As an indicator of the optical characteristics of perovskite materials, the band gap is a crucial parameter that impacts the functionality of a wide range of optoelectronic devices. Obtaining the band gap of a material via a labor-intensive, time-consuming, and inefficient high-throughput calculation based on first principles is possible. However, it does not yield the most accurate results. Machine learning techniques emerge as a viable and effective substitute for conventional approaches in band gap prediction. This paper collected 201 pieces of data through the literature and open-source databases. By separating the features related to bits A, B, and X, a dataset of 1208 pieces of data containing 30 feature descriptors was established. The dataset underwent preprocessing, and the Pearson correlation coefficient method was employed to eliminate non-essential features as a subset of features. The band gap was predicted using the GBR algorithm, the random forest algorithm, the LightGBM algorithm, and the XGBoost algorithm, in that order, to construct a prediction model for organic–inorganic hybrid perovskites. The outcomes demonstrate that the XGBoost algorithm yielded an MAE value of 0.0901, an MSE value of 0.0173, and an R² value of 0.991310. These values suggest that, compared to the other two models, the XGBoost model exhibits the lowest prediction error, suggesting that the input features may better fit the prediction model. Finally, analysis of the XGBoost-based prediction model’s prediction results using the SHAP model interpretation method reveals that the occupancy rate of the A-position ion has the greatest impact on the prediction of the band gap and has an A-negative correlation with the prediction results of the band gap. The findings provide valuable insights into the relationship between the prediction of band gaps and significant characteristics of organic–inorganic hybrid perovskites.

The search for stable, lead-free perovskite materials is critical for developing efficient and environmentally friendly energy solutions. In this study, machine learning methods were applied to predict the bandgap and formation energy of double perovskites, aiming to identify promising photovoltaic candidates. A dataset of 1053 double perovskites was extracted from the Materials Project database, with 50 feature descriptors generated. Feature selection was carried out using Pearson correlation and mRMR methods, and 23 key features for bandgap prediction and 18 key features for formation energy prediction were determined. Four algorithms, including gradient-boosting regression (GBR), random forest regression (RFR), LightGBM, and XGBoost, were evaluated, with XGBoost demonstrating the best performance (R² = 0.934 for bandgap, R² = 0.959 for formation energy; MAE = 0.211 eV and 0.013 eV/atom). The SHAP (Shapley Additive Explanations) analysis revealed that the X-site electron affinity positively influences the bandgap, while the B″-site first and third ionization energies exhibit strong negative effects. Formation energy is primarily governed by the X-site first ionization energy and the electronegativities of the B′ and B″ sites. To identify optimal photovoltaic materials, 4573 charge-neutral double perovskites were generated via elemental substitution, with 2054 structurally stable candidates selected using tolerance and octahedral factors. The XGBoost model predicted bandgaps, yielding 99 lead-free double perovskites with ideal bandgaps (1.3~1.4 eV). Among them, four candidates are known compounds according to the Materials Project database, namely Ca₂NbFeO₆, Ca₂FeTaO₆, La₂CrFeO₆, and Cs₂YAgBr₆, while the remaining 95 candidate perovskites are unknown compounds. Notably, X-site elements (Se, S, O, C) and B″-site elements (Pd, Ir, Fe, Ta, Pt, Cu) favor narrow bandgap formation. These findings provide valuable guidance for designing high-performance, non-toxic photovoltaic materials.

As an important photovoltaic material, organic–inorganic hybrid perovskites have attracted much attention in the field of solar cells, but their instability is one of the main challenges limiting their commercial application. However, the search for stable perovskites among the thousands of perovskite materials still faces great challenges. In this work, the energy above the convex hull values of organic–inorganic hybrid perovskites was predicted based on four different machine learning algorithms, namely random forest regression (RFR), support vector machine regression (SVR), XGBoost regression, and LightGBM regression, to study the thermodynamic phase stability of organic–inorganic hybrid perovskites. The results show that the LightGBM algorithm has a low prediction error and can effectively capture the key features related to the thermodynamic phase stability of organic–inorganic hybrid perovskites. Meanwhile, the Shapley Additive Explanation (SHAP) method was used to analyze the prediction results based on the LightGBM algorithm. The third ionization energy of the B element is the most critical feature related to the thermodynamic phase stability, and the second key feature is the electron affinity of ions at the X site, which are significantly negatively correlated with the predicted values of energy above the convex hull (E_hull). In the screening of organic–inorganic perovskites with high stability, the third ionization energy of the B element and the electron affinity of ions at the X site is a worthy priority. The results of this study can help us to understand the correlation between the thermodynamic phase stability of organic–inorganic hybrid perovskites and the key features, which can assist with the rapid discovery of highly stable perovskite materials.