CN112992290A - Perovskite band gap prediction method based on machine learning and cluster model - Google Patents
Perovskite band gap prediction method based on machine learning and cluster model Download PDFInfo
- Publication number
- CN112992290A CN112992290A CN202110285597.9A CN202110285597A CN112992290A CN 112992290 A CN112992290 A CN 112992290A CN 202110285597 A CN202110285597 A CN 202110285597A CN 112992290 A CN112992290 A CN 112992290A
- Authority
- CN
- China
- Prior art keywords
- machine learning
- model
- perovskite
- cluster
- band gap
- 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 73
- 238000004138 cluster model Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 10
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 239000000463 material Substances 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004057 DFT-B3LYP calculation Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 238000005421 electrostatic potential Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 150000002892 organic cations Chemical group 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000003786 synthesis reaction Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 239000012761 high-performance material Substances 0.000 description 1
- 150000002500 ions Chemical class 0.000 description 1
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
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a perovskite band gap prediction method based on machine learning and a cluster model, which comprises the following steps of: s1, determining a perovskite cluster model and optimizing the structure of the cluster model; s2, selecting a series of intrinsic structure parameters of the cluster model to construct a database of a certain number of models as a training database for machine learning according to the optimization result of the cluster model structure; s3, screening the constructed database by using the autocorrelation heat map and the xgboost self-contained feature importance ranking to obtain a final machine learning training database; and S4, training the machine learning model by using the obtained machine learning training database and predicting the band gap. The perovskite band gap prediction method based on machine learning and cluster models has the characteristics of high calculation speed, high precision and convenience in electronic structure analysis.
Description
Technical Field
The invention relates to the technical field of perovskite solar cell materials, in particular to a perovskite band gap prediction method based on machine learning and a cluster model.
Background
With the gradual depletion of traditional fossil energy, renewable energy represented by solar perovskite cells is widely concerned, the band gap between a conduction band and a valence band of a material determines the difficulty of photon excitation of photo-generated electron and hole pairs and is a main parameter influencing the photoelectric conversion rate of the solar perovskite cells, and the performance of the solar perovskite cells can be predicted and potential perovskite materials can be optimized by calculating the band gap widths of different perovskite models, so that the experimental synthesis of high-performance materials is guided.
Currently known theoretical models for predicting the band gap width of perovskite are all based on bulk phase models, which can well show the crystal structure of perovskite, but due to the influence of lattice parameters, crystal forms, point groups and the like, the construction of the bulk phase model is very complex, the constructed bulk phase model contains a large number of atoms, the calculation cost is high, and the calculation with high flux is not facilitated; and the perovskite battery with high photoelectric conversion rate is prepared by screening through an experimental method, so that the problem of long period exists. Based on the above problems, it is desirable to provide a new perovskite bandgap prediction method based on machine learning and cluster model.
Disclosure of Invention
The invention aims to provide a perovskite band gap prediction method based on machine learning and a cluster model, which trains the machine learning model and completes band gap prediction by establishing the perovskite cluster model and has the characteristics of high calculation speed, high precision and convenient electronic structure analysis.
In order to achieve the purpose, the invention provides the following scheme:
a perovskite band gap prediction method based on machine learning and cluster models comprises the following steps:
s1, determining a perovskite cluster model and optimizing the structure of the cluster model;
s2, selecting a series of intrinsic structure parameters of the cluster model to construct a database of a set number of models as a training database for machine learning according to the optimization result of the cluster model structure;
and S3, screening the constructed database by using the autocorrelation heat map and the xgboost self-carried feature importance ranking to obtain a final machine learning training database.
And S4, training the machine learning model by using the obtained machine learning training database and predicting the band gap.
Optionally, the determining a cluster model and optimizing the structure of the cluster model in step S1 specifically include:
s101, introducing a bulk phase perovskite model through a Materials project database, intercepting key groups meeting chemical proportion from a bulk phase material, and constructing a cluster model;
s102, performing structure optimization on the initial configuration by using Gaussian 09 software, wherein the adopted functional is B3LYP, the basis group is def2svp, and D-3 dispersion correction is added;
and S103, verifying the valence state of the organic cation position of the perovskite cluster model, so that the sum of net charges of all atoms of the A position group is close to + 1.
Optionally, the intrinsic structure parameters in step S2 include: molecular volume, binding energy, ionization energy, minimum bond length, band gap value, dipole moment, ionic charge, molecular surface electrostatic potential, and ionization energy.
Optionally, the specific number of the set number of models in the step S2 is 700.
Optionally, in the step S3, screening the constructed database by using the autocorrelation heat map and the xgboost-carried feature importance ranking to obtain a final machine learning training database, which specifically includes:
s301, calculating Pearson correlation coefficients among the features;
s302, sorting the features by using the self feature importance sorting of the xgboost algorithm;
and S303, finding out a pair of features with the Pearson correlation coefficient absolute value of more than 0.8 among the features, and sorting and removing the features at the bottom of the sorting according to the feature importance.
Optionally, the number of models in the final machine learning training database in step S3 is 9.
Optionally, the training of the machine learning model and the prediction of the band gap by using the obtained machine learning training database in step S4 specifically include:
s401, splitting the obtained machine learning training database according to 70% of a training set and 30% of a testing set, establishing an initial model by using an xgboost machine learning model, and performing parameter adjustment by using a genetic algorithm to enable r of the model2The value reaches 0.959, the MSE value reaches 0.098;
s402, predicting the band gap value of the bulk model from the band gap value of the cluster model according to the established machine learning model, and for band gap prediction, obtaining the band gap value of the bulk model according to rules obtained by the machine learning model after a series of characteristic quantity calculation results are obtained by utilizing the cluster model outside the training set, so that the perovskite band gap prediction is realized.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: according to the perovskite band gap prediction method based on machine learning and cluster models, the simple cluster models are constructed, on the basis of ensuring that the physical meanings of the models are clear, the time consumption and the calculation cost of high-throughput calculation are greatly reduced, richer machine learning independent variables are obtained, and the credibility of machine learning results is improved; the perovskite band gap prediction method based on machine learning and cluster model is suitable for screening perovskite solar cell materials with high photoelectric conversion rate through high-throughput calculation, can rapidly guide experimental synthesis of related materials, and has the characteristics of high calculation speed, high precision and convenience in electronic structure analysis.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a perovskite band gap prediction method based on machine learning and cluster models according to the present invention;
FIG. 2 is a characteristic autocorrelation heat map of the perovskite band gap prediction method based on machine learning and cluster models;
FIG. 3 is a feature importance ranking diagram of the perovskite band gap prediction method based on machine learning and cluster models according to the present invention;
FIG. 4 is a model training fitting graph of the perovskite band gap prediction method based on machine learning and cluster models according to the present invention;
fig. 5 is a cluster structure diagram of the perovskite band gap prediction method based on machine learning and cluster models.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a perovskite band gap prediction method based on machine learning and a cluster model, which trains the machine learning model and completes band gap prediction by establishing the perovskite cluster model and has the characteristics of high calculation speed, high precision and convenient electronic structure analysis.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The perovskite band gap prediction method based on machine learning and cluster model provided by the invention is shown in figure 1, and comprises the following specific steps:
s1, determining a perovskite cluster model and optimizing the structure of the cluster model, wherein the perovskite cluster optimization method based on machine learning and the cluster model provided by the invention is shown in FIG. 5 and comprises the following specific steps:
s101, introducing a bulk phase perovskite model through a Materials project database, intercepting key groups meeting chemical proportion from a bulk phase material, and constructing a cluster model;
s102, performing structure optimization on the initial configuration by using Gaussian 09 software, wherein the adopted functional is B3LYP, the basis group is def2svp, and D-3 dispersion correction is added;
s103, verifying the valence state of the organic cation position of the perovskite cluster model, so that the sum of net charges of all atoms of the A-position group is close to +1, and ensuring that the model has definite physical significance; the building of the cluster models provides a database required by training for the building of a subsequent machine learning database;
s2, selecting intrinsic structure parameters of a series of cluster models according to the optimization result of the cluster model structure, including: the method comprises the following steps of constructing a database of about 700 models as a training database for machine learning from relevant data of more than ten characteristic quantities, such as molecular volume, binding energy, ionization energy, minimum bond length, band gap value, dipole moment, ion charge, molecular surface electrostatic potential, ionization energy and the like;
s3, screening the constructed database by using the autocorrelation heat map and the xgboost self-contained feature importance sequence to obtain a final machine learning training database, wherein the number of models of the final machine learning training database is 9; the perovskite database feature screening method based on machine learning and cluster model provided by the invention is shown in fig. 2 and 3, and comprises the following specific steps:
s301, calculating Pearson correlation coefficients among the features;
s302, sorting the features by using the self feature importance sorting of the xgboost algorithm;
s303, finding out a pair of features with the absolute value of the Pearson correlation coefficient between the features being more than 0.8, sorting according to the importance of the features, eliminating the features of the features at the bottom of the sorting, and finally selecting 9 features;
s4, training a machine learning model by using the obtained machine learning training database and predicting the band gap, wherein the perovskite data fitting method based on the machine learning and cluster model provided by the invention is shown in FIG. 4 and comprises the following specific steps:
s401, splitting the obtained machine learning training database according to 70% of a training set and 30% of a testing set, establishing an initial model by using an xgboost machine learning model, and carrying out parameter adjustment by using a genetic algorithm, wherein for learning rate (learning _ rate), the number (n _ estimators) of weak classifiers, proportion (sampling _ byte) of random sampling characteristics when a tree is generated each time, regularization parameter L1(alpha), regularization parameter L2(lambda), penalty term (gamma) of complexity, proportion (sampling _ byte) of random sampling characteristics when a tree is generated each time, proportion (sampling _ byte) of random sampling characteristics when a layer of the tree is generated each time, carrying out parameter adjustment by using a differential evolution algorithm, and carrying out parameter adjustment on a correlation coefficient r by using a differential algorithm2As an optimization target, the cross-validation is carried out by using ten-fold cross validation, so that r of the model is2The value reaches 0.959, the MSE value reaches 0.098, which shows that the machine learning model has high rationality, namely, the intrinsic variable of the cluster model and the band gap value of the bulk model have good relation, so that the prediction from the band gap value of the cluster model to the band gap value of the bulk model can be carried out;
s402, predicting the band gap value of the bulk model from the band gap value of the cluster model according to the established machine learning model, and for band gap prediction, obtaining the band gap value of the bulk model according to rules obtained by the machine learning model after a series of characteristic quantity calculation results are obtained by utilizing the cluster model outside the training set, so that the perovskite band gap prediction is realized.
According to the perovskite band gap prediction method based on machine learning and cluster models, the simple cluster models are constructed, on the basis of ensuring that the physical meanings of the models are clear, the time consumption and the calculation cost of high-throughput calculation are greatly reduced, richer machine learning independent variables are obtained, and the credibility of machine learning results is improved; the perovskite band gap prediction method based on machine learning and cluster model is suitable for screening perovskite solar cell materials with high photoelectric conversion rate through high-throughput calculation, can rapidly guide experimental synthesis of related materials, and has the characteristics of high calculation speed, high precision and convenience in electronic structure analysis.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (7)
1. A perovskite band gap prediction method based on machine learning and cluster models is characterized by comprising the following steps:
s1, determining a perovskite cluster model and optimizing the structure of the cluster model;
s2, selecting a series of intrinsic structure parameters of the cluster model to construct a database of a set number of models as a training database for machine learning according to the optimization result of the cluster model structure;
and S3, screening the constructed database by using the autocorrelation heat map and the xgboost self-carried feature importance ranking to obtain a final machine learning training database.
And S4, training the machine learning model by using the obtained machine learning training database and predicting the band gap.
2. The perovskite bandgap prediction method based on machine learning and cluster model according to claim 1, wherein the determining a cluster model and optimizing the structure of the cluster model in step S1 specifically includes:
s101, introducing a bulk phase perovskite model through a Materials project database, intercepting key groups meeting chemical proportion from a bulk phase material, and constructing a cluster model;
s102, performing structure optimization on the initial configuration by using Gaussian 09 software, wherein the adopted functional is B3LYP, the basis group is def2svp, and D-3 dispersion correction is added;
and S103, verifying the valence state of the organic cation position of the perovskite cluster model, so that the sum of net charges of all atoms of the A position group is close to + 1.
3. The machine learning and cluster model based perovskite bandgap prediction method according to claim 1, wherein the intrinsic structure parameters in step S2 comprise: molecular volume, binding energy, ionization energy, minimum bond length, band gap value, dipole moment, ionic charge, molecular surface electrostatic potential, and ionization energy.
4. The method according to claim 1, wherein the specific number of models in the step S2 is 700.
5. The perovskite bandgap prediction method based on machine learning and cluster model according to claim 1, wherein the screening of the constructed database by using the autocorrelation heat map and the xgboost self-carried feature importance ranking in step S3 to obtain the final machine learning training database specifically comprises:
s301, calculating Pearson correlation coefficients among the features;
s302, sorting the features by using the self feature importance sorting of the xgboost algorithm;
and S303, finding out a pair of features with the Pearson correlation coefficient absolute value of more than 0.8 among the features, and sorting and removing the features at the bottom of the sorting according to the feature importance.
6. The machine-learning and cluster-model-based perovskite bandgap prediction method of claim 5, wherein the number of models in the final machine-learning training database in step S3 is 9.
7. The perovskite bandgap prediction method based on machine learning and cluster model according to claim 1, wherein the training of the machine learning model and the prediction of the bandgap in step S4 with the obtained machine learning training database specifically comprises:
s401, splitting the obtained machine learning training database according to 70% of a training set and 30% of a testing set, establishing an initial model by using an xgboost machine learning model, and performing parameter adjustment by using a genetic algorithm to enable r of the model2The value reaches 0.959, the MSE value reaches 0.098;
s402, predicting the band gap value of the bulk model from the band gap value of the cluster model according to the established machine learning model, and for band gap prediction, obtaining the band gap value of the bulk model according to rules obtained by the machine learning model after a series of characteristic quantity calculation results are obtained by utilizing the cluster model outside the training set, so that the perovskite band gap prediction is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110285597.9A CN112992290B (en) | 2021-03-17 | 2021-03-17 | Perovskite band gap prediction method based on machine learning and cluster model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110285597.9A CN112992290B (en) | 2021-03-17 | 2021-03-17 | Perovskite band gap prediction method based on machine learning and cluster model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112992290A true CN112992290A (en) | 2021-06-18 |
CN112992290B CN112992290B (en) | 2024-02-23 |
Family
ID=76334112
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110285597.9A Active CN112992290B (en) | 2021-03-17 | 2021-03-17 | Perovskite band gap prediction method based on machine learning and cluster model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112992290B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113326664A (en) * | 2021-06-28 | 2021-08-31 | 南京玻璃纤维研究设计院有限公司 | Method for predicting dielectric constant of glass based on M5P algorithm |
CN115547425A (en) * | 2022-11-25 | 2022-12-30 | 安徽大学 | Method for predicting perovskite lattice constant based on atomic scale feature descriptor |
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 |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0644210A (en) * | 1992-07-23 | 1994-02-18 | Sony Corp | Method for finding band gap of crystal |
CN104330371A (en) * | 2014-11-04 | 2015-02-04 | 中国石油大学(华东) | Method for quantitative analysis of photocatalytic performance of silver bromide cluster |
CN105070836A (en) * | 2015-08-03 | 2015-11-18 | 华北电力大学 | Mesoporous perovskite solar cell and preparation method thereof |
CN110610746A (en) * | 2019-08-29 | 2019-12-24 | 浙江工业大学 | Method for researching structure of supported single-layer hydrotalcite |
US20200294630A1 (en) * | 2019-03-12 | 2020-09-17 | California Institute Of Technology | Systems and Methods for Determining Molecular Structures with Molecular-Orbital-Based Features |
CN112071370A (en) * | 2020-07-15 | 2020-12-11 | 北京化工大学 | Optimization method of metal nanocluster structure |
CN112132177A (en) * | 2020-08-14 | 2020-12-25 | 上海大学 | ABO rapid prediction based on machine learning3Perovskite band gap online forecasting method |
CN112132185A (en) * | 2020-08-26 | 2020-12-25 | 上海大学 | Method for rapidly predicting band gap of double perovskite oxide based on data mining |
CN112132183A (en) * | 2020-08-20 | 2020-12-25 | 上海大学 | Method for rapidly predicting specific surface area of perovskite material based on XGboost algorithm |
CN112216355A (en) * | 2020-10-22 | 2021-01-12 | 哈尔滨理工大学 | Multi-component crystal configuration energy prediction method based on machine learning |
-
2021
- 2021-03-17 CN CN202110285597.9A patent/CN112992290B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0644210A (en) * | 1992-07-23 | 1994-02-18 | Sony Corp | Method for finding band gap of crystal |
CN104330371A (en) * | 2014-11-04 | 2015-02-04 | 中国石油大学(华东) | Method for quantitative analysis of photocatalytic performance of silver bromide cluster |
CN105070836A (en) * | 2015-08-03 | 2015-11-18 | 华北电力大学 | Mesoporous perovskite solar cell and preparation method thereof |
US20200294630A1 (en) * | 2019-03-12 | 2020-09-17 | California Institute Of Technology | Systems and Methods for Determining Molecular Structures with Molecular-Orbital-Based Features |
CN110610746A (en) * | 2019-08-29 | 2019-12-24 | 浙江工业大学 | Method for researching structure of supported single-layer hydrotalcite |
CN112071370A (en) * | 2020-07-15 | 2020-12-11 | 北京化工大学 | Optimization method of metal nanocluster structure |
CN112132177A (en) * | 2020-08-14 | 2020-12-25 | 上海大学 | ABO rapid prediction based on machine learning3Perovskite band gap online forecasting method |
CN112132183A (en) * | 2020-08-20 | 2020-12-25 | 上海大学 | Method for rapidly predicting specific surface area of perovskite material based on XGboost algorithm |
CN112132185A (en) * | 2020-08-26 | 2020-12-25 | 上海大学 | Method for rapidly predicting band gap of double perovskite oxide based on data mining |
CN112216355A (en) * | 2020-10-22 | 2021-01-12 | 哈尔滨理工大学 | Multi-component crystal configuration energy prediction method based on machine learning |
Non-Patent Citations (2)
Title |
---|
DITTMER, A ET.AL: "Accurate Band Gap Predictions of Semiconductors in the Framework of the Similarity Transformed Equation of Motion Coupled Cluster Theory", 《INORGANIC CHEMISTRY 》, 16 August 2019 (2019-08-16) * |
郑伟达;张惠然;胡红青;刘尧;李盛洲;丁广太;张金仓;: "基于不同机器学习算法的钙钛矿材料性能预测", 中国有色金属学报, no. 04 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113326664A (en) * | 2021-06-28 | 2021-08-31 | 南京玻璃纤维研究设计院有限公司 | Method for predicting dielectric constant of glass based on M5P algorithm |
CN115547425A (en) * | 2022-11-25 | 2022-12-30 | 安徽大学 | Method for predicting perovskite lattice constant based on atomic scale feature descriptor |
CN115547425B (en) * | 2022-11-25 | 2023-04-07 | 安徽大学 | Method for predicting perovskite lattice constant based on atomic scale feature descriptor |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN112992290B (en) | 2024-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112992290A (en) | Perovskite band gap prediction method based on machine learning and cluster model | |
CN109902863B (en) | Wind speed prediction method and device based on multi-factor time-space correlation | |
CN111008728B (en) | Prediction method for short-term output of distributed photovoltaic power generation system | |
CN110110912B (en) | Photovoltaic power multi-model interval prediction method | |
Monfared et al. | Fuzzy predictor with additive learning for very short-term PV power generation | |
CN108183488B (en) | High-permeability distributed energy system intelligent pressure regulating method based on cluster division | |
CN116721537A (en) | Urban short-time traffic flow prediction method based on GCN-IPSO-LSTM combination model | |
CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
CN110956312A (en) | Photovoltaic power distribution network voltage prediction method based on EMD-CNN deep neural network | |
CN106951995A (en) | A kind of EHV transmission electric field extreme learning machine predicts multiple-objection optimization screen method | |
CN112541613B (en) | Multi-layer ConvLSTM sea surface temperature prediction calculation method based on remote sensing data | |
Wang et al. | Short-term load forecasting of power system based on time convolutional network | |
Zhu et al. | Forecasting air quality in China using novel self-adaptive seasonal grey forecasting models | |
CN116845868A (en) | Distributed photovoltaic power prediction method and device, electronic equipment and storage medium | |
Suresh et al. | Probabilistic LSTM-Autoencoder based hour-ahead solar power forecasting model for intra-day electricity market participation: A Polish case study | |
Khademi et al. | Power Prediction and Technoeconomic Analysis of a Solar PV Power Plant by MLP‐ABC and COMFAR III, considering Cloudy Weather Conditions | |
CN117113054A (en) | Multi-element time sequence prediction method based on graph neural network and transducer | |
CN117273200A (en) | Runoff interval forecasting method based on convolution optimization algorithm and Pyraformer neural network | |
Sun et al. | Short-term photovoltaic power prediction modeling based on AdaBoost algorithm and Elman | |
CN109447843A (en) | A kind of photovoltaic power generation output forecasting method and device | |
Roy et al. | Day-ahead Solar Power Generation Forecasting using LSTM and Random Forest Methods for North Eastern Region of India | |
Omar et al. | LSTM and RBFNN based univariate and multivariate forecasting of day-ahead solar irradiance for Atlantic region in Canada and Mediterranean region in Libya | |
CN114021847A (en) | Short-term power load prediction method and system based on ISGU (inverse transformation and aggregation) hybrid model | |
CN114169758A (en) | Air quality data determination method and device, readable storage medium and electronic equipment | |
Pham et al. | LS-SPP: A LSTM-Based Solar Power Prediction Method from Weather Forecast Information |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |