Touati Soundous, Benghia Ali, Hebboul Zoulikha, Lefkaier Ibn Khaldoun, Kanoun Mohammed Benali, Goumri-Said Souraya
Laboratoire de Physique des Matériaux, Université Amar Telidji de Laghouat, BP 37G, Laghouat 03000, Algeria.
Laboratory of Applied Sciences and Didactic, Higher Normal School of Laghouat, Laghouat 03000, Algeria.
ACS Omega. 2024 Nov 18;9(48):47519-47531. doi: 10.1021/acsomega.4c06139. eCollection 2024 Dec 3.
Recently, ABX materials have garnered significant attention due to their diverse applications in photovoltaics, catalysis, and optoelectronics as well as their remarkable efficiency in energy conversion. However, progress has been somewhat slow due to the high expenses of the experiment or the time-consuming density functional theory (DFT) calculation. In this study, we utilized the extreme gradient boosting (XGBoost) algorithm to facilitate the discovery and characterization of ABX compounds based on vast data sets generated by DFT calculations. While the XGBoost algorithm provides a powerful tool for accelerating the discovery of ABX compounds, it is crucial to acknowledge that different DFT approximation levels can significantly impact the predicted band gaps, potentially introducing discrepancies when compared with experimental values. In the first step, we predict the space group of 13947 oxides and halides using the Open Quantum Materials Database and elemental features. Our analysis yields classification accuracies ranging from 82.39% to 99.14% across these materials. Following this, XGBoost regression algorithms are employed to interrogate the data set, enabling predictions of volume (achieving an optimal accuracy of 98.41%, with a mean absolute error (MAE) of 2.395 Å and a root-mean-square error (RMSE) of 4.416 Å), formation energy (an optimal accuracy of 97.36%, with an MAE of 0.075 eV/atom and an RMSE of 0.132 eV/atom), and band gap energy (an optimal accuracy of 87.00%, an MAE of 0.391 eV, and an RMSE of 0.574 eV). Finally, these prediction models are employed to identify the possible space groups for each of the 1252 new ABX formulas. Then, we predict the volume, the formation energy, and the band gap energy for each candidate space group. Through these predictive models, machine learning accelerates the exploration of new materials with enhanced performance and functionality.
近年来，ABX材料因其在光伏、催化和光电子学等领域的多样应用以及在能量转换方面的卓越效率而备受关注。然而，由于实验成本高昂或耗时的密度泛函理论（DFT）计算，进展一直较为缓慢。在本研究中，我们利用极端梯度提升（XGBoost）算法，基于DFT计算生成的大量数据集，促进ABX化合物的发现和表征。虽然XGBoost算法为加速ABX化合物的发现提供了强大工具，但必须认识到，不同的DFT近似水平会显著影响预测的带隙，与实验值相比可能会引入差异。第一步，我们使用开放量子材料数据库和元素特征预测13947种氧化物和卤化物的空间群。我们的分析在这些材料中得出的分类准确率在82.39%至99.14%之间。在此之后，采用XGBoost回归算法对数据集进行分析，从而能够预测体积（最佳准确率为98.41%，平均绝对误差（MAE）为2.395 Å，均方根误差（RMSE）为4.416 Å）、形成能（最佳准确率为97.36%，MAE为0.075 eV/原子，RMSE为0.132 eV/原子）和带隙能量（最佳准确率为87.00%，MAE为0.391 eV，RMSE为0.574 eV）。最后，这些预测模型用于确定1252个新ABX配方各自可能的空间群。然后，我们预测每个候选空间群的体积、形成能和带隙能量。通过这些预测模型，机器学习加速了对具有增强性能和功能的新材料的探索。
