journal article·2023-06

Employing artificial neural network on geometrical morphological descriptors for deriving physics-based insights in multi-component organic photovoltaics

Manjeet Keshav, Fiyanshu Kaka

Publisher page

Abstract

In recent years, high energy demands have posed a huge challenge to the research community to come up with efficient and robust energy-producing materials. In lieu of this, materials discovery by building a Process-Structure-Properties (P–S–P) relationship for organic photovoltaic (OPV) cells using mathematical and statistical models is a useful approach, however, computationally expensive and time-consuming. The present study utilizes the physics-based model to develop the Process-Structure (P–S) relationship for 68 different blend ratios and proposed Artificial Neural Network (ANN) models to map blend concentration with structural properties of OPV cells, namely, Percolation Fraction (PF) and Interfacial Area (IA). The fitted ANN model is then utilised for multi-objective optimization to find the optimal concentration of donor and acceptor to have maximum PF and IA using a Genetic Algorithm; this is further verified by search-based multi-objective optimization to have better insight into the design sub-space which contained optimal solution. Finally, the optimal values of concentrations are validated through device optimization where efficiency predictions were made on structural data of the same morphologies using a mechanistic and regression model. It has been demonstrated that the amalgamation of data-driven techniques and physics-based simulation is the new way forward for accelerated material discovery.
Source: expertdata · 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 (45)

Show source-provided references
1. Cost estimates of production scale semitransparent organic photovoltaic modules for building integrated photovoltaics10.1039/D0SE00910E ↗
2. Comprehensive review on the application of inorganic and organic photovoltaics as greenhouse shading materials
3. Advances in organic and perovskite photovoltaics enabling a greener Internet of Things10.1002/adfm.202200694 ↗
4. Organic and solution-processed tandem solar cells with 17.3% efficiency10.1126/science.aat2612 ↗
5. Understanding the blade coated to roll-to-roll coated performance gap in organic photovoltaics10.1016/j.solmat.2022.111852 ↗
6. Enhanced lifetime of organic photovoltaic diodes achieved by blending with PMMA: impact of morphology and Donor:Acceptor combination10.1016/j.solmat.2020.110765 ↗
7. Two‐layer organic photovoltaic cell10.1063/1.96937 ↗
8. Single-layered organic photovoltaics with double cascading charge transport pathways: 18% efficiencies
9. Solution-Processed semitransparent organic photovoltaics: from molecular design to device performance
10. Highly efficient flexible organic photovoltaic modules for sustainable energy harvesting under low-light condition via suppressing voltage-drop by metal-mediated cross-linkable polymer interfacial layer10.1016/j.cej.2022.137555 ↗
11. GraSPI: extensible software for the graph-based quantification of morphology in organic electronics
12. Skeletal-based microstructure representation and convolution reconstruction10.1016/j.commatsci.2021.110409 ↗
13. Optimising the photovoltaic parameters in donor–acceptor–acceptor ternary polymer solar cells using Machine Learning framework10.1016/j.solener.2021.11.054 ↗
14. Epitaxial growth of vertically aligned antimony selenide nanorod arrays for heterostructure based self-powered photodetector10.1002/adom.202200816 ↗
15. Theoretical insight into high-efficiency triple-junction tandem solar cells via the band engineering of antimony chalcogenides10.1002/solr.202000800 ↗
16. Rotational design of charge carrier transport layers for optimal antimony trisulfide solar cells and its integration in tandem devices10.1016/j.solmat.2019.110279 ↗
17. Energy band alignment in molybdenum oxide/Cu(in,Ga)Se2Interface for high-efficiency ultrathin Cu(in,Ga)Se2Solar cells from low-temperature growth10.1021/acsaem.9b02460 ↗
18. Bending and pinching of three-phase stripes: from secondary instabilities to morphological deformations in organic photovoltaics10.1103/PhysRevE.102.062213 ↗
19. Simulating charge transport in organic semiconductors and devices: a review10.1088/1361-6633/80/2/026502 ↗
20. Machine learning in materials science10.1002/inf2.12028 ↗
21. Computer-aided screening of conjugated polymers for organic solar cell: classification by random forest10.1021/acs.jpclett.8b00635 ↗
22. Structure-property correlation study for organic photovoltaic polymer materials using data science approach10.1021/acs.jpcc.0c00517 ↗
23. Insights from machine learning techniques for predicting the efficiency of fullerene derivatives-based ternary organic solar cells at ternary blend design10.1002/aenm.201900891 ↗
24. Robust random forest based non-fullerene organic solar cells efficiency prediction10.1016/j.orgel.2019.105465 ↗
25. An attention-driven long short-term memory network for high throughput virtual screening of organic photovoltaic candidate molecules10.1016/j.solener.2021.05.064 ↗
26. Experiment-oriented machine learning of polymer:non-fullerene organic solar cells
27. Data-driven strategies for accelerated materials design10.1021/acs.accounts.0c00785 ↗
28. Enhancing the stability of organic photovoltaics through machine learning10.1016/j.nanoen.2020.105342 ↗
29. Algorithmically extracted morphology descriptions for predicting device performance10.1016/j.commatsci.2021.110599 ↗
30. Machine learning-assisted development of organic photovoltaics via high-throughput in situ formulation10.1039/D1EE00641J ↗
31. Beyond Langevin recombination: how equilibrium between free carriers and charge transfer states determines the open-circuit voltage of organic solar cells10.1002/aenm.201500123 ↗
32. Organic photovoltaics: relating chemical structure, local morphology, and electronic properties10.1016/j.trechm.2020.03.006 ↗
33. Chen · 2003 · vol. 32 · 113
34. The coupling and competition of crystallization and phase separation, correlating thermodynamics and kinetics in OPV morphology and performances
35. Investigation of process–structure–property relationship in ternary organic photovoltaics10.1063/5.0020863 ↗
36. Critical factors governing vertical phase separation in polymer-PCBM blend films for organic solar cells
37. On the solubility parameter of C60 and higher fullerenes10.1080/15363830802671288 ↗
38. Self-diffusivity estimation by molecular dynamics
39. Modeling morphology evolution during solvent-based fabrication of organic solar cells10.1016/j.commatsci.2011.12.012 ↗
40. Bimolecular recombination in polymer/fullerene bulk heterojunction solar cells10.1063/1.2170424 ↗
41. Ternary organic solar cells offer 14% power conversion efficiency10.1016/j.scib.2017.11.003 ↗
42. Electron collection as a limit to polymer:PCBM solar cell efficiency: effect of blend microstructure on carrier mobility and device performance in PTB7:PCBM10.1002/aenm.201400311 ↗
43. Improvement of electrical conductivity for high-performance organic solar cells by multi-temperature solvent annealing
44. Artificial neural networks: a practical course
45. Moré · 1978 · 105