基于深度学习预测有机光伏电池能量转换效率

doi:10.11949/0438-1157.20201880

摘要/Abstract

摘要：

采用一种针对有机化合物提出的类语言分子描述符对哈佛清洁能源项目数据库（CEPDB）中29000个有机太阳能电池供体分子进行描述，分子将基于最近邻子图理论被分解成片段（词），并利用广度优先搜索算法将片段排列成一定的序列（句子），在每个片段的信息被嵌入一个数值向量后，每个分子可表示为一个信息矩阵。在此基础上，通过一个深层神经网络提取嵌入信息，并与对应材料的光电转换效率（PCE）关联，获得了决定系数（R²）为0.97、均方误差（MSE）为0.16的预测结果。与现有方法的比较表明该方法在精度上具有竞争力。在建模过程中引入注意力机制，识别出了几个对PCE值具有决定性意义的分子片段，可为有机光伏材料的逆向设计提供指导信息。

关键词: 有机化合物, 太阳能, 类语言描述符, 深度学习, 预测, 光电转换效率

Abstract:

A language-like descriptor for organic compounds was used to describe 29000 organic solar cell donor molecules collected from the Harvard Clean Energy Project Database (CEPDB). Inspired by the similarity between organic chemistry and natural language, these molecules were decomposed into fragments (words) based on the nearest neighbor subgraph theory, and these fragments were arranged into a certain sequence (sentences) by the breadth first search algorithm. After the information of each fragment was embedded into a numerical vector, each molecule can be represented by an information matrix. This matrix is a descriptor called g-FSI, which can reflect the composition and structure information of molecules. The descriptor was then parsed by a deep neural network to extract the embedded information and correlate to the corresponding PCE. The prediction model has obtained the prediction result in which the determination coefficient (R²) is 0.97 and the mean square error (MSE) is 0.16. Compared with the existing research, this model is competitive in accuracy of prediction. The attention mechanism is introduced in the modeling process, and several molecular fragments that are decisive for the PCE value are identified, which can provide guidance information for the reverse design of organic photovoltaic materials.

Key words: organic compounds, solar energy, language-like descriptor, deep learning, prediction, power conversion efficiency

中图分类号:

于程远, 吴金奎, 周利, 吉旭, 戴一阳, 党亚固. 基于深度学习预测有机光伏电池能量转换效率[J]. 化工学报, 2021, 72(3): 1487-1495.

YU Chengyuan, WU Jinkui, ZHOU Li, JI Xu, DAI Yiyang, DANG Yagu. Prediction of energy conversion efficiency of organic solar cells based on deep learning[J]. CIESC Journal, 2021, 72(3): 1487-1495.

图/表 1

参考文献 44

1	Leijtens T, Eperon G E, Barker A J, et al. Carrier trapping and recombination: the role of defect physics in enhancing the open circuit voltage of metal halide perovskite solar cells[J]. Energy & Environmental Science, 2016, 9(11): 3472-3481.
2	Zheng B, Wang F, Dong S, et al. Supramolecular polymers constructed by crown ether-based molecular recognition[J]. Chemical Society Reviews, 2012, 41(5): 1621-1636.
3	Jošt M, Kegelmann L, Korte L, et al. Monolithic Perovskite Tandem solar cells: a review of the present status and advanced characterization methods toward 30% efficiency[J]. Advanced Energy Materials, 2020, 10(26): 1904102.
4	Kaltenbrunner M, White M S, Glowacki E D, et al. Ultrathin and lightweight organic solar cells with high flexibility[J]. Nature Communications, 2012, 3(1): 770.
5	Fukuda K, Yu K, Someya T. The future of flexible organic solar cells[J]. Advanced Energy Materials, 2020, 10(25): 2000765.
6	Meng L X, Zhang Y M, Wan X J, et al. Organic and solution-processed tandem solar cells with 17.3% efficiency[J]. Science, 2018, 361(6407): 1094-1098.
7	Jinno H, Fukuda K, Xu X M. et al. Stretchable and waterproof elastomer-coated organic photovoltaics for washable electronic textile applications[J]. Nature Energy, 2017, 2(10): 780-785.
8	Hedley G J, Ruseckas A, Samuel I D W. Light harvesting for organic photovoltaics[J]. Chemical Reviews, 2017, 117(2): 796-837.
9	Liu C, Wang K, Gong X, et al. Low bandgap semiconducting polymers for polymeric photovoltaics[J]. Chemical Society Reviews, 2016, 45(17): 4825-4846.
10	Chen C, Zuo Y, Ye W, et al. A critical review of machine learning of energy materials[J]. Advanced Energy Materials, 2020, 10(8): 1903242.
11	Scharber M C, Mühlbacher D, Koppe M, et al. Design rules for donors in bulk-heterojunction solar cells—towards 10% energy-conversion efficiency [J]. Advanced Materials, 2006, 18(6): 789-794.
12	Green M A, Dunlop E D, Hohl-Ebinger J, et al. Solar cell efficiency tables (Version 55)[J]. Progress in Photovoltaics: Research and Applications, 2020, 28(1): 3-15.
13	Gómez-Bombarelli R, Aguilera-Iparraguirre J, Hirzel T D, et al. Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach[J]. Nature Materials, 2016, 15(10): 1120-1127.
14	Kim E, Huang K, Jegelka S, et al. Virtual screening of inorganic materials synthesis parameters with deep learning[J]. npj Computational Materials, 2017, 3(1): 53.
15	Wu S, Kondo Y, Kakimoto M, et al. Machine-learning-assisted discovery of polymers with high thermal conductivity using a molecular design algorithm[J]. npj Computational Materials, 2019, 5(1): 66.
16	Yamada H, Liu C, Wu S, et al. Predicting materials properties with little data using shotgun transfer learning[J]. ACS Central Science, 2019, 5(10): 1717-1730.
17	Hachmann J, Olivares-Amaya R, Atahan-Evrenk S, et al. The Harvard clean energy project: large-scale computational screening and design of organic photovoltaics on the world community grid[J]. The Journal of Physical Chemistry Letters, 2011, 2(17): 2241-2251.
18	Lopez S A, Pyzer-Knapp E O, Simm G N, et al. The Harvard organic photovoltaic dataset[J]. Scientific Data, 2016, 3(1): 160086.
19	Lopez S A, Sanchez-Lengeling B, de Goes Soares J, et al. Design principles and top non-fullerene acceptor candidates for organic photovoltaics[J]. Joule, 2017, 1(4): 857-870.
20	Hachmann J, Olivares-Amaya R, Jinich A, et al. Lead candidates for high-performance organic photovoltaics from high-throughput quantum chemistry – the Harvard clean energy project[J]. Energy & Environmental Science, 2014, 7(2): 698-704.
21	Padula D, Simpson J D, Troisi A. Combining electronic and structural features in machine learning models to predict organic solar cells properties[J]. Materials Horizons, 2019, 6(2): 343-349.
22	Sahu H, Rao W, Troisi A, et al. Toward predicting efficiency of organic solar cells via machine learning and improved descriptors[J]. Advanced Energy Materials, 2018, 8(24): 1801032.1-1801032.9.
23	Sahu H, Yang F, Ye X B, et al. Designing promising molecules for organic solar cells via machine learning assisted virtual screening[J]. Journal of Materials Chemistry A, 2019, 7(29): 17480-17488.
24	Sun W B, Li M, Li Y, et al. Material evaluation: the use of deep learning to fast evaluate organic photovoltaic materials[J]. Advanced Theory & Simulations, 2019, 2(1): 1970001.
25	Paul A, Jha D, Al-Bahrani R, et al. Transfer learning using ensemble neural networks for organic solar cell screening[C]//2019 International Joint Conference on Neural Networks. Budapest, Hungary, 2019.
26	Cadeddu A, Wylie E K, Jurczak J, et al. Organic chemistry as a language and the implications of chemical linguistics for structural and retrosynthetic analyses[J]. Angewandte Chemie International Edition, 2014, 53(31): 8108-8112.
27	Wu J K, Wang S H, Zhou L, et al. Deep-learning architecture in QSPR modeling for the prediction of energy conversion efficiency of solar cells[J]. Industrial & Engineering Chemistry Research, 2020, 59 (42): 18991-19000.
28	RDKit: Open-Source Cheminformatics Software[CP/OL]. [2020-10-26]. .
29	Hagberg A A, Schult D A, Swart P J. Exploring network structure, dynamics, and function using networkx[C]//Varoquaux G, Vaught T, Millman J. Proceedings of the 7th Python in Science Conference. Pasadena, CA, USA, 2008: 11-15.
30	Costa F, de Grave K D. Fast neighborhood subgraph pairwise distance kernel[C]//Fürnkranz J, Joachims T. Proceedings of the 27th International Conference on International Conference on Machine Learning. Madison, WI, USA: Omnipress, 2010: 255-262.
31	Zhao Y, Hayashida M, Jindalertudomdee J, et al. Breadth-first search approach to enumeration of tree-like chemical compounds[J]. Journal of Bioinformatics & Computational Biology, 2013, 11(6): 1343007.
32	Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[C]//Bengio Y, LeCun Y. 3rd International Conference on Learning Representations. San Diego, CA, USA, 2015.
33	Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
34	Schuster M, Paliwal K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11): 2673-2681.
35	Graves A, Liwicki M, Fernández S, et al. A novel connectionist system for unconstrained handwriting recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2009, 31(5): 855-868.
36	Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[C]//Ghahramani Z, Welling M, Cortes C, et al. Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. Cambridge, MA, USA: MIT Press, 2014: 3104-3112.
37	Wang C, Yang H J, Bartz C, et al. Image captioning with deep bidirectional LSTMs[C]//Proceedings of the 24th ACM International Conference on Multimedia. New York, NY, USA: Association for Computing Machinery, 2016: 988-997.
38	Zhou P, Shi W, Tian J, et al. Attention-based bidirectional long short-term memory networks for relation classification[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Berlin, Germany: Association for Computational Linguistics, 2016: 207-212.
39	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Luxburg U V, Guyon I. Proceedings of the 31st International Conference on Neural Information Processing Systems. Long. Red Hook, NY, USA: Curran Associates Inc., 2017: 6000-6010.
40	Paszke A, Gross S, Massa F. PyTorch: an imperative style, high-performance deep learning library[C]//33rd Conference on Neural Information Processing Systems. Vancouver, Canada, 2019.
41	Kingma D, Ba J. Adam: a method for stochastic optimization[C]//Bengio Y, LeCun Y. 3rd International Conference on Learning Representations. San Diego, CA, USA, 2015.
42	Rogers D, Hahn M. Extended-connectivity fingerprints[J]. Journal of Chemical Information & Modeling, 2010, 50(5): 742-754.
43	Jaeger S, Fulle S, Turk S. Mol2vec: unsupervised machine learning approach with chemical intuition[J]. Journal of Chemical Information & Modeling, 2018, 58(1): 27-35.
44	Lipton Z C. The mythos of model interpretability[J]. Communications of the ACM, 2018, 61(10): 36-43.

[1]	叶展羽, 山訸, 徐震原. 用于太阳能蒸发的折纸式蒸发器性能仿真[J]. 化工学报, 2023, 74(S1): 132-140.
[2]	温凯杰, 郭力, 夏诏杰, 陈建华. 一种耦合CFD与深度学习的气固快速模拟方法[J]. 化工学报, 2023, 74(9): 3775-3785.
[3]	齐聪, 丁子, 余杰, 汤茂清, 梁林. 基于选择吸收纳米薄膜的太阳能温差发电特性研究[J]. 化工学报, 2023, 74(9): 3921-3930.
[4]	傅予, 刘兴翀, 王瀚雨, 李海敏, 倪亚飞, 邹文静, 雷月, 彭永姗. F₃EACl修饰层对钙钛矿太阳能电池性能提升的研究[J]. 化工学报, 2023, 74(8): 3554-3563.
[5]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[6]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[7]	郭雨莹, 敬加强, 黄婉妮, 张平, 孙杰, 朱宇, 冯君炫, 陆洪江. 稠油管道水润滑减阻及压降预测模型修正[J]. 化工学报, 2023, 74(7): 2898-2907.
[8]	李艳辉, 丁邵明, 白周央, 张一楠, 于智红, 邢利梅, 高鹏飞, 王永贞. 非常规服役超临界锅炉的微纳尺度腐蚀动力学模型建立及应用[J]. 化工学报, 2023, 74(6): 2436-2446.
[9]	于源, 陈薇薇, 付俊杰, 刘家祥, 焦志伟. 几何相似涡流空气分级机环形区流场变化规律研究及预测[J]. 化工学报, 2023, 74(6): 2363-2373.
[10]	朱理想, 罗默也, 张晓东, 龙涛, 余冉. 醌指纹法指示三氯乙烯污染土功能微生物活性应用研究[J]. 化工学报, 2023, 74(6): 2647-2654.
[11]	张生安, 刘桂莲. 高效太阳能电解水制氢系统及其性能的多目标优化[J]. 化工学报, 2023, 74(3): 1260-1274.
[12]	黄玉龙, 吕凡, 仇俊杰, 章骅, 何品晶. 易腐垃圾厌氧消化沼液理化性质及VOCs分子特征[J]. 化工学报, 2023, 74(3): 1275-1285.
[13]	张中秋, 李宏光, 石逸林. 基于人工预测调控策略的复杂化工过程多任务学习方法[J]. 化工学报, 2023, 74(3): 1195-1204.
[14]	吴心远, 刘奇磊, 曹博渊, 张磊, 都健. Group2vec：基于无监督机器学习的基团向量表示及其物性预测应用[J]. 化工学报, 2023, 74(3): 1187-1194.
[15]	陈家辉, 杨鑫泽, 陈顾中, 宋震, 漆志文. 以离子液体密度为例的分子性质预测模型建模方法探讨[J]. 化工学报, 2023, 74(2): 630-641.