journal article·2020-01

Robust random forest based non-fullerene organic solar cells efficiency prediction

Min-Hsuan Lee

Publisher page

Abstract

Abstract Non-fullerene materials have attracted attention as high-performance molecular acceptors in organic solar cells (OSCs). A proper understanding of the energy level alignment between donors and non-fullerene acceptors is crucial for photoactive materials selection in designing high-performance non-fullerene OSCs. However, the quantitative assessment for the proper selection of donors and non-fullerene acceptors is still rarely studied, which is seen as time-consuming and complicated tasks. In this study, the optimized Random Forest model based on the electronic descriptors (e.g., highest occupied molecular orbitals levels, lowest unoccupied molecular orbitals levels, and band gap) provides the high predictive power, reaching the coefficient of determination (R2) of 0.85 and 0.80 for the training set and testing set, respectively. The use of machine learning approach benefits the development of non-fullerene OSCs in two ways: (1) it helps to extract complex correlation between various descriptors and device performance, and (2) it indicates that the band gap of acceptors is the more critical feature for improving the efficiency of non-fullerene OSCs. The machine-learning model for predicting the efficiency of non-fullerene OSCs (macroscopic performance) from frontier molecular orbital energy levels of the organic materials (microscopic properties) is developed, as an important guide to design the heterojunction blends and accelerate the research for non-fullerene OSCs.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Organic Electronics and Photovoltaics · Conducting polymers and applications · Machine Learning in Materials Science

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

References (51)

Show source-provided references
1. Single-junction organic solar cell with over 15% efficiency using fused-ring acceptor with electron-deficient core10.1016/j.joule.2019.01.004 ↗
2. Achieving over 15% efficiency in organic photovoltaic cells via copolymer design10.1002/adma.201808356 ↗
3. Over 12% efficiency nonfullerene all-small-molecule organic solar cells with sequentially evolved multilength scale morphologies10.1002/adma.201807842 ↗
4. High-efficiency small-molecule ternary solar cells with a hierarchical morphology enabled by synergizing fullerene and non-fullerene acceptors10.1038/s41560-018-0234-9 ↗
5. Fine-tuning of the chemical structure of photoactive materials for highly efficient organic photovoltaics10.1038/s41560-018-0263-4 ↗
6. Fast charge separation in a non-fullerene organic solar cell with a small driving force10.1038/nenergy.2016.89 ↗
7. 11.4% Efficiency non-fullerene polymer solar cells with trialkylsilyl substituted 2D-conjugated polymer as donor10.1038/ncomms13651 ↗
8. Critical review of the molecular design progress in non-fullerene electron acceptors towards commercially viable organic solar cells10.1039/C7CS00892A ↗
9. Materials interface engineering for solution-processed photovoltaics10.1038/nature11476 ↗
10. Nonfullerene acceptor molecules for bulk heterojunction organic solar cells10.1021/acs.chemrev.7b00535 ↗
11. Molecular design of photovoltaic materials for polymer solar cells: toward suitable electronic energy levels and broad absorption10.1021/ar2002446 ↗
12. Next-generation organic photovoltaics based on non-fullerene acceptors10.1038/s41566-018-0104-9 ↗
13. What makes fullerene acceptors special as electron acceptors in organic solar cells and how to replace them10.1002/adma.201203486 ↗
14. Trends in the electronic and geometric structure of non-fullerene based acceptors for organic solar cells10.1039/C6EE03654F ↗
15. Quantitative relations between interaction parameter, miscibility and function in organic solar cells10.1038/s41563-017-0005-1 ↗
16. Enabling low voltage losses and high photocurrent in fullerene-free organic photovoltaics10.1038/s41467-019-08386-9 ↗
17. Computer-aided screening of conjugated polymers for organic solar cell: classification by random forest10.1021/acs.jpclett.8b00635 ↗
18. Design principles and top non-fullerene acceptor candidates for organic photovoltaics10.1016/j.joule.2017.10.006 ↗
19. Dye-sensitized solar cells: design-to-device approach affords panchromatic Co-sensitized solar cells10.1002/aenm.201970014 ↗
20. Machine learning optimization of p-type transparent conducting films10.1021/acs.chemmater.9b01953 ↗
21. Combining electronic and structural features in machine learning models to predict organic solar cells properties10.1039/C8MH01135D ↗
22. Toward predicting efficiency of organic solar cells via machine learning and improved descriptors10.1002/aenm.201801032 ↗
23. Efficient computational screening of organic polymer photovoltaics10.1021/jz400215j ↗
24. Insights from machine learning techniques for predicting the efficiency of fullerene derivatives‐based ternary organic solar cells at ternary blend design10.1002/aenm.201900891 ↗
25. Deep learning and random forest approach for finding the optimal traditional Chinese medicine formula for treatment of Alzheimer's disease10.1021/acs.jcim.9b00041 ↗
26. Random forest refinement of pairwise potentials for protein–ligand decoy detection10.1021/acs.jcim.9b00356 ↗
27. The progress and prospects of non-fullerene acceptors in ternary blend organic solar cells10.1039/C7MH00958E ↗
28. Recent progress on non-fullerene acceptors for organic photovoltaics10.1016/j.mattod.2018.09.004 ↗
29. Finding the right bricks for molecular legos: a data mining approach to organic semiconductor design10.1021/acs.chemmater.8b04436 ↗
30. Knowledge discovery through chemical space networks: the case of organic electronics10.1007/s00894-019-3950-6 ↗
31. Impact of the molecular quadrupole moment on ionization energy and electron affinity of organic thin films: experimental determination of electrostatic potential and electronic polarization energies10.1103/PhysRevB.97.245206 ↗
32. Recent progress in non-fullerene small molecule acceptors in organic solar cells10.1039/C6TC05066B ↗
33. Machine-learning assisted accurate band gap predictions of functionalized MXene10.1021/acs.chemmater.8b00686 ↗
34. Accelerated data-driven accurate positioning of the band edges of MXenes10.1021/acs.jpclett.9b00009 ↗
35. Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning10.1038/s41467-018-05761-w ↗
36. A deep neural network model using random forest to extract feature representation for gene expression data classification10.1038/s41598-018-34833-6 ↗
37. Creating machine learning-driven material recipes based on crystal structure10.1021/acs.jpclett.8b03527 ↗
38. Machine learning for understanding the relationship between the charge transport mobility and electronic energy levels for n‐type organic field‐effect transistors10.1002/aelm.201900573 ↗
39. Machine learning classification and structure–functional analysis of cancer mutations reveal unique dynamic and network signatures of driver sites in oncogenes and tumor suppressor genes10.1021/acs.jcim.8b00414 ↗
40. The recent progress of wide bandgap donor polymers towards non-fullerene organic solar cells10.1016/j.cclet.2019.02.030 ↗
41. Designing promising molecules for organic solar cells via machine learning assisted virtual screening10.1039/C9TA04097H ↗
42. Concurrent optimization of organic donor–acceptor pairs through machine learning10.1002/aenm.201902463 ↗
43. Over 16% efficiency organic photovoltaic cells enabled by a chlorinated acceptor with increased open-circuit voltages10.1038/s41467-019-10351-5 ↗
44. Ultra-narrow bandgap non-fullerene acceptors for organic solar cells with low energy loss
45. A comparative study on hole transfer inversely correlated with driving force in two non-fullerene organic solar cells10.1021/acs.jpclett.9b01383 ↗
46. Chlorinated thiophene end groups for highly crystalline alkylated non-fullerene acceptors toward efficient organic solar cells10.1021/acs.chemmater.9b00980 ↗
47. Low-bandgap non-fullerene acceptors based on selenopheneπspacer and alkylated indaceno [1,2-b:5,6-b′]dithiophene for organic solar cells10.1016/j.orgel.2019.03.038 ↗
48. Predicting the band gaps of inorganic solids by machine learning10.1021/acs.jpclett.8b00124 ↗
49. A chlorinated low-bandgap small-molecule acceptor for organic solar cells with 14.1% efficiency and low energy loss10.1007/s11426-018-9334-9 ↗
50. High efficiency near-infrared and semitransparent non-fullerene acceptor organic photovoltaic cells10.1021/jacs.7b11278 ↗
51. Molecular optimization enables over 13% efficiency in organic solar cells10.1021/jacs.7b02677 ↗