A cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbons
Abstract This study predicts the thermoelectric figure of merit (ZT) for defective gamma-graphyne nanoribbons (γ-GYNRs) using binary coding, convolutional neural networks (CNN), long short-term memory networks (LSTM), and multi-scale feature fusion. The approach accurately predicts ZT values with on...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84074-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544584583184384 |
|---|---|
| author | Jiayi Guo Chunfeng Cui Tao Ouyang Juexian Cao Xiaolin Wei |
| author_facet | Jiayi Guo Chunfeng Cui Tao Ouyang Juexian Cao Xiaolin Wei |
| author_sort | Jiayi Guo |
| collection | DOAJ |
| description | Abstract This study predicts the thermoelectric figure of merit (ZT) for defective gamma-graphyne nanoribbons (γ-GYNRs) using binary coding, convolutional neural networks (CNN), long short-term memory networks (LSTM), and multi-scale feature fusion. The approach accurately predicts ZT values with only 500 initial structures (3% of 16,512 candidates), achieving an R2 above 0.91 and a mean absolute error (MAE) of 0.05 to 0.06. The use of artificial feature extraction combined with an attention mechanism reveals that the number and distribution of defects are crucial for achieving high ZT values. γ-GYNRs with moderate and evenly distributed defect count show superior thermoelectric performance. This demonstrates the effectiveness of neural networks in designing low-dimensional materials like γ-GYNRs and offers insights into exploring other materials with excellent thermoelectric properties. |
| format | Article |
| id | doaj-art-552b09031dee45b9a52b32c51526624f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-552b09031dee45b9a52b32c51526624f2025-01-12T12:23:50ZengNature PortfolioScientific Reports2045-23222025-01-0115111110.1038/s41598-024-84074-zA cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbonsJiayi Guo0Chunfeng Cui1Tao Ouyang2Juexian Cao3Xiaolin Wei4Department of Physics & Hunan Institute of Advanced Sensing and Information Technology, Xiangtan UniversityDepartment of Physics & Hunan Institute of Advanced Sensing and Information Technology, Xiangtan UniversityDepartment of Physics & Hunan Institute of Advanced Sensing and Information Technology, Xiangtan UniversityDepartment of Physics & Hunan Institute of Advanced Sensing and Information Technology, Xiangtan UniversityDepartment of Physics & Hunan Institute of Advanced Sensing and Information Technology, Xiangtan UniversityAbstract This study predicts the thermoelectric figure of merit (ZT) for defective gamma-graphyne nanoribbons (γ-GYNRs) using binary coding, convolutional neural networks (CNN), long short-term memory networks (LSTM), and multi-scale feature fusion. The approach accurately predicts ZT values with only 500 initial structures (3% of 16,512 candidates), achieving an R2 above 0.91 and a mean absolute error (MAE) of 0.05 to 0.06. The use of artificial feature extraction combined with an attention mechanism reveals that the number and distribution of defects are crucial for achieving high ZT values. γ-GYNRs with moderate and evenly distributed defect count show superior thermoelectric performance. This demonstrates the effectiveness of neural networks in designing low-dimensional materials like γ-GYNRs and offers insights into exploring other materials with excellent thermoelectric properties.https://doi.org/10.1038/s41598-024-84074-zThermoelectric figure of meritGraphyne nanoribbonsConvolutional neural networksLong short-term memory networksMulti-scale feature fusionAttention mechanism |
| spellingShingle | Jiayi Guo Chunfeng Cui Tao Ouyang Juexian Cao Xiaolin Wei A cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbons Scientific Reports Thermoelectric figure of merit Graphyne nanoribbons Convolutional neural networks Long short-term memory networks Multi-scale feature fusion Attention mechanism |
| title | A cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbons |
| title_full | A cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbons |
| title_fullStr | A cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbons |
| title_full_unstemmed | A cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbons |
| title_short | A cutting-edge neural network approach for predicting the thermoelectric efficiency of defective gamma-graphyne nanoribbons |
| title_sort | cutting edge neural network approach for predicting the thermoelectric efficiency of defective gamma graphyne nanoribbons |
| topic | Thermoelectric figure of merit Graphyne nanoribbons Convolutional neural networks Long short-term memory networks Multi-scale feature fusion Attention mechanism |
| url | https://doi.org/10.1038/s41598-024-84074-z |
| work_keys_str_mv | AT jiayiguo acuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT chunfengcui acuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT taoouyang acuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT juexiancao acuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT xiaolinwei acuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT jiayiguo cuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT chunfengcui cuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT taoouyang cuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT juexiancao cuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons AT xiaolinwei cuttingedgeneuralnetworkapproachforpredictingthethermoelectricefficiencyofdefectivegammagraphynenanoribbons |