Optoelectronic devices informatics: optimizing DSSC performance using random-forest machine learning algorithm

Abstract

This paper provides an attempt to utilize machine learning algorithm, explicitly random-forest algorithm, to optimize the performance of dye sensitized solar cells (DSSCs) in terms of conversion efficiency. The optimization is implemented with respect to both the mesoporous TiO₂ active layer thickness and porosity. Herein, the porosity impact is reflected to the model as a variation in the effective refractive index and dye absorption. Database set has been established using our data in the literature as well as numerical data extracted from our numerical model. The random-forest model is used for model regression, prediction, and optimization, reaching 99.87% accuracy. Perfect agreement with experimental data was observed, with 4.17% conversion efficiency.

References

[1] SánchezM, FranciscoJ, SteinerM, et al.. Worldwide energy harvesting potential of hybrid CPV/PV technology[J]. Joule, 2021, 24(7):971-987

[2] AhmadK S, NaqviK S, JaffriS B. Systematic review elucidating the generations and classifications of solar cells contributing towards environmental sustainability integration[J]. Reviews in inorganic chemistry, 2021, 41(1):21-39

[3] AbdellatifS O, JostenS, KhalilA S G, et al.. Transparency and diffused light efficiency of dye-sensitized solar cells: tuning and a new figure of merit[J]. IEEE journal of photovoltaics, 2020, 10(2):522-530

[4] MoustafaM M, IsmailZ S, HashemE M, et al.. Investigating the tradeoff between transparency and efficiency in semitransparent bifacial mesosuperstructured solar cells for millimeter-scale applications[J]. IEEE journal of photovoltaics, 2021, 11(5):222-235

[5] AbdellatifS, SharifiS, KirahK, et al.. Refractive index and scattering of porous TiO₂ films[J]. Microporous and mesoporous materials, 2018, 264: 84-91

[6] AbdellatifS, JostenS, SharifiP, et al.. Optical investigation of porous TiO₂ in mesostructured solar cells[C], 2018, Washington, SPIE: 105260A

[7] HatemT, IsmailZ, ElmahgaryZ, et al.. Optimization of organic meso-superstructured solar cells for underwater IoT² self-powered sensors[J]. IEEE transactions on electron devices, 2021, 68(10):5319-5321

[8] MarriA R, MarchiniE, CabanesV D, et al.. Record power conversion efficiencies for iron (II)-NHC-sensitized DSSCs from rational molecular engineering and electrolyte optimization[J]. Journal of materials chemistry A, 2021, 9(6):3540-3554

[9] ShahS A A, GuoZ, SayyadM H, et al.. Optimizing zinc oxide nanorods based DSSC employing different growth conditions and SnO coating[J]. Journal of materials science: materials in electronics, 2021, 32(2):2366-2372

[10] WardL, WolvertonC. Atomistic calculations and materials informatics: a review[J]. Current opinion in solid state and materials science, 2017, 21(3):167-176

[11] MahmoodA, WangJ L. Machine learning for high performance organic solar cells: current scenario and future prospects[J]. Energy & environmental science, 2021, 14(1):90-105

[12] ChoudharyK, BercxM, JiangJ, et al.. Accelerated discovery of efficient solar cell materials using quantum and machine-learning methods[J]. Chemistry of materials, 2019, 31(15):5900-5908

[13] SahuH, MaH. Unraveling correlations between molecular properties and device parameters of organic solar cells using machine learning[J]. The journal of physical chemistry letters, 2019, 10(22):7277-7284

[14] AroojQ, WangF. Switching on optical properties of D-π-A DSSC sensitizers from π-spacers towards machine learning[J]. Solar energy, 2019, 188: 1189-1200

[15] WenY, FuL, LiG, et al.. Accelerated discovery of potential organic dyes for dye-sensitized solar cells by interpretable machine learning models and virtual screening[J]. Solar RRL, 2020, 4(6):2000110

[16] Al-SabanO, AbdellatifS O. Optoelectronic materials informatics: utilizing random-forest machine learning in optimizing the harvesting capabilities of mesostructured-based solar cells[C], 2021, New York, IEEE: 1-4

[17] Rodriguez-GalianoV, Sanchez-CastilloM, Chica-OlmoM, et al.. Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines[J]. Ore geology reviews, 2015, 71: 804-818

[18] EidA A, IsmailZ S, AbdellatifS O. Optimizing SCAPS model for perovskite solar cell equivalent circuit with utilizing Matlab-based parasitic resistance estimator algorithm[C], 2020, New York, IEEE: 503-507

[19] HassanM M, SahbelA, AbdellatifS O, et al.. Toward low-cost, stable, and uniform high-power LED array for solar cells characterization[C], 2020, Washington, SPIE: 114960Q

[20] KimJ Y, LeeK, CoatesN E, et al.. Efficient tandem polymer solar cells fabricated by all-solution processing[J]. Science, 2007, 317(5835):222-225