Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.
Advertisement
Nature (2026)
9647
1
5
Metrics details
The commercialization of perovskite solar cells (PSCs) is bottlenecked by inefficient trial-and-error approaches reliant on human expertise in both materials discovery and device fabrication1,2,3. Here we introduce an autonomous closed-loop framework that integrates machine learning (ML)-driven materials discovery with an automated manufacturing platform. The system uses active learning and quantum modelling to rapidly identify high-performance molecules and the platform uses Bayesian optimization and symbolic regression in a feedback loop to continuously refine the fabrication process. This integrated approach enabled the discovery of a passivation molecule, 5-(aminomethyl)nicotinonitrile hydroiodide (5ANI), which yielded 0.05-cm2 solar cells with a power conversion efficiency (PCE) of 27.22% (certified maximum power point tracking (MPPT) efficiency of 27.18%) and 21.4-cm2 mini-modules with a PCE of 23.49%. Moreover, the devices exhibited long-term operational stability, retaining 98.7% of their initial efficiency after 1,200 h of continuous operation under the ISOS-L-1I protocol. Crucially, the automated platform achieved an efficiency reproducibility nearly five times that of manual fabrication. This work establishes an automated closed-loop system that synergizes ML-powered discovery with the high-fidelity data from automated manufacturing, setting a benchmark for autonomous discovery and manufacturing in photovoltaics and materials.
This is a preview of subscription content, access via your institution
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 51 print issues and online access
$199.00 per year
only $3.90 per issue
Buy this article
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
All data generated or analysed during this study are included in this published article and its supplementary information files. The datasets used in this study are also publicly available on GitHub (https://github.com/ShuaihuaLu/PVK_Passivation_ML) and have been permanently archived in Zenodo (https://doi.org/10.5281/zenodo.18803626)46.
The custom code used to reproduce the plots shown in the ML section of the manuscript is publicly available on GitHub (https://github.com/ShuaihuaLu/PVK_Passivation_ML). The exact version of the code used to generate the results in this paper has been deposited in Zenodo and can be accessed at https://doi.org/10.5281/zenodo.18803626 (ref. 46).
Hering, A. R., Sutter-Fella, C. M. & Leite, M. S. An AI-accelerated pathway for reproducible and stable halide perovskites. Chem. Soc. Rev. 54, 10397–10426 (2025).
Article CAS PubMed Google Scholar
Wang, Y. et al. Hybrid learning enables reproducible >24% efficiency in autonomously fabricated perovskites solar cells. Adv. Energy Mater. 16, e04340 (2026).
Article CAS Google Scholar
MacLeod, B. P. et al. Self-driving laboratory for accelerated discovery of thin-film materials. Sci. Adv. 6, eaaz8867 (2020).
Article ADS CAS PubMed PubMed Central Google Scholar
Li, Z. et al. Stabilized hole-selective layer for high-performance inverted p-i-n perovskite solar cells. Science 382, 284–289 (2023).
Article ADS CAS PubMed Google Scholar
Green, M. A. et al. Solar cell efficiency tables (version 66). Prog. Photovolt. Res. Appl. 33, 795–810 (2025).
Article Google Scholar
Li, B. et al. Closed-loop manufacturing for sustainable perovskite photovoltaics. Nat. Rev. Mater. 11, 10–25 (2026).
Article Google Scholar
Abdi-Jalebi, M. et al. Maximizing and stabilizing luminescence from halide perovskites with potassium passivation. Nature 555, 497–501 (2018).
Article ADS CAS PubMed Google Scholar
Gao, D. et al. High-efficiency perovskite solar cells enabled by suppressing intermolecular aggregation in hole-selective contacts. Nat. Photon. 19, 1070–1077 (2025).
Article ADS CAS Google Scholar
Zhang, Z. et al. Rationalization of passivation strategies toward high-performance perovskite solar cells. Chem. Soc. Rev. 52, 163–195 (2023).
Article CAS PubMed Google Scholar
Zhang, C. et al. Exploring the potential and hurdles of perovskite solar cells with p-i-n structure. ACS Nano 18, 32299–32314 (2024).
Article CAS PubMed Google Scholar
Yu, X. et al. Stabilization strategies of buried interface for efficient SAM-based inverted perovskite solar cells. Angew. Chem. Int. Ed. 64, e202419608 (2025).
Article CAS Google Scholar
Li, Z. et al. Scalable fabrication of perovskite solar cells. Nat. Rev. Mater. 3, 18017 (2018).
Article ADS CAS Google Scholar
Rong, Y. et al. Challenges for commercializing perovskite solar cells. Science 361, eaat8235 (2018).
Article PubMed Google Scholar
Ashworth, C. Reproducible, high-performance perovskite solar cells. Nat. Rev. Mater. 6, 293–293 (2021).
Article CAS Google Scholar
Xu, J. et al. Anion optimization for bifunctional surface passivation in perovskite solar cells. Nat. Mater. 22, 1507–1514 (2023).
Article CAS PubMed Google Scholar
Tabor, D. P. et al. Accelerating the discovery of materials for clean energy in the era of smart automation. Nat. Rev. Mater. 3, 5–20 (2018).
Article CAS Google Scholar
Peng, J. et al. Human- and machine-centred designs of molecules and materials for sustainability and decarbonization. Nat. Rev. Mater. 7, 991–1009 (2022).
Article Google Scholar
Gregoire, J. M. et al. Combinatorial synthesis for AI-driven materials discovery. Nat. Synth. 2, 493–504 (2023).
Article CAS Google Scholar
Hippalgaonkar, K. et al. Knowledge-integrated machine learning for materials: lessons from gameplaying and robotics. Nat. Rev. Mater. 8, 241–260 (2023).
Article Google Scholar
Lu, S. et al. Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning. Nat. Commun. 9, 3405 (2018).
Article ADS PubMed PubMed Central Google Scholar
Rao, Z. et al. Machine learning–enabled high-entropy alloy discovery. Science 378, 78–85 (2022).
Article ADS CAS PubMed Google Scholar
Szymanski, N. J. et al. An autonomous laboratory for the accelerated synthesis of novel materials. Nature 624, 86–91 (2023).
Article ADS CAS PubMed PubMed Central Google Scholar
Wu, J. et al. Inverse design workflow discovers hole-transport materials tailored for perovskite solar cells. Science 386, 1256–1264 (2024).
Article ADS CAS PubMed Google Scholar
Li, Z. et al. Organometallic-functionalized interfaces for highly efficient inverted perovskite solar cells. Science 376, 416–420 (2022).
Article ADS CAS PubMed Google Scholar
Li, B. et al. Highly efficient and scalable p-i-n perovskite solar cells enabled by poly-metallocene interfaces. J. Am. Chem. Soc. 146, 13391–13398 (2024).
Article ADS CAS PubMed PubMed Central Google Scholar
Gao, D. et al. Long-term stability in perovskite solar cells through atomic layer deposition of tin oxide. Science 386, 187–192 (2024).
Article ADS CAS PubMed Google Scholar
Minh, D. N. et al. The reactive nature of formamidinium: Amine passivation induces heterostructure formation in inverted perovskite cells. Joule 9, 102055 (2025).
Article Google Scholar
Li, B. et al. Fundamental understanding of stability for halide perovskite photovoltaics: the importance of interfaces. Chem. 10, 35–47 (2024).
Article CAS Google Scholar
Zhang, J. et al. Autonomous optimization of air-processed perovskite solar cell in a multidimensional parameter space. Adv. Energy Mater. 15, 2404957 (2025).
Article CAS Google Scholar
Zhang, J. et al. Advancing perovskite photovoltaic technology through machine learning-driven automation. InfoMat 7, e70005 (2025).
Article CAS Google Scholar
RDKit: open-source cheminformatics software. https://www.rdkit.org.
Zhang, H. et al. Tailoring passivators for highly efficient and stable perovskite solar cells. Nat. Rev. Chem. 7, 632–652 (2023).
Article CAS PubMed Google Scholar
Shields, B. J. et al. Bayesian reaction optimization as a tool for chemical synthesis. Nature 590, 89–96 (2021).
Article ADS CAS PubMed Google Scholar
Wang, Y. et al. NEXTorch: a design and Bayesian optimization toolkit for chemical sciences and engineering. J. Chem. Inf. Model. 61, 5312–5319 (2021).
Article CAS PubMed Google Scholar
Ouyang, R. et al. SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates. Phys. Rev. Mater. 2, 083802 (2018).
Article CAS Google Scholar
Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2, 56–67 (2020).
Article PubMed PubMed Central Google Scholar
Duan, T. et al. NGBoost: natural gradient boosting for probabilistic prediction. Preprint at https://arxiv.org/abs/1910.03225 (2019).
Azam, M. et al. Tailoring pyridine bridged chalcogen-concave molecules for defects passivation enables efficient and stable perovskite solar cells. Nat. Commun. 16, 602 (2025).
Article ADS CAS PubMed PubMed Central Google Scholar
Yang, L. et al. Suppressing halide segregation via pyridine-derivative isomers enables efficient 1.68 eV bandgap perovskite solar cells. Adv. Mater. 36, 2311923 (2024).
Article CAS Google Scholar
Ma, D. et al. An effective strategy of combining surface passivation and secondary grain growth for highly efficient and stable perovskite solar cells. Small 17, 2100678 (2021).
Article CAS Google Scholar
Frohna, K. et al. The impact of interfacial quality and nanoscale performance disorder on the stability of alloyed perovskite solar cells. Nat. Energy 10, 66–76 (2025).
Article ADS CAS PubMed Google Scholar
Cacovich, S. et al. Imaging and quantifying non-radiative losses at 23% efficient inverted perovskite solar cells interfaces. Nat. Commun. 13, 2868 (2022).
Article ADS CAS PubMed PubMed Central Google Scholar
Olive, R. D. J. et al. Understanding and suppressing non-radiative losses in methylammonium-free wide-bandgap perovskite solar cells. Energy Environ. Sci. 15, 714–726 (2022).
Article Google Scholar
Wolff, C. M. et al. Nonradiative recombination in perovskite solar cells: the role of interfaces. Adv. Mater. 31, 1902762 (2019).
Article CAS Google Scholar
Wagner, L. et al. Revealing fundamentals of charge extraction in photovoltaic devices through potentiostatic photoluminescence imaging. Matter 5, 2352–2364 (2022).
Article CAS Google Scholar
Lu, S. ShuaihuaLu/PVK_Passivation_ML: PVK_Passivation_ML. Zenodo https://doi.org/10.5281/zenodo.18803626 (2026).
Download references
This work was supported by the National Natural Science Foundation of China (52322318), Research Grants Council of Hong Kong grants (RFS2526-1S02, R1001-24F, C1055-23G, CRS_CityU104/24, 11308125, N_CityU102/23, 11306521, 11300124, C4005-22Y), Innovation and Technology Fund (ITS/147/22FP, MHP/079/23), the Science Technology and Innovation Committee of Shenzhen Municipality (JCYJ20220818101018038) and National Key Research and Development Program of China (no. 2023YFB3809700). R.M. acknowledges a studentship part-funded by the Engineering and Physical Sciences Research Council (EPSRC) as part of its Co-operative Awards in Science and Engineering (CASE Awards). S.D.S. acknowledges the Royal Society and Tata Group (grant nos. UF150033, URFR221026). M.S. acknowledges financial support from the Chinese University of Hong Kong (CUHK) through the Vice-Chancellor Early Career Professorship Scheme, the Research Grants Council (RGC) under the NSCF/RGC Joint Research Scheme (N_CUHK414/24) and the Innovation and Technology Commission (ITC) through the ITF Seed Fund (ITS/239/23). The work described in this paper was conducted in part by D.G. and S.L., Jockey Club Global STEM Postdoctoral Fellowship supported by the Hong Kong Jockey Club Charities Trust.
Xianglang Sun (孙祥浪)
Present address: Hubei Key Laboratory of Material Chemistry and Service Failure, Key Laboratory for Material Chemistry of Energy Conversion and Storage, Ministry of Education, School of Chemistry and Chemical Engineering, Huazhong University of Science and Technology, Wuhan, People’s Republic of China
These authors contributed equally: Danpeng Gao, Shuaihua Lu, Chunlei Zhang, Ning Wang, Zexin Yu, Xianglang Sun
Department of Chemistry, City University of Hong Kong, Kowloon, Hong Kong
Danpeng Gao (高丹鹏), Chunlei Zhang (张春雷), Ning Wang (王宁), Zexin Yu (余泽鑫), Xianglang Sun (孙祥浪), Francesco Vanin, Liangchen Qian (钱良辰), Bo Li (李博) & Zonglong Zhu (朱宗龙)
Department of Materials Science and Engineering, City University of Hong Kong, Kowloon, Hong Kong
Shuaihua Lu (陆帅华), Nan Li (李楠) & Xiao Cheng Zeng (曾晓成)
Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, UK
Rebecca Martin & Samuel D. Stranks
Department of Chemistry, Imperial College London, London, UK
Francesco Vanin, Nicholas Long & Nicola Gasparini
Institute of Materials for Electronics and Energy Technology (i-MEET), Department of Materials Science and Engineering, Friedrich-Alexander University (FAU) of Erlangen–Nürnberg, Erlangen, Germany
Larry Lüer & Christoph Joseph Brabec
School of Materials Science and Engineering, Central South University, Changsha, People’s Republic of China
Bo Li (李博)
Electronic Engineering Department, The Chinese University of Hong Kong, New Territories, Hong Kong
Martin Stolterfoht
Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong
Junhui Hou (侯军辉)
Department of Applied Physics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong
Jun Yin (殷骏)
Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong
Yen-Hung Lin (林彥宏)
Department of Chemistry, The Hong Kong University of Science and Technology, Kowloon, Hong Kong
Haipeng Lu (吕海鹏)
Helmholtz-Institute Erlangen-Nürnberg for Renewable Energy (HI ERN), Forschungszentrum Jülich, Erlangen, Germany
Christoph Joseph Brabec
Energy Campus Nürnberg (EnCN), Nürnberg, Germany
Christoph Joseph Brabec
Institute of Energy Materials and Devices: Photovoltaics (IMD-3), Forschungszentrum Jülich, Jülich, Germany
Christoph Joseph Brabec
Hong Kong Institute for Clean Energy, City University of Hong Kong, Kowloon, Hong Kong
Zonglong Zhu (朱宗龙)
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
PubMed Google Scholar
D.G., S.L., C.Z., N.W., Z.Y. and X.S. contributed equally to this work. Z.Z. conceived the ideas and supervised the research. D.G., S.L., C.Z., N.W. and Z.Y. designed the project and experiment. D.G. fabricated the devices and conducted characterizations. S.L., supervised by X.C.Z., conducted the DFT calculations and constructed the ML algorithm. N.W., C.Z. and D.G. built the automated fabrication platform. X.S. synthesized the molecule. C.Z., F.V., R.M. and L.Q. conducted device characterizations. N. Long, L.L., B.L., M.S., J.H., Y.-H.L., J.Y., H.L., N. Li, N.G., X.C.Z. and S.D.S. analysed the data. C.J.B. engaged in project discussions and offered constructive feedback. D.G., S.L., B.L., C.Z., N.W., Z.Y., X.C.Z. and Z.Z. drafted and finalized the paper. All of the authors contributed to the manuscript revision.
Correspondence to Samuel D. Stranks, Xiao Cheng Zeng (曾晓成) or Zonglong Zhu (朱宗龙).
S.D.S. is a co-founder of Swift Solar, Inc. R.M. has a studentship part-funded by Swift Solar, Inc. The other authors declare no competing interests.
Nature thanks Jesper Jacobsson and Kai Wang for their contribution to the peer review of this work. Peer reviewer reports are available.
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The file includes: Supplementary Notes 1–8, Supplementary Figs. 1–66, Supplementary Tables 1–16 and Supplementary References.
Source Data for Supplementary Figs. 4–23.
Demonstration of the automated manufacturing platform for PSC processing. This video demonstrates the end-to-end, continuous manufacturing process of PSCs on an automated platform, encompassing thin-film fabrication, electrode thermal evaporation and device performance testing. The specific steps are labelled in the top-left corner of the video as follows: (1) Perovskite solution intake: automated positioning of pipette A and aspiration of the perovskite precursor solution. (2) Antisolvent intake: automated positioning of pipette B and aspiration of the antisolvent (CB). (3) Spin coating: robotic gripper handling the substrate and the subsequent automated dispensing of the perovskite solution. (4) Antisolvent dropping: precise, automated dispensing of the antisolvent during the spin-coating process. (5) Film annealing: robotic gripper transferring the fabricated thin film to a hotplate for thermal annealing. (6) Edge trimming: automated mechanical cutter performing the P2 scribing process on the device. (7) Thermal evaporation: automated transfer and loading of samples into the thermal evaporation chamber for electrode deposition. (8) Performance testing: automated picking and transferring of the devices to the testing station, followed by automated data acquisition.
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Reprints and permissions
Gao, D., Lu, S., Zhang, C. et al. Autonomous closed-loop framework for reproducible perovskite solar cells. Nature (2026). https://doi.org/10.1038/s41586-026-10482-y
Download citation
Received:
Accepted:
Published:
Version of record:
DOI: https://doi.org/10.1038/s41586-026-10482-y
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
Advertisement
Nature (Nature)
ISSN 1476-4687 (online)
ISSN 0028-0836 (print)
© 2026 Springer Nature Limited
Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.
