Guo Jiayi, Cui Chunfeng, Ouyang Tao, Cao Juexian, Wei Xiaolin
Department of Physics & Hunan Institute of Advanced Sensing and Information Technology, Xiangtan University, Xiangtan, 411105, People's Republic of China.
College of Physics and Electronics Engineering, Hengyang Normal University, Hengyang, 421002, People's Republic of China.
Sci Rep. 2025 Jan 7;15(1):1182. doi: 10.1038/s41598-024-84074-z.
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 R 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.
本研究利用二进制编码、卷积神经网络（CNN）、长短期记忆网络（LSTM）和多尺度特征融合来预测有缺陷的γ-石墨炔纳米带（γ-GYNRs）的热电优值（ZT）。该方法仅用500个初始结构（占16512个候选结构的3%）就能准确预测ZT值，相关系数R大于0.91，平均绝对误差（MAE）为0.05至0.06。结合注意力机制使用人工特征提取表明，缺陷的数量和分布对于实现高ZT值至关重要。具有适度且均匀分布的缺陷数量的γ-GYNRs表现出卓越的热电性能。这证明了神经网络在设计如γ-GYNRs这样的低维材料方面的有效性，并为探索其他具有优异热电性能的材料提供了见解。
