Benzothiophene semiconductor polymer design by machine learning with low exciton binding energy: A vast chemical space generation for new structures
Source abstract
Abstract
The development of new organic semiconductors with low exciton binding energies (Eb) is crucial for improving the efficiency of organic photovoltaic (PV) devices. Here, we report the generation of a chemical space of benzothiophene (BDT)-based organic semiconductors with lowest Eb energies using machine learning (ML). Our study involves the design of over 500 organic semiconductor structures with low Eb energies and their synthetic accessibility scores. For this, we collect 1061 BDT based compounds from literature, calculated their Eb energies, and predicted them using ML with Random Forest (RF) regression, yielding the best results. Our analysis, using SHAP values, reveals that heavy atoms are the main factors in lowering Eb values. Furthermore, we tested new organic chromophore structures, which showed an efficient shift of their molecular charges. The UV–Vis spectra of these structures exhibits a redshift in the range of 358–667 nm, while their open-circuit voltage (Voc) and light-harvesting efficiency (LHE) ranges from 1.64 to 1.954 V and 52–91 %, respectively. Current study provides a valuable chemical space for the development of new organic semiconductors with improved efficiency. © 2025 Elsevier Ltd
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Organic Electronics and Photovoltaics · Perovskite Materials and Applications · Conducting polymers and applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (47)
Show source-provided references
1. The role of financial markets in the energy transition: an analysis of investment trends and opportunities in renewable energy and clean technology10.1007/s11356-023-29014-6 ↗
2. Influence of donor groups on benzoselenadiazole-based dopant-free hole transporting materials for high performance perovskite solar cells10.1021/acsaem.0c02264 ↗
3. Progress and prospects of thick-film organic solar cells10.1039/D0TA10594E ↗
4. A history and perspective of non-fullerene electron acceptors for organic solar cells10.1002/aenm.202003570 ↗
5. Constructing high-performance organic photovoltaics via emerging non-fullerene acceptors and tandem-junction structure10.1002/aenm.202000746 ↗
6. Naphthalenediimide and perylenediimide based donor-acceptor crystalline hybrid materials: structures and applications10.1016/j.ccr.2024.216350 ↗
7. Deep red PhOLED from dimeric salophen Platinum(II) complexes10.1016/j.dyepig.2018.10.053 ↗
8. Design of organic small molecules for photovoltaic application with high open-circuit voltage (V oc)10.1039/C8TC06589F ↗
9. Benzothiadiazole-based D- $π$-A- $π$-D organic dyes with tunable band gap: synthesis and photophysical properties10.1021/ol101754q ↗
10. Biomass-based shape-stabilized composite phase-change materials with high solar–thermal conversion efficiency for thermal energy storage10.3390/polym15183747 ↗
11. Machine learning-based q-RASPR modeling of power conversion efficiency of organic dyes in dye-sensitized solar cells10.1039/D3SE00457K ↗
12. Graph-aware tensor factorization convolutional network for knowledge graph completion10.1007/s13042-023-01995-3 ↗
13. Determination of the exciton binding energy and effective masses for methylammonium and formamidinium lead tri-halide perovskite semiconductors10.1039/C5EE03435C ↗
14. Origin of the variation of exciton binding energy in semiconductors
15. New tailored substituted benzothiazole Schiff base Cu (II)/Zn (II) antitumor drug entities: effect of substituents on DNA binding profile, antimicrobial and cytotoxic activity10.1080/07391102.2018.1467794 ↗
16. PSI4 1.4: open-source software for high-throughput quantum chemistry10.1063/5.0006002 ↗
17. Visualizing chemical space networks with RDKit and NetworkX10.1186/s13321-022-00664-x ↗
18. Definition and application of a novel valence molecular connectivity index10.1016/j.theochem.2003.08.093 ↗
19. An atom-in-molecule adaptive polarized valence single-ζ atomic orbital basis for electronic structure calculations10.1063/5.0172373 ↗
20. Frisch · 2013
21. Description of adenine and cytosine on Au (111) nano surface using different DFT functionals (PW91PW91, wB97XD, M06-2X, M06-L and CAM-B3LYP) in the framework of ONIOM scheme: non-periodic calculations10.1016/j.chemphys.2017.03.001 ↗
22. Addition of polarization and diffuse functions to the LANL2DZ basis set for p-block elements10.1021/jp011945l ↗
23. Systematic study on the TD-DFT calculated electronic circular dichroism spectra of chiral aromatic nitro compounds: a comparison of B3LYP and CAM-B3LYP10.1016/j.saa.2015.11.002 ↗
24. A long-range planar polymer with efficient π-electron delocalization for superior proton storage
25. Multiwfn: a multifunctional wavefunction analyzer10.1002/jcc.22885 ↗
26. Application of Gaussian 09/GaussView 5.0 in analytical chemistry teaching
27. A machine learning prediction model for quantitative analyzing the influence of non-radiative voltage loss on non-fullerene organic solar cells10.1016/j.cej.2023.145958 ↗
28. GUIDEMOL: a Python graphical user interface for molecular descriptors based on RDKit10.1002/minf.202300190 ↗
29. Zhu L, Huang M, Han G, et al The Key Descriptors for Predicting the Exciton Binding Energy of Organic Photovoltaic Materials. Angew. Chem. 137:e202413913. https://doi.org/10.1002/ange.202413913.10.1002/ange.202413913 ↗
30. Design of organic electronic materials with lower exciton binding energy: machine learning analysis and high-throughput screening10.1007/s11082-024-07241-6 ↗
31. Machine-learning-assisted performance improvements for multi-resonance thermally activated delayed fluorescence molecules10.1039/D3CP04441F ↗
32. Design of experiments with the support of machine learning for process parameter optimization of all-small-molecule organic solar cells10.1002/flm2.34 ↗
33. Risk assessment of bridge construction investigated using random forest algorithm
34. SHapley additive exPlanations for explaining artificial neural network based mode choice models10.1007/s40890-024-00200-6 ↗
35. Implementasi metode support vector machine (SVM) dan t-distributed stochastic neighbor embedding (t-SNE) untuk klasifikasi depresi
36. Molecular fragmentation as a crucial step in the AI-based drug development pathway10.1038/s42004-024-01109-2 ↗
37. Photocyclodimers from Z-ligustilide. Experimental results and FMO analysis10.1016/j.tetlet.2005.03.024 ↗
38. DFT/TDDFT, NPA, and AIM-based study of the molecular switching properties of photocyclization and metallochromism of the DAE complexes10.1007/s00214-018-2204-5 ↗
39. The measurement of oscillator strengths10.1088/0034-4885/49/4/002 ↗
40. Koopmans' theorem for large molecular systems within density functional theory10.1021/jp063669m ↗
41. New relationships connecting the dipole polarizability, radius, and second ionization potential for atoms10.1021/jp2094438 ↗
42. Theoretical analysis of frontier orbitals, electronic transitions, and global reactivity descriptors of M (CO) 4 L 2 type metal carbonyl complexes: a DFT/TDDFT study10.1007/s11224-018-1231-0 ↗
43. Modeling of lattice constant and their relations with ionic radii and electronegativity of constituting ions of A2XY6 cubic crystals (A= K, Cs, Rb, Tl; X= tetravalent cation, Y= F, Cl, Br, I)10.1016/j.jpcs.2011.07.016 ↗
44. Electron donor-acceptor complexes as potential high-efficiency second-order nonlinear optical materials. A computational investigation10.1021/ja00055a043 ↗
45. Highly efficient light-harvesting ruthenium sensitizer for thin-film dye-sensitized solar cells10.1021/nn900756s ↗
46. Origin of the open circuit voltage of plastic solar cells10.1002/1616-3028(200110)11:5<374::AID-ADFM374>3.0.CO;2-W ↗
47. Analysis of interturn short circuit in regulating winding of power transformer based on field-circuit coupling10.3389/fenrg.2024.1393436 ↗