Machine Learning-Enhanced Design of Lead-Free Halide Perovskite Materials Using Density Functional Theory

Aug 3, 2026

The study advances environmentally sustainable lead-free halide perovskite solar cells by proposing a machine learning workflow for predicting promising halide perovskite compositions for photovoltaic use. Seven new candidate materials are generated and first screened through machine learning, then validated using density functional theory calculations. Among them, CsMnCl4 exhibits a 1.37 eV bandgap within the Shockley–Queisser limit, supporting photovoltaic applicability. By integrating ML and DFT, the approach enables more effective and thorough material discovery and design than conventional trial-and-error routes.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Introduction

Motivation for lead-free halide perovskites

Machine learning and DFT driven design strategy

Data-driven screening and validation

arXiv :2407 . 15573v1 [ cond-mat .mtrl-sci ] 22 Jul 2024 Machine Learning-Enhanced Design of Lead-Free Halide Perovskite Materials Using Density Functional Theory Upendra Kumar, 1, ∗ Hyeon Woo Kim, 1, 2, ∗ Gyanendra Kumar Maurya,3 Bincy Babu Raj, 1, 4 Sobhit Singh,5, 6 Ajay Kumar Kushwaha,7 Sung Beom Cho,8,† and Hyunseok Ko 1,‡ 1 Division of Carbon Neutrality and Digitalization, Korea Institute of Ceramic Engineering and Technology (KICET), Jinju 52851, South Korea. 2 Department of Materials Science and Engineering, Hanyang University, Seoul 04763, South Korea. 3 Department of Physics, GLA University, Mathura 281406, India. 4 School of Material Science and Engineering, Pusan National University, 2 Busandaehak-ro 63beon-gil, Geumjeong-gu, Busan 46241, South Korea. 5 Department of Mechanical Engineering at the University of Rochester, New York 14611, United States. 6 Materials Science Program, University of Rochester, Rochester, New York 14627, USA 7 Department of Metallurgy Engineering and Materials Science, Indian Institute of Technology Indore, Khandwa Road, Simrol, Indore 453552, India. 8 Department of Energy Systems Research, Ajou University, Suwon 16499, South Korea. The investigation of emerging non-toxic perovskite materials has been undertaken to advance the fabrication of environmentally sustainable lead-free perovskite solar cells. This study introduces a machine learning methodology aimed at predicting innovative halide perovskite materials that hold promise for use in photovoltaic applications. The seven newly predicted materials are as follows: CsMnCl4, Rb 3Mn2 Cl9, Rb 4MnCl6, Rb 3MnCl5, RbMn 2Cl7, RbMn 4Cl9, and CsIn 2Cl7. The predicted compounds are first screened using a machine learning approach, and their validity is subsequently verified through density functional theory calculations. CsMnCl4 is notable among them, displaying a bandgap of 1.37 eV, falling within the Shockley-Queisser limit, making it suitable for photovoltaic applications. Through the integration of machine learning and density functional theory, this study presents a methodology that is more effective and thorough for the discovery and design of materials. Keywords: Halide Perovskite Materials; Machine Learning; Density Functional Theory; Photovoltaic application I. INTRODUCTION Halide perovskites have emerged as promising candidates for revolutionizing the landscape of solar cell technology [1] . Characterized by their unique crystalline structure and exceptional optoelectronic properties, halide perovskites offer unparalleled potential for efficient and cost-effective solar energy conversion. Their tunable bandgap [2], high absorption coefficients [3], and long carrier diffusion lengths [4] make them highly attractive for photovoltaic applications. Moreover, their facile synthesis methods [5] and compatibility with flexible substrates [6] open avenues for scalable and versatile solar cell designs. Beyond their application in solar cells, halide perovskite materials hold immense promise for a wide range of electronic devices [7] . However, concerns over the toxicity of lead-based halide perovskites have prompted significant research efforts towards developing lead-free alternatives. Lead-free perovskite halide materials [8] represent a promising avenue in the quest for sustainable and environmentally friendly solar energy solutions. These materials offer potential for high-performance solar cells [9] while mitigating environmental and health risks. Research efforts have focused on exploring a diverse range of lead-free perovskite compositions, including tin, bismuth, and other metal halides [10], which exhibit encouraging optoelectronic properties and demonstrate potential for efficient photovoltaic applications [11] . By addressing the need for lead-free halide designs, researchers aim to unlock the full potential of halide perovskite materials while ensuring environmental sustainability and human health

FAQs

What is the main goal of the study?

To design and predict lead-free halide perovskite materials for environmentally sustainable photovoltaic applications.

How are the candidate materials generated and verified?

A machine learning approach screens seven predicted compositions, and density functional theory calculations are used to verify their validity.

Which predicted compound shows notable photovoltaic relevance and why?

CsMnCl4 stands out with a 1.37 eV bandgap that falls within the Shockley–Queisser limit, making it suitable for photovoltaic use.

Aug 3, 2026

Upload by River Wang