The next major change in perovskite and organic photovoltaic research may not come from a new material or device architecture, but from a new way of doing and analyzing experiments. Conventional trial-and-error optimization, often a onevariable-at-a-time (OVAT) approach, typically varies a limited number of parameters sequentially, making it difficult to resolve interactions within the increasingly complex processing spaces of complex, multilayer solar cells and demands a large number of experiments. We argue that robotic experimentation combined with machine learning can fundamentally alter this approach. The key advantage of robotics is not simply higher throughput, but highly precise and reproducible fabrication together with comprehensive recording of processing and environmental conditions. This transforms individual experiments into reliable, machine-readable data points and provides the foundation for machine learning to explore multidimensional parameter spaces, identify hidden correlations and autonomously select informative experiments. Optimization can consequently move beyond maximizing power-conversion efficiency toward understanding how parameters interact, with simultaneous consideration of efficiency, lifetime, stability, reproducibility, resource consumption and environmental impact. Such a transition could replace sequential trial-and-error optimization with reproducible, data-rich and closed-loop experimentation. Rather than replacing researchers, robotic laboratories may enable them to investigate materials and processing spaces that are too complex to explore manually. We propose that the long-term impact of autonomous experimentation in photovoltaics will therefore be measured by how much more can be learned from every experiment.
- Open Access
- Perspective
From Trial-and-Error to Learn-by-Experiment: The Future of Materials Research in Perovskite and Organic Photovoltaics
- Maria Azhar 1,
- Stefan Kraner 1,
- Nikky Chandrakar 1,
- Nathanael Füssinger 1,
- Lukas Schmidt-Mende 1,*,
- Udo Bach 2,*
Author Information
Received: 10 Sep 2026 | Revised: 23 Sep 2026 | Accepted: 24 Sep 2026 | Published: 28 Sep 2026
Abstract
References
- 1.
Yu, Y.; Zhang, F.; Hou, T.; et al. A Review on Gas-Quenching Technique for Efficient Perovskite Solar Cells. Sol. RRL 2021, 5, 2100386. https://doi.org/10.1002/solr.202100386.
- 2.
Wagner, J.; Berger, C.G.; Du, X.; et al. The evolution of Materials Acceleration Platforms: toward the laboratory of the future with AMANDA. J. Mater. Sci. 2021, 56, 16422–16446. https://doi.org/10.1007/s10853-021-06281-7.
- 3.
Du, X.; Luer, L.; Heumueller, T.; et al. Elucidating the Full Potential of OPV Materials Utilizing a High-Throughput Robot-Based Platform and Machine Learning. Joule 2021, 5, 495–506. https://doi.org/10.1016/j.joule.2020.12.013.
- 4.
Zhao, Y.; Zhang, J.; Xu, Z.; et al. Discovery of temperature-induced stability reversal in perovskites using high-throughput robotic learning. Nat. Commun. 2021, 12, 2191. https://doi.org/10.1038/s41467-021-22472-x.
- 5.
Zhang, J.; Liu, B.; Liu, Z.; et al. Optimizing Perovskite Thin-Film Parameter Spaces with Machine Learning-Guided Robotic Platform for High-Performance Perovskite Solar Cells. Adv. Energy Mater. 2023, 13, 2302594. https://doi.org/10.1002/aenm.202302594.
- 6.
Meftahi, N.; Surmiak, M.A.; Furer, S.O.; et al. Machine Learning Enhanced High-Throughput Fabrication and Optimization of Quasi-2D Ruddlesden–Popper Perovskite Solar Cells. Adv. Energy Mater. 2023, 13, 2203859. https://doi.org/10.1002/aenm.202203859.
- 7.
Zhang, J.; Hauch, J.A.; Brabec, C.J. Toward Self-Driven Autonomous Material and Device Acceleration Platforms (AMADAP) for Emerging Photovoltaics Technologies. Acc. Chem. Res. 2024, 57, 1434–1445. https://doi.org/10.1021/acs.accounts.4c00095.
- 8.
8. Zhang, J.; Wu, J.; Stroyuk, O.; et al. Self-driving AMADAP laboratory: Accelerating the discovery and optimization of emerging perovskite photovoltaics. MRS Bull. 2024, 49, 1284–1294. https://doi.org/10.1557/s43577-024-00816-4.
- 9.
Zhang, J.; Wu, J.; Le Corre, V.M.; et al. Advancing perovskite photovoltaic technology through machine learning-driven automation. InfoMat 2025, 7, e70005. https://doi.org/10.1002/inf2.70005.
- 10.
Gao, D.; Lu, S.; Zhang, C.; et al. Autonomous closed-loop framework for reproducible perovskite solar cells. Nature 2026, 653, 707–714. https://doi.org/10.1038/s41586-026-10482-y.
- 11.
Cakan, D.N.; Oberholtz, E.; Kaushal, K.; et al. Bayesian optimization and prediction of the durability of triple-halide perovskite thin films under light and heat stressors. Mater. Adv. 2025, 6, 598–606. https://doi.org/10.1039/d4ma00747f.
- 12.
Ismaeel, S.; Manzoor, S.; Sabir, M.Z. Toward autonomous discovery in small-molecule organic photovoltaics: A review integrating artificial intelligence and machine learning within the molecular design landscape. Org. Electron. 2026, 154, 107424. https://doi.org/10.1016/j.orgel.2026.107424.
- 13.
Kim, S.A.; Bae, M.; Park, S.H.; et al. Beyond manual processing: Robotic-arm automation coupled with machine learning for precision control and correlation insights in perovskite solar cells. Adv. Sens. Energy Mater. 2026, 5, 100206. https://doi.org/10.1016/j.asems.2026.100206.
- 14.
Chen, W.; Zhang, Z.; Mularso, K.T.; et al. Smart Exploration of Perovskite Photovoltaics: From AI Driven Discovery to Autonomous Laboratories. Adv. Energy Mater. 2026. e06803. https://doi.org/10.1002/aenm.202506803.
- 15.
Lee, J.; Noh, J.; Lee, H.; et al. Recent advances in data-driven and artificial intelligence-integrated perovskite solar cells: From design to self-driving laboratories. InfoMat 2026, 8, e70124. https://doi.org/10.1002/inf2.70124.
- 16.
Ternes, S.; Laufer, F.; Paetzold, U.W. Modeling and Fundamental Dynamics of Vacuum, Gas, and Antisolvent Quenching for Scalable Perovskite Processes. Adv. Sci. 2024, 11, 2308901. https://doi.org/10.1002/advs.202308901.
- 17.
Wilkinson, M.D.; Dumontier, M.; Aalbersberg, I.J.; et al. The FAIR Guiding Principles for scientific data management and stewardship. Sci. Data 2016, 3, 160018. https://doi.org/10.1038/sdata.2016.18.
- 18.
Azhar, M.; Cuzzupe, D.T.; Yalcinkaya, Y.; et al. Impact of Antisolvent and Gas Quenching on Wrinkling in Cs0.15FA0.85Pb(I0.6Br0.4)3Perovskite Films. ACS Appl. Mater. Interfaces 2025. https://doi.org/10.1021/acsami.5c07659.
- 19.
Azhar, M.; Yalcinkaya, Y.; Cuzzupe, D.T.; et al. Perovskite Thin Films Solar Cells: The Gas Quenching Method. Mater. Sustain. 2025, 1, 5. https://doi.org/10.53941/matsus.2025.100005.
- 20.
Temitmie, Y.A.; Azhar, M.; Haider, M.I.; et al. Gas Quenching-Mediated Crystallization for Optoelectronic-Grade Pb–Sn Perovskite Films. Sol. RRL 2026, 10, e202500713. https://doi.org/10.1002/solr.202500713.
- 21.
Du, X.; Luer, L.; Heumueller, T.; et al. Revealing processing stability landscape of organic solar cells with automated research platforms and machine learning. InfoMat 2024, 6, e12554. https://doi.org/10.1002/inf2.12554.
- 22.
Otsu, N. A Threshold Selection Method from Gray-Level Histograms. IEEE Trans. Syst. Man Cybern. 1979, 9, 62–66. https://doi.org/10.1109/tsmc.1979.4310076.
- 23.
Kim, M.; Lee, J.; Chun, H.W.; et al. Cross-laboratory generalization failure in perovskite solar cell machine learning: A diagnostic protocol and evaluation threshold. Energy AI 2026, 25, 100856. https://doi.org/10.1016/j.egyai.2026.100856.
- 24.
Day, A.L.; Wahl, C.B.; dos Reis, R.; et al. Automated image segmentation for accelerated nanoparticle characterization. Sci. Rep. 2025, 15, 17180. https://doi.org/10.1038/s41598-025-01337-z.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com