Data-driven designing of dyes: Chemical space generation and dipole moment prediction
Source abstract
Abstract
The current study presents machine learning-assisted designing of dyes for photovoltaics applications. Multiple machine learning models are trained to predict the dipole moment. Random forest model has appeared as best model with lower root mean square error value (1.01 Debye) and higher r-squared value (0.87). New dyes are designed using automatic method and their dipole moment is predicted using best machine learning model. The generated chemical space of dyes is visualized and analyzed using cluster plot, silhouette plot and t-distributed Stochastic Neighbor Embedding (t-SNE plot). 30 dyes with highest dipole moment values (6.31–7.12 Debye) are chosen. Chemical similarity analyses are performed on the selected dyes using cluster analysis and heatmap. Furthermore, an investigation into the synthetic accessibility score of the newly designed dyes is conducted. This method facilitates the swift selection of dyes for potential use in photovoltaic devices.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Photochromic and Fluorescence Chemistry · Photopolymerization techniques and applications · Chemistry and Chemical Engineering
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (32)
Show source-provided references
1. Triphenylamine based dyes for dye sensitized solar cells: A review10.1016/j.solener.2015.11.015 ↗
2. Recent research progress on quasi-solid-state electrolytes for dye-sensitized solar cells10.1016/j.jechem.2015.10.018 ↗
3. Squaraine dyes: The hierarchical synthesis and its application in optical detection10.1016/j.jphotochemrev.2017.03.001 ↗
4. Computational designing of triphenylamine dyes with broad and red-shifted absorption spectra for dye-sensitized solar cells using multi-thiophene rings in π-spacer10.1002/bkcs.10526 ↗
5. Heterocyclic azo dyes for dye sensitized solar cells: A quantum chemical study10.1016/j.comptc.2015.05.020 ↗
6. A binary solution strategy enables high-efficiency Quasi-2D perovskite solar cells with excellent thermal stability10.1021/acsnano.3c01908 ↗
7. Achieving high open-circuit voltage in efficient kesterite solar cells via lanthanide europium ion induced carrier lifetime enhancement10.1016/j.nanoen.2024.109448 ↗
8. Machine learning for organic photovoltaic polymers: A minireview10.1007/s10118-022-2782-5 ↗
9. Easy and fast prediction of green solvents for small molecule donor-based organic solar cells through machine learning10.1039/D3CP00177F ↗
10. Predicting the thermal distribution in a convective wavy fin using a novel training physics-informed neural network method10.1038/s41598-024-57772-x ↗
11. Radiative heat transfer analysis of a concave porous fin under the local thermal non-equilibrium condition: Application of the clique polynomial method and physics-informed neural networks10.1007/s10483-024-3143-6 ↗
12. Advanced deep learning approach with physics-informed neural networks for analysing the thermal variation through a radial fin applicable in heat exchangers10.1007/s12043-024-02823-1 ↗
13. Physics-informed Hermite neural networks for wetted porous fin under the local thermal non-equilibrium condition: Application of clique polynomial method10.1140/epjs/s11734-024-01247-7 ↗
14. Developing efficient small molecule acceptors with sp2-hybridized nitrogen at different positions by density functional theory calculations, molecular dynamics simulations and machine learning10.1002/chem.202103712 ↗
15. A physics-informed machine learning prediction for thermal analysis in a convective-radiative concave fin with periodic boundary conditions10.1002/zamm.202300712 ↗
16. V.K. R S, C. K, N. Sharma, K. K, N.K. R, R.J. Punith Gowda, T. Muhammad, H. Singh Gill, Analyzing magnetic dipole impact in fluid flow with endothermic/exothermic reactions: neural network simulation, Phys. Scr., 99 (2024) 065215.10.1088/1402-4896/ad4072 ↗
17. Solvent effects on nonlinear optical response of certain tetrammineruthenium(II) complexes of modified 1,10-phenanthrolines10.1139/cjc-2013-0377 ↗
18. Electronic absorption spectra and nonlinear optical properties of ruthenium acetylide complexes: A DFT study toward the designing of new high NLO response compounds
19. Design of molecules with low hole and electron reorganization energy using DFT calculations and Bayesian optimization10.1021/acs.jpca.2c05229 ↗
20. G. Landrum, RDKit: Open-source cheminformatics. http://www.rdkit.org.
21. On the art of compiling and using 'Drug-Like' chemical fragment spaces10.1002/cmdc.200800178 ↗
22. Facile development of CoAl-LDHs/RGO nanocomposites as photocatalysts for efficient hydrogen generation from water splitting under visible-light irradiation10.1039/C9QI00307J ↗
23. A biopolymeric buffer layer improves device efficiency and stability in inverted organic solar cells10.1039/D0TC03048A ↗
24. An investigation on 4-aminobenzoic acid modified polyvinyl chloride/graphene oxide and PVC/graphene oxide based nanocomposite membranes10.1177/8756087915616434 ↗
25. Structure and properties of 4-aminobenzoic acid-modified polyvinyl chloride and functionalized graphite-based membranes10.1080/1536383X.2015.1118620 ↗
26. Generation of library of dyes for photovoltaic applications: A machine learning assisted framework10.1016/j.jphotochem.2024.116053 ↗
27. Machine learning assisted designing of Y-series small molecule acceptors: Library generation and property prediction10.1016/j.jphotochem.2024.115670 ↗
28. Chemical similarity-based design of materials for organic solar cells: Visualizing the generated chemical space of polymers
29. A surface modifier enhances the performance of the all-inorganic CsPbI2Br perovskite solar cells with efficiencies approaching 15%10.1039/D0CP01437K ↗
30. Perspectives on polyvinyl chloride and carbon nanofiller composite: A review10.1080/03602559.2016.1163587 ↗
31. Polydopamine/ZnO electron transport layers enhance charge extraction in inverted non-fullerene organic solar cells10.1039/C9TC02781E ↗
32. Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions10.1186/1758-2946-1-8 ↗