Page 100 - Read Online

Page 24 of 31 Shu et al. J. Mater. Inf. 2025, 5, 36 https://dx.doi.org/10.20517/jmi.2025.13

Table 1. A year-by-year comparison of ML studies, highlighting the types of materials investigated, the ML models employed, and
the key results
Year Material type ML models Key results Ref.
2019 Perovskite oxides/halides SISSO τ factor 92% stability prediction accuracy [135]
2019 2D OOHs GBR Several candidates with excellent bandgap/mobility have [144]
been identified
2020 Cd-based RFR Accurately predict impurity formation enthalpy and [139]
chalcogenides charge transition levels
2020 2D inorganic crystal GBC Developed HT and ML methods to identify 2DPV [126]
candidate materials
2021 Spinel XGBoost Successfully screened out 8 spinels [146]
2022 Perovskite GCNN A model is proposed to evaluate the synthesizability of [136]
perovskites
2022 Hybrid heterostructured semiconductors GBRT 96 stable HHSs were found [148]
2022 DHOIPs Δ-GBR 19 promising DHOIPs were screened [149]
2022 Perovskite BO Achieved 18.5% power conversion efficiency [140]
2023 2D hybrid Organic-inorganic lead-halide XGBR Develop a 2D HOIPs exploration platform [150]
perovskites
2023 All-inorganic lead-free perovskites Multi-component neural 34 lead-free AABBX X identified [145]
3 3
network
2023 2D hybrid perovskites Bagging classifier Accurate classification of type I/II band alignment [129]
2024 Multi-element MHPs CGCNN Achieved high prediction accuracy in stability and band [128]
gap
2024 Perovskites SISSO Developing a universal ML descriptor [127]
2024 Haeckelite structures RFR and CNN Identified 13 stable Haeckelite configurations with ideal [147]
band gaps
2024 Lead-free VOHPs Unsupervised ML Revealed the influence of A-site cations on carrier [130]
lifetimes
ML: Machine learning; SISSO: sure independence screening and sparsifying operator; 2D: two-dimensional; OOHs: octahedral oxyhalides; GBR:
gradient boosting regressor; RFR: random forest regressor; GBC: gradient boosting classifier; HT: high-throughput; PV: photovoltaic; GCNN: graph
convolutional neural network; GBRT: gradient boosting regression trees; HHSs: hybrid heterostructure semiconductors; DHOIPs: double hybrid
organic-inorganic perovskites; BO: Bayesian Optimization; XGBR: XGBoost regressor; HOIPs: hybrid organic-inorganic perovskites; MHPs: metal
halide perovskites; CGCNN: crystal graph convolutional neural network; CNN: convolutional neural network; VOHPs: vacancy-ordered halide
perovskites.

efficiently exploring large compositional spaces and optimizing for specific properties. These features are
particularly advantageous for identifying high-performance candidate materials with ideal energy band
alignment and environmental stability. Future advances may include combining ML predictions with
experimental feedback to enable more precise tuning to optimize material properties.

Finally, while ML models excel at identifying statistical correlations within data, their lack of direct physical
interpretation can limit their ability to predict mechanisms accurately. Unlike traditional physics-based
models, ML models are not inherently bound by the laws of physics, which restricts their applicability in
certain contexts. Combining ML techniques with first-principles methods or physics-driven models could
enhance the predictive accuracy and physical validity of ML outcomes, fostering a balanced approach that
leverages the strengths of both paradigms.

Looking ahead, the integration of AI and ML techniques has revolutionized materials research. The shift
from traditional experimental approaches to HT screening and ML-driven prediction has allowed
researchers to rapidly assess vast chemical and structural spaces, enabling the systematic exploration of key
parameters that influence optoelectronic properties. AI-driven ML methods have proven particularly
effective in predicting material properties . For instance, DeepMind of Google developed GNoME, a
[151]