Machine learning enhanced characterization and optimization of photonic cured MAPbI₃ for efficient perovskite solar cells

Abstract

Photonic curing (PC) can facilitate high-speed perovskite solar cell (PSC) manufacturing because it uses high-intensity light pulses to crystallize perovskite films in milliseconds. However, optimizing PC conditions is challenging due to its many variables, and using power conversion efficiency (PCE) as the optimization metric is both time-consuming and labor-intensive. This work presents a machine learning (ML) approach to optimize PC conditions for fabricating methylammonium lead iodide (MAPbI₃) films by quantitatively comparing their ultraviolet-visible (UV-vis) absorbance spectra to thermal annealed (TA) films using four similarity metrics. We perform Bayesian optimization coupled with Gaussian process regression (BO-GP) to minimize the similarity metrics. Refining PC conditions using active learning based on BO-GP models, we achieve a PC MAPbI₃ film with an absorbance spectrum closely matching a TA reference film, which is further verified by its crystalline and morphological properties. Thus, we demonstrate that the UV-vis absorption spectrum can accurately proxy film quality. Additionally, we use an AI-based segmentation model for a more efficient grain size analysis. However, when we use the optimized PC condition to fabricate PSCs, we find that interaction between MAPbI₃ and the hole transport layer (HTL) during PC critically degrades the PSC performance. By adding a buffer layer between the HTL and MAPbI₃, the optimized PC PSCs produce a champion PCE of 11.8%, comparable to the TA reference of 11.7%. Using UV-vis similarity metrics instead of device PCE as the objective in our BO-GP method accelerates the optimization of PC processing conditions for MAPbI₃ films.

Keywords

Perovskite solar cells / Bayesian optimization / photonic curing / image segmentation / machine learning

References

[1] NREL. Best research-cell efficiency chart. Available from: https://www.nrel.gov/pv/cell-efficiency.html. [Last accessed on 30 Dec 2024]

[2] Zhang C.Materials and methods for cost-effective fabrication of perovskite photovoltaic devices.Commun Mater2024;5:636

[3] Abbasi S,Tipparak P.Proper annealing process for a cost effective and superhydrophobic ambient-atmosphere fabricated perovskite solar cell.Mat Sci Semicon Proc2023;155:107241

[4] Penpong K,Naikaew A.Robust perovskite formation via vacuum thermal annealing for indoor perovskite solar cells.Sci Rep2023;13:10933 PMCID:PMC10325999

[5] Huddy JE,Scheideler WJ.Eliminating the perovskite solar cell manufacturing bottleneck via high-speed flexography.Adv Mater Technol2022;7:2101282

[6] Lavery BW,Konermann H,Spurgeon J.Intense pulsed light sintering of CH₃NH₃PbI₃ solar cells.ACS Appl Mater Interfaces2016;8:8419-26

[7] Xu W,Piper RT.Effects of photonic curing processing conditions on MAPbI₃ film properties and solar cell performance.ACS Appl Energy Mater2020;3:8636-45

[8] Ghahremani AH,Bahadur J.Intense pulse light annealing of perovskite photovoltaics using gradient flashes.ACS Appl Energy Mater2020;3:11641-54

[9] Serafini P,Barea EM,Sánchez S.Photonic processing of MAPbI₃ films by flash annealing and rapid growth for high-performance perovskite solar cells.Solar RRL2022;6:2200641

[10] Ankireddy K,Martin B,Druffel T.Rapid thermal annealing of CH₃NH₃PbI₃ perovskite thin films by intense pulsed light with aid of diiodomethane additive.J Mater Chem A2018;6:9378-83

[11] Xu W,Piper RT.Effects of residual DMSO adduct on photonically cured MAPbI₃ solar cells.J Phys Chem C2023;127:14933-9

[12] Xu W,Piper RT.Bayesian optimization of photonic curing process for flexible perovskite photovoltaic devices.Sol Energ Mat Sol C2023;249:112055

[13] Yılmaz B.Critical review of machine learning applications in perovskite solar research.Nano Energy2021;80:105546

[14] Song Q,Chen Q.The spring of processing chemistry in perovskite solar cells-bayesian optimization.J Phys Chem Lett2022;13:10741-50

[15] Srivastava M,Gong T,Leite MS.Machine learning roadmap for perovskite photovoltaics.J Phys Chem Lett2021;12:7866-77

[16] Higgins K,Ziatdinov M,Ahmadi M.Chemical robotics enabled exploration of stability in multicomponent lead halide perovskites via machine learning.ACS Energy Lett2020;5:3426-36

[17] Taherimakhsousi N,Macleod BP.A machine vision tool for facilitating the optimization of large-area perovskite photovoltaics.npj Comput Mater2021;7:657

[18] Kumar V,Vishvakarma A,Kumar L.Growth of MAPbI₃ perovskite films on MWCNT-modified TiO₂ thin films for solar cell applications.Inorg Chem Commun2024;163:112360

[19] Tian SIP,Chellappan V.Rapid and accurate thin film thickness extraction via UV-vis and machine learning. In: 2020 47th IEEE Photovoltaic Specialists Conference (PVSC); 2020 Jun 15 - Aug 21; Calgary, Canada. IEEE; 2020. pp. 0128-32.

[20] Qaid SMH,Al-Asbahi BA.Solvent effects on the structural and optical properties of MAPbI₃ perovskite thin film for photovoltaic active layer.Coatings2022;12:549

[21] Standard test methods for determining average grain size. 2021.

[22] Dunlap-Shohl WA,Mitzi DB.Interfacial effects during rapid lamination within MAPbI₃ thin films and solar cells.ACS Appl Energy Mater2019;2:5083-93

[23] Thampy S,Hong K,Hsu JWP.Altered stability and degradation pathway of CH₃NH₃PbI₃ in contact with metal oxide.ACS Energy Lett2020;5:1147-52

[24] Lee SH,Kim HJ.Selection of a suitable solvent additive for 2-methoxyethanol-based antisolvent-free perovskite film fabrication.ACS Appl Mater Interfaces2022;14:39132-40

[25] Bhandari B,Piper RT.Effects of transparent conducting electrodes and hole transport layers on the performance of MAPbI₃ solar cells fabricated on PET substrates.Flex Print Electron2024;9:035002

[26] Mohanraj J,Almora O.NiO_x passivation in perovskite solar cells: from surface reactivity to device performance.ACS Appl Mater Interfaces2024;16:42835-50

[27] Phung N,Todinova A.Enhanced self-assembled monolayer surface coverage by ALD NiO in p-i-n perovskite solar cells.ACS Appl Mater Interfaces2022;14:2166-76 PMCID:PMC8763377

[28] Gower JC.Generalized procrustes analysis.Psychometrika1975;40:33-51

[29] MathWorks. Procrustes. Available from: https://www.mathworks.com/help/stats/procrustes.html. [Last accessed on 30 Dec 2024]

[30] Eiter T. Computing discrete fréchet distance. 1994. Available from: https://www.researchgate.net/profile/Thomas-Eiter-2/publication/228723178_Computing_Discrete_Frechet_Distance/links/5714d93908aebda86c0d1a7b/Computing-Discrete-Frechet-Distance.pdf. [Last accessed on 30 Dec 2024]

[31] Danziger Z. Discrete frechet distance. MATLAB Central File Exchange. 2024. Available from: https://www.mathworks.com/matlabcentral/fileexchange/31922-discrete-frechet-distance. [Last accessed on 30 Dec 2024]

[32] Gongora AE,Perry W.A Bayesian experimental autonomous researcher for mechanical design.Sci Adv2020;6:eaaz1708 PMCID:PMC7148087

[33] Rohr B,Guevarra D.Benchmarking the acceleration of materials discovery by sequential learning.Chem Sci2020;11:2696-706 PMCID:PMC8157525

[34] Liu Z,Flick AC.Machine learning with knowledge constraints for process optimization of open-air perovskite solar cell manufacturing.Joule2022;6:834-49

[35] Kirillov A,Ravi N.Segment anything.arXiv2023; arXiv:2304.02643. Available from: https://doi.org/10.48550/arXiv.2304.02643.

[36] Wu G,Cao Y.Enlarging grain sizes for efficient perovskite solar cells by methylamine chloride assisted recrystallization.J Energy Chem2022;65:55-61

[37] Jin H,Ball JM.Alumina nanoparticle interfacial buffer layer for low-bandgap lead-tin perovskite solar cells.Adv Funct Mater2023;33:2303012

[38] Cui P,Wei D.Reduced surface defects of organometallic perovskite by thermal annealing for highly efficient perovskite solar cells.RSC Adv2015;5:75622-9

[39] Wang T,Huang L.MAPbI₃ quasi-single-crystal films composed of large-sized grains with deep boundary fusion for sensitive vis-NIR photodetectors.ACS Appl Mater Interfaces2020;12:38314-24

[40] Giesbrecht N,Grill I.Single-crystal-like optoelectronic-properties of MAPbI₃ perovskite polycrystalline thin films.J Mater Chem A2018;6:4822-8

[41] Kim HD,Benten H.Photovoltaic performance of perovskite solar cells with different grain sizes.Adv Mater2016;28:917-22

[42] deQuilettes DW,Stranks SD.Solar cells. Impact of microstructure on local carrier lifetime in perovskite solar cells.Science2015;348:683-6

[43] Ahmad S,Zheng J.Suppressing nickel oxide/perovskite interface redox reaction and defects for highly performed and stable inverted perovskite solar cells.Small Methods2022;6:e2200787