Is machine learning redefining the perovskite solar cells

Abstract Development of novel materials with desirable properties remains at the forefront of modern scientific research. Machine learning (ML), a branch of artificial intelligence, has recently emerged as a powerful technology in optoelectronic devices for the prediction of various properties and rational design of materials. Metal halide perovskites (MHPs) have been at the centre of attraction owing to their outstanding photophysical properties and rapid development in solar cell application. Therefore, the application of ML in the field of MHPs is also getting much attention to optimize the fabrication process and reduce the cost of processing. Here, we comprehensively reviewed different applications of ML in the designing of both MHP absorber layers as well as complete perovskite solar cells (PSCs). At the end, the challenges of ML along with the possible future direction of research are discussed. We believe that this review becomes an indispensable roadmap for optimizing materials composition and predicting design strategies in the field of perovskite technology in the future.

[1]  I. Castelli,et al.  Machine-learning structural and electronic properties of metal halide perovskites using a hierarchical convolutional neural network , 2020, npj Computational Materials.

[2]  V. Sidey.  A simplified empirical model for predicting the lattice parameters for the cubic perovskite-related inorganic A2BX6 halides , 2019, Journal of Physics and Chemistry of Solids.

[3]  Liang Ma,et al.  Earth-Abundant Nontoxic Titanium(IV)-based Vacancy-Ordered Double Perovskite Halides with Tunable 1.0 to 1.8 eV Bandgaps for Photovoltaic Applications , 2018 .

[4]  Sergei V. Kalinin,et al.  Chemical Robotics Enabled Exploration of Stability in Multicomponent Lead Halide Perovskites via Machine Learning , 2020 .

[5]  Çağla Odabaşı,et al.  Performance analysis of perovskite solar cells in 2013–2018 using machine-learning tools , 2019, Nano Energy.

[6]  Jinlan Wang,et al.  Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning , 2018, Nature Communications.

[7]  O. Voznyy,et al.  Machine Learning Accelerates Discovery of Optimal Colloidal Quantum Dot Synthesis. , 2019, ACS nano.

[8]  A. Kalam,et al.  Mesoscopic TiO2/Nb2O5 Electron Transfer Layer for Efficient and Stable Perovskite Solar Cells , 2021, Advanced Materials Interfaces.

[9]  Kristin A. Persson,et al.  Commentary: The Materials Project: A materials genome approach to accelerating materials innovation , 2013 .

[10]  M. Chan,et al.  Comprehensive Computational Study of Partial Lead Substitution in Methylammonium Lead Bromide , 2019, Chemistry of Materials.

[11]  S. Zakeeruddin,et al.  Elucidation of Charge Recombination and Accumulation Mechanism in Mixed Perovskite Solar Cells , 2018, The Journal of Physical Chemistry C.

[12]  Gerbrand Ceder,et al.  Rapid Photovoltaic Device Characterization through Bayesian Parameter Estimation , 2017 .

[13]  David B. Mitzi,et al.  Templating and structural engineering in organic–inorganic perovskites , 2001 .

[14]  E. Sargent,et al.  Machine-Learning-Accelerated Perovskite Crystallization , 2020, Matter.

[15]  Ruipeng Li,et al.  How machine learning can help select capping layers to suppress perovskite degradation , 2020, Nature Communications.

[16]  Mohammad Khaja Nazeeruddin,et al.  One-Year stable perovskite solar cells by 2D/3D interface engineering , 2017, Nature Communications.

[17]  Y. Qi,et al.  Highly stable and efficient all-inorganic lead-free perovskite solar cells with native-oxide passivation , 2019, Nature Communications.

[18]  Chiho Kim,et al.  Finding New Perovskite Halides via Machine Learning , 2016, Front. Mater..

[19]  Anders Hagfeldt,et al.  Cesium-containing triple cation perovskite solar cells: improved stability, reproducibility and high efficiency† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c5ee03874j Click here for additional data file. , 2016, Energy & environmental science.

[20]  Jie Jiang,et al.  Accelerated Discovery of Efficient Solar-cell Materials using Quantum and Machine-learning Methods. , 2019, Chemistry of materials : a publication of the American Chemical Society.

[21]  Muratahan Aykol,et al.  The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies , 2015 .

[22]  Yiying Wu,et al.  Machine Learning for Understanding Compatibility of Organic–Inorganic Hybrid Perovskites with Post-Treatment Amines , 2019, ACS Energy Letters.

[23]  Xin Li,et al.  Identifying and monitoring the development trends of emerging technologies using patent analysis and Twitter data mining: The case of perovskite solar cell technology , 2019, Technological Forecasting and Social Change.

[24]  Valter Maurino,et al.  Carbon Materials as Additives to WO3 for an Enhanced Conversion of Simulated Solar Light , 2016, Front. Mater..

[25]  Peter Moeck,et al.  Crystallography Open Database (COD): an open-access collection of crystal structures and platform for world-wide collaboration , 2011, Nucleic Acids Res..

[26]  Liang Ma,et al.  Lead-Free Mixed Tin and Germanium Perovskites for Photovoltaic Application. , 2017, Journal of the American Chemical Society.

[27]  Brian L. DeCost,et al.  Accelerated Development of Perovskite-Inspired Materials via High-Throughput Synthesis and Machine-Learning Diagnosis , 2018, Joule.

[28]  Dane Morgan,et al.  Materials Discovery of Stable and Nontoxic Halide Perovskite Materials for High‐Efficiency Solar Cells , 2019, Advanced Functional Materials.

[29]  Daniel A. Dalgo,et al.  A Clear, Strong, and Thermally Insulated Transparent Wood for Energy Efficient Windows , 2019, Advanced Functional Materials.

[30]  Xiaojie Xu,et al.  Machine Learning Lattice Constants for Cubic Perovskite Compounds , 2020 .

[31]  T. M. Dieb,et al.  Monte Carlo tree search for materials design and discovery , 2019, MRS Communications.

[32]  Nam-Gyu Park,et al.  Stability Issues on Perovskite Solar Cells , 2015 .

[33]  Miriam Rafailovich,et al.  Application of Machine Learning in Perovskite Solar Cell Crystal Size Distribution Analysis , 2019, MRS Advances.

[34]  A. Aspuru-Guzik,et al.  Self-driving laboratory for accelerated discovery of thin-film materials , 2019, Science Advances.

[35]  S. Zakeeruddin,et al.  Engineering of Perovskite Materials Based on Formamidinium and Cesium Hybridization for High-Efficiency Solar Cells , 2019, Chemistry of Materials.

[36]  Nam-Gyu Park,et al.  Perovskite solar cells: an emerging photovoltaic technology , 2015 .

[37]  P. Yadav,et al.  Effect of CsCl Additive on the Morphological and Optoelectronic Properties of Formamidinium Lead Iodide Perovskite , 2019, Solar RRL.

[38]  Beyza Yılmaz,et al.  Critical review of machine learning applications in perovskite solar research , 2021 .

[39]  C. Brabec,et al.  Discovery of temperature-induced stability reversal in perovskites using high-throughput robotic learning , 2021, Nature Communications.

[40]  M. Lei,et al.  Machine learning in materials science , 2019, InfoMat.

[41]  J. Berry,et al.  Advances in two-dimensional organic–inorganic hybrid perovskites , 2020, Energy & Environmental Science.

[42]  D. Solís-Ibarra,et al.  Two-Dimensional Halide Perovskites in Solar Cells: 2D or not 2D? , 2019, ChemSusChem.

[43]  S. Ong,et al.  New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships , 2016 .

[44]  Yang Yang,et al.  Addressing the stability issue of perovskite solar cells for commercial applications , 2018, Nature Communications.

[45]  Xionggang Lu,et al.  Formability of ABX3 (X = F, Cl, Br, I) halide perovskites. , 2008, Acta crystallographica. Section B, Structural science.

[46]  Sergei V. Kalinin,et al.  Exploration of Electrochemical Reactions at Organic–Inorganic Halide Perovskite Interfaces via Machine Learning in In Situ Time‐of‐Flight Secondary Ion Mass Spectrometry , 2020, Advanced Functional Materials.

[47]  David Cahen,et al.  Halide Perovskites: Is It All about the Interfaces? , 2018, Chemical reviews.

[48]  I. Bruno,et al.  Cambridge Structural Database , 2002 .

[49]  Oleg V. Prezhdo,et al.  Structural Deformation Controls Charge Losses in MAPbI3: Unsupervised Machine Learning of Nonadiabatic Molecular Dynamics , 2020 .

[50]  Hsin-An Chen,et al.  Fast and Accurate Artificial Neural Network Potential Model for MAPbI3 Perovskite Materials , 2019, ACS omega.

[51]  J. Kong,et al.  Surface Engineering of TiO2 ETL for Highly Efficient and Hysteresis‐Less Planar Perovskite Solar Cell (21.4%) with Enhanced Open‐Circuit Voltage and Stability , 2018, Advanced Energy Materials.

[52]  D. Rapaport,et al.  Molecular dynamics simulation: a tool for exploration and discovery using simple models , 2014, Journal of physics. Condensed matter : an Institute of Physics journal.

[53]  V. Bulović,et al.  Controllable Perovskite Crystallization via Antisolvent Technique Using Chloride Additives for Highly Efficient Planar Perovskite Solar Cells , 2019, Advanced Energy Materials.

[54]  Peter Lund,et al.  Critical analysis on the quality of stability studies of perovskite and dye solar cells , 2018 .

[55]  Qichen Xu,et al.  Thermodynamic Stability Landscape of Halide Double Perovskites via High‐Throughput Computing and Machine Learning , 2019, Advanced Functional Materials.

[56]  Raghvendra Mall,et al.  Exploring new approaches towards the formability of mixed-ion perovskites by DFT and machine learning. , 2019, Physical chemistry chemical physics : PCCP.

[57]  Raghvendra Mall,et al.  Machine Learning Accelerated Recovery of the Cubic Structure in Mixed-Cation Perovskite Thin Films , 2020 .

[58]  Jun Hee Lee,et al.  Pseudo-halide anion engineering for α-FAPbI3 perovskite solar cells , 2021, Nature.

[59]  Michael Saliba,et al.  Polyelemental, Multicomponent Perovskite Semiconductor Libraries through Combinatorial Screening , 2019, Proceedings of the International Conference on Perovskite Thin Film Photovoltaics and Perovskite Photonics and Optoelectronics.

[60]  B. Rai,et al.  Bulk and surface DFT investigations of inorganic halide perovskites screened using machine learning and materials property databases. , 2019, Physical chemistry chemical physics : PCCP.

[61]  Raghvendra Mall,et al.  Learn and Match Molecular Cations for Perovskites. , 2019, The journal of physical chemistry. A.

[62]  Kai Zhu,et al.  Towards stable and commercially available perovskite solar cells , 2016, Nature Energy.

[63]  Tugrul U. Daim,et al.  Forecasting technology trends using text mining of the gaps between science and technology: The case of perovskite solar cell technology , 2019, Technological Forecasting and Social Change.

[64]  Qichen Xu,et al.  Rationalizing Perovskite Data for Machine Learning and Materials Design. , 2018, The journal of physical chemistry letters.

[65]  Savitha Ramasamy,et al.  Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks , 2018, npj Computational Materials.

[66]  Li Xiang,et al.  Computational Screening of New Perovskite Materials Using Transfer Learning and Deep Learning , 2019, Applied Sciences.

[67]  Bo Qu,et al.  Machine learning (ML)-assisted optimization doping of KI in MAPbI3 solar cells , 2020, Rare Metals.

[68]  R. Yıldırım,et al.  Machine learning analysis on stability of perovskite solar cells , 2020 .

[69]  I. Kityk,et al.  Modeling of lattice constant and their relations with ionic radii and electronegativity of constituting ions of A2XY6 cubic crystals (A=K, Cs, Rb, Tl; X=tetravalent cation, Y=F, Cl, Br, I) , 2011 .

[70]  M. Saidaminov,et al.  Making and Breaking of Lead Halide Perovskites. , 2016, Accounts of chemical research.

[71]  T. Miyasaka,et al.  Halide Perovskite Photovoltaics: Background, Status, and Future Prospects. , 2019, Chemical reviews.

[72]  S. Trivedi,et al.  A review of aspects of additive engineering in perovskite solar cells , 2020 .

[73]  Xiaojie Xu,et al.  Machine learning lattice constants for cubic perovskiteA2XY6compounds , 2020 .

[74]  Wencong Lu,et al.  Machine learning for perovskite materials design and discovery , 2021, npj Computational Materials.

[75]  Kai Sundmacher,et al.  Big Data Creates New Opportunities for Materials Research: A Review on Methods and Applications of Machine Learning for Materials Design , 2019, Engineering.

[76]  Lei Zhang,et al.  Machine learning for halide perovskite materials , 2020 .

[77]  Raghvendra Mall,et al.  Importance of structural deformation features in the prediction of hybrid perovskite bandgaps , 2020 .

[78]  Antonio Abate,et al.  Perovskite Solar Cells Go Lead Free , 2017 .

[79]  S. Akin,et al.  Poly(N,N′‐bis‐4‐butylphenyl‐N,N′‐bisphenyl)benzidine‐Based Interfacial Passivation Strategy Promoting Efficiency and Operational Stability of Perovskite Solar Cells in Regular Architecture , 2020, Advanced materials.

[80]  Tianmin Wu,et al.  Global discovery of stable and non-toxic hybrid organic-inorganic perovskites for photovoltaic systems by combining machine learning method with first principle calculations , 2019 .

[81]  Garth J. Williams,et al.  Corrigendum: Diffraction data of core-shell nanoparticles from an X-ray free electron laser , 2017, Scientific Data.

[82]  Kwang S. Kim,et al.  Machine Learning for Predicting the Band Gaps of ABX3 Perovskites from Elemental Properties , 2020, The Journal of Physical Chemistry C.

[83]  R. Yıldırım,et al.  Assessment of Reproducibility, Hysteresis, and Stability Relations in Perovskite Solar Cells Using Machine Learning , 2020 .

[84]  Monica Lira-Cantu,et al.  Perovskite solar cells: Stability lies at interfaces , 2017, Nature Energy.

[85]  Giuseppe Gigli,et al.  MAPbI3-xClx Mixed Halide Perovskite for Hybrid Solar Cells: The Role of Chloride as Dopant on the Transport and Structural Properties , 2013 .

[86]  H. Hillhouse,et al.  Forecasting the Decay of Hybrid Perovskite Performance Using Optical Transmittance or Reflected Dark-Field Imaging , 2020, ACS Energy Letters.

[87]  D. Ma,et al.  Searching for stability at lower dimensions: current trends and future prospects of layered perovskite solar cells , 2019, Energy & Environmental Science.

[88]  S. Zakeeruddin,et al.  Synergistic Crystal and Interface Engineering for Efficient and Stable Perovskite Photovoltaics , 2018, Advanced Energy Materials.

[89]  Shunbo Hu,et al.  Electronic transport of organic-inorganic hybrid perovskites from first-principles and machine learning , 2019, Applied Physics Letters.

[90]  L. Jan Anton Koster,et al.  Identification of the dominant recombination process for perovskite solar cells based on machine learning , 2021 .

[91]  A. Gagliardi,et al.  Machine Learning Stability and Bandgaps of Lead‐Free Perovskites for Photovoltaics , 2019, Advanced Theory and Simulations.

[92]  Hongwei Zhu,et al.  Stabilization of highly efficient and stable phase-pure FAPbI3 Perovskite Solar Cells by Molecularly Tailored 2D-Overlayers. , 2020, Angewandte Chemie.

[93]  Qionghua Zhou,et al.  Rapid Discovery of Ferroelectric Photovoltaic Perovskites and Material Descriptors via Machine Learning , 2019, Small Methods.

[94]  Chao-Sung Lai,et al.  Element Code from Pseudopotential as Efficient Descriptors for a Machine Learning Model to Explore Potential Lead-Free Halide Perovskites. , 2020, The journal of physical chemistry letters.

[95]  G. R. Schleder,et al.  From DFT to machine learning: recent approaches to materials science–a review , 2019, Journal of Physics: Materials.

[96]  YunKyong Hyon,et al.  Identifying Pb-free perovskites for solar cells by machine learning , 2019, npj Computational Materials.

[97]  M. Kubát.  An Introduction to Machine Learning , 2017, Springer International Publishing.

[98]  Elizabeth M. Tennyson,et al.  Machine Learning for Perovskites' Reap-Rest-Recovery Cycle , 2019, Joule.

[99]  V. Berry,et al.  Cuboctahedral stability in Titanium halide perovskites via machine learning , 2020 .

[100]  Itsuki Miyazato,et al.  Searching for Hidden Perovskite Materials for Photovoltaic Systems by Combining Data Science and First Principle Calculations , 2018 .

[101]  Tsutomu Miyasaka,et al.  Organometal halide perovskites as visible-light sensitizers for photovoltaic cells. , 2009, Journal of the American Chemical Society.

[102]  Anders Hagfeldt,et al.  Interpretation and evolution of open-circuit voltage, recombination, ideality factor and subgap defect states during reversible light-soaking and irreversible degradation of perovskite solar cells , 2018 .

[103]  Mariette Hellenbrandt,et al.  The Inorganic Crystal Structure Database (ICSD)—Present and Future , 2004 .