 3) according to the forecasting model of the band gap of the double perovskite oxide established in the step 5).
2. The method for rapidly predicting the band gap of the double perovskite oxide based on data mining according to claim 1, wherein the stability and reliability level of the data modeling method are judged by the error of the predicted value and the experimental value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010869907.7A CN112132185B (en) | 2020-08-26 | 2020-08-26 | Method for rapidly predicting double perovskite oxide band gap based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010869907.7A CN112132185B (en) | 2020-08-26 | 2020-08-26 | Method for rapidly predicting double perovskite oxide band gap based on data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112132185A true CN112132185A (en) | 2020-12-25 |
| CN112132185B CN112132185B (en) | 2023-07-18 |
Family
ID=73847985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010869907.7A Active CN112132185B (en) | 2020-08-26 | 2020-08-26 | Method for rapidly predicting double perovskite oxide band gap based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112132185B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112992290A (en) * | 2021-03-17 | 2021-06-18 | 华北电力大学 | Perovskite band gap prediction method based on machine learning and cluster model |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106055525A (en) * | 2016-06-27 | 2016-10-26 | 中国矿业大学银川学院 | Stepwise regression analysis-based big data processing method |
| CN106503867A (en) * | 2016-11-14 | 2017-03-15 | 吉林大学 | A kind of genetic algorithm least square wind power forecasting method |
| CN108597601A (en) * | 2018-04-20 | 2018-09-28 | 山东师范大学 | Diagnosis of chronic obstructive pulmonary disease auxiliary system based on support vector machines and method |
| CN109473147A (en) * | 2018-10-08 | 2019-03-15 | 上海大学 | A kind of method of quick predict macromolecule forbidden bandwidth |
| CN110516701A (en) * | 2019-07-12 | 2019-11-29 | 上海大学 | Method based on data mining quick predict perovskite Curie temperature |
| CN111091878A (en) * | 2019-11-07 | 2020-05-01 | 上海大学 | Method for rapidly predicting perovskite dielectric constant |
| CN111429980A (en) * | 2020-04-14 | 2020-07-17 | 北京迈高材云科技有限公司 | Automatic acquisition method for material crystal structure characteristics |
-
2020
- 2020-08-26 CN CN202010869907.7A patent/CN112132185B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106055525A (en) * | 2016-06-27 | 2016-10-26 | 中国矿业大学银川学院 | Stepwise regression analysis-based big data processing method |
| CN106503867A (en) * | 2016-11-14 | 2017-03-15 | 吉林大学 | A kind of genetic algorithm least square wind power forecasting method |
| CN108597601A (en) * | 2018-04-20 | 2018-09-28 | 山东师范大学 | Diagnosis of chronic obstructive pulmonary disease auxiliary system based on support vector machines and method |
| CN109473147A (en) * | 2018-10-08 | 2019-03-15 | 上海大学 | A kind of method of quick predict macromolecule forbidden bandwidth |
| CN110516701A (en) * | 2019-07-12 | 2019-11-29 | 上海大学 | Method based on data mining quick predict perovskite Curie temperature |
| CN111091878A (en) * | 2019-11-07 | 2020-05-01 | 上海大学 | Method for rapidly predicting perovskite dielectric constant |
| CN111429980A (en) * | 2020-04-14 | 2020-07-17 | 北京迈高材云科技有限公司 | Automatic acquisition method for material crystal structure characteristics |
Non-Patent Citations (3)
| Title |
|---|
| 冯新泸 等, 《中国石化出版社》 * |
| 冯新泸 等, 《中国石化出版社》, pages: 135 - 138 * |
| 顾天鸿: "ABC_2半导体化合物性能预测和数据挖掘平台开发", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》, 15 July 2015 (2015-07-15), pages 2 - 4 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112992290A (en) * | 2021-03-17 | 2021-06-18 | 华北电力大学 | Perovskite band gap prediction method based on machine learning and cluster model |
| CN112992290B (en) * | 2021-03-17 | 2024-02-23 | 华北电力大学 | Perovskite band gap prediction method based on machine learning and cluster model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112132185B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Simulation and design of energy materials accelerated by machine learning | |
| Wang et al. | Applications of machine learning in perovskite materials | |
| Mossa et al. | Parameter estimation of PEMFC model based on Harris Hawks’ optimization and atom search optimization algorithms | |
| Cao et al. | Complementarity assessment of wind‐solar energy sources in Shandong province based on NASA | |
| Wu et al. | Deep Learning Accelerates the Discovery of Two‐Dimensional Catalysts for Hydrogen Evolution Reaction | |
| Khmaissia et al. | Accelerating band gap prediction for solar materials using feature selection and regression techniques | |
| CN112132177B (en) | Machine learning based fast prediction of ABO 3 On-line forecasting method of perovskite band gap | |
| Mathi et al. | Enhanced leader adaptive velocity particle swarm optimisation based global maximum power point tracking technique for a PV string under partially shaded conditions | |
| Rath et al. | Discovery of direct band gap perovskites for light harvesting by using machine learning | |
| CN112132185A (en) | Method for rapidly predicting band gap of double perovskite oxide based on data mining | |
| Zhang et al. | Accurate and efficient machine learning models for predicting hydrogen evolution reaction catalysts based on structural and electronic feature engineering in alloys | |
| Wang et al. | Graph mixture of experts: Learning on large-scale graphs with explicit diversity modeling | |
| Liu et al. | Auto-MatRegressor: liberating machine learning alchemists | |
| Xu et al. | Machine Learning in Energy Chemistry: Introduction, Challenge and Perspective | |
| Patrick et al. | Interaction distance in the extended XXZ model | |
| Ji et al. | A local environment descriptor for machine-learned density functional theory at the generalized gradient approximation level | |
| Scher et al. | Development of effective stochastic potential method using random matrix theory for efficient conformational sampling of semiconductor nanoparticles at non-zero temperatures | |
| Atilgan et al. | First-principle-based computational doping of SrTiO 3 using combinatorial genetic algorithms | |
| Farh et al. | Global research trends on photovoltaic maximum power extraction: Systematic and scientometric analysis | |
| KR102631134B1 (en) | Method for predicting lithium-ion battery performance, system using the same, and device comprising thereof | |
| How et al. | Dimensionality reduction in machine learning for nonadiabatic molecular dynamics: Effectiveness of elemental sublattices in lead halide perovskites | |
| Chen et al. | Application of machine learning in perovskite materials and devices: A review | |
| Doan et al. | Accelerating the evaluation of crucial descriptors for catalyst screening via message passing neural network | |
| CN113838538A (en) | Prediction method and system for organic-inorganic hybrid perovskite post-treatment amine based on random forest rapid classification | |
| Han et al. | Artificial intelligence guided thermoelectric materials design and discovery |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yang Xue Inventor after: Peng Jubo Inventor after: Lu Wencong Inventor after: Fu Zewei Inventor after: Zhao Hui Inventor after: Liu Long Inventor before: Yang Xue Inventor before: Lu Wencong |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230111 Address after: 200444 No. 99, upper road, Shanghai, Baoshan District Applicant after: Shanghai University Applicant after: R & D Center of Yunnan Tin Industry Group (Holdings) Co.,Ltd. Address before: 200444 No. 99, upper road, Shanghai, Baoshan District Applicant before: Shanghai University |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |