journal article·2023-12

Interpretable machine learning assisted multi-objective optimization design for small molecule hole transport materials

Xian Zhou, Zhichun Zheng, Tian Lu, Pengcheng Xu, Ting Chang, Minjie Li, Wencong Lu

Publisher page

Abstract

Small molecule hole transport materials (SM-HTMs) play an important role in the development of perovskite solar cells (PSCs) due to the simple structure and excellent photoelectric performance. Herein, we established interpretable models for designing materials with high hole mobility ( μ) and absolute hardness ( η). The μ and η models were constructed by Gradient Boosting Regression (GBR) due to the better performances. The coefficient of determination ( R 2) for leave-one-out cross validation (LOOCV) and the test set are 0.86 and 0.86 in μ model, 0.84 and 0.89 in η model, respectively. SHapley Additive exPlanations (SHAP) analysis reveals that higher μ are more likely to be obtained with fewer C–O and N-O pairs at topological distance 9, and molecules with high degree of cyclization and less polar fragments might have higher η. New groups were designed based on the strategies and used to generate 785 virtual samples. Finally, 35 promising candidates ( μ > 10 −1.54 cm 2 V −1 s −1 and η > 2.71 eV) with high synthesizability were screened out using high-throughput screening and pattern recognition. Our work provides an effective way to accelerate the design of prominent SM-HTMs.
Source: expertdata · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Perovskite Materials and Applications · Quantum Dots Synthesis And Properties · Machine Learning in Materials Science

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (45)

Show source-provided references
1. Recent advances in carbon nanotube utilizations in perovskite solar cells10.1002/adfm.202004765 ↗
2. Minimizing non-radiative recombination losses in perovskite solar cells10.1038/s41578-019-0151-y ↗
3. Lead-free perovskite materials for solar cells
4. Lead-free tin perovskite solar cells10.1016/j.joule.2021.03.001 ↗
5. Organometal Halide Perovskites as visible-light sensitizers for photovoltaic cells10.1021/ja809598r ↗
6. Superhalogen passivation for efficient and stable perovskite solar cells10.1002/solr.202200013 ↗
7. Bifunctional green cellulose derivatives employed for high efficiency and stable perovskite solar cells under ambient environment10.1016/j.jallcom.2021.161247 ↗
8. Metal oxide charge transport layers in perovskite solar cells - Optimising low temperature processing and improving the interfaces towards low temperature processed, efficient and stable devices
9. Carbon quantum dot additive engineering for efficient and stable carbon-based perovskite solar cells10.1016/j.jallcom.2020.157784 ↗
10. Facile synthesized fluorine substituted benzothiadiazole based dopant-free hole transport material for high efficiency perovskite solar cell10.1016/j.dyepig.2020.108786 ↗
11. Asymmetrically substituted phthalocyanines as dopant-free hole selective layers for reliability in perovskite solar cells10.1021/acsaem.1c02039 ↗
12. Passivation functionalized phenothiazine-based hole transport material for highly efficient perovskite solar cell with efficiency exceeding 22%10.1016/j.cej.2020.128328 ↗
13. Hole-transport materials for Perovskite solar cells
14. Hole-transport materials for Perovskite solar cells10.1002/anie.201601757 ↗
15. Defect passivation in hybrid perovskite solar cells using quaternary ammonium halide anions and cations10.1038/nenergy.2017.102 ↗
16. Hole-transporting layer based on a conjugated polyelectrolyte with organic cations enables efficient inverted perovskite solar cells10.1016/j.nanoen.2018.12.033 ↗
17. Polymer assisted small molecule hole transport layers toward highly efficient inverted Perovskite solar cells
18. High-efficiency solution-processed perovskite solar cells with millimeter-scale grains10.1126/science.aaa0472 ↗
19. Air-exposure induced dopant redistribution and energy level shifts in spin-coated spiro-MeOTAD films10.1021/cm504022q ↗
20. Recent advances in spiro‐MeOTAD hole transport material and its applications in organic–inorganic halide Perovskite solar cells
21. Low band gap S,N-heteroacene-based oligothiophenes as hole-transporting and light absorbing materials for efficient perovskite-based solar cells10.1039/C4EE01220H ↗
22. Characterization of the interface properties and processes in solid state dye-sensitized solar cells employing a Perylene sensitizer10.1021/jp111466h ↗
23. Design and synthesis of stable triarylamines for hole-transport applications10.1016/S0040-4039(01)00702-X ↗
24. Molecular level understanding of the chalcogen atom effect on chalcogen-based polymers through electrostatic potential, non-covalent interactions, excited state behaviour, and radial distribution function10.1039/D2PY00960A ↗
25. Machine learning and molecular dynamics simulation-assisted evolutionary design and discovery pipeline to screen efficient small molecule acceptors for PTB7-Th-based organic solar cells with over 15% efficiency10.1039/D1TA09762H ↗
26. Accelerated discovery of two-dimensional optoelectronic octahedral oxyhalides via high-throughput ab initio calculations and machine learning10.1021/acs.jpclett.9b02420 ↗
27. Identifying Pb-free perovskites for solar cells by machine learning10.1038/s41524-019-0177-0 ↗
28. Discovery of novel two-dimensional photovoltaic materials accelerated by machine learning10.1021/acs.jpclett.0c00721 ↗
29. Machine learning for organic photovoltaic polymers: a minireview10.1007/s10118-022-2782-5 ↗
30. A time and resource efficient machine learning assisted design of non-fullerene small molecule acceptors for P3HT-based organic solar cells and green solvent selection10.1039/D1TA04742F ↗
31. M.O. Yildirim, E.C. Gok Yildirim, E. Eren, P. Huang, M.P.U. Haris, S. Kazim, J. Vanschoren, A. Uygun Oksuz, S. Ahmad, Automated machine learning approach in material discovery of hole selective layers for Perovskite solar cells, Energy Technol., (2022).10.1002/ente.202200980 ↗
32. Machine-learning guided quantum chemical and molecular dynamics calculations to design novel hole-conducting organic materials10.1021/acs.jpca.0c05769 ↗
33. Design of molecules with low hole and electron reorganization energy using DFT calculations and bayesian optimization10.1021/acs.jpca.2c05229 ↗
34. Small data machine learning in materials science, npj Computational
35. The curse(s) of dimensionality10.1038/s41592-018-0019-x ↗
36. The curse of dimensionality loses its power10.1038/s43588-021-00182-0 ↗
37. From local explanations to global understanding with explainable AI for trees10.1038/s42256-019-0138-9 ↗
38. Evaluating the performance of the K-fold cross-validation approach for model selection in growth mixture modeling10.1080/10705511.2018.1500140 ↗
39. Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions10.1186/1758-2946-1-8 ↗
40. A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness10.1016/j.actamat.2021.117431 ↗
41. Machine learning-assisted design of yttria-stabilized zirconia thermal barrier coatings with high bonding strength10.1021/acsomega.2c01839 ↗
42. How the change of OMe substituent position affects the performance of spiro-OMeTAD in neutral and oxidized forms: theoretical approaches10.1039/C8RA01879K ↗
43. Boron-nitrogen substituted planar cores: designing dopant-free hole-transporting materials for efficient perovskite solar cells10.1039/D1NR00030F ↗
44. Positional effect of the triphenylamine group on the optical and charge-transfer properties of thiophene-based hole-transporting materials10.1002/asia.201901552 ↗
45. A theoretical study of the electronic structure and charge transport properties of thieno[2,3-b]benzothiophene based derivatives10.1039/C5CP07879B ↗