Scholarlink

<p>Predicting the band gap of inorganic semiconductors is crucial for designing materials used in electronic and optoelectronic applications. This study employs a range of machine learning (ML) and deep learning (DL) algorithms i.e. Linear Regression, Random Forest, XGBoost, Artificial Neural Network (ANN), and Graph Neural Network (GNN) to predict band gaps using the expt_gap dataset from the Matminer library, which contains experimental band gap values for 6,354 inorganic semiconductors. Following rigorous preprocessing and extraction of composition-based descriptors via the Magpie featurizer, the models were evaluated using a unified fivefold cross-validation protocol applied consistently to all five model classes. The Random Forest model achieved the highest predictive accuracy with a Mean Absolute Error (MAE) of 0.2836&#xa0;eV, closely followed by the ANN (0.3321&#xa0;eV) and XGBoost (0.3575&#xa0;eV). These results significantly outperform the Linear Regression baseline (MAE: 0.5718&#xa0;eV) and demonstrate the effectiveness of non-linear ensemble and deep learning architectures in capturing the complex, multi-dimensional relationships between chemical composition and electronic properties. The competitive performance of the GNN (MAE: 0.3978&#xa0;eV) further highlights the potential of graph-based representations in materials informatics. These findings underscore the capacity of advanced ML and DL frameworks to accelerate materials discovery by providing accurate, scalable, and computationally efficient band gap predictions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting band gap from chemical composition: a comparative study of machine learning and deep learning models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月25日

查看全文
  • D. N. Siva Sathyaseelan,
  • D. N. Kesava Perumal,
  • Bharti,
  • V. Ramanathan

摘要

Predicting the band gap of inorganic semiconductors is crucial for designing materials used in electronic and optoelectronic applications. This study employs a range of machine learning (ML) and deep learning (DL) algorithms i.e. Linear Regression, Random Forest, XGBoost, Artificial Neural Network (ANN), and Graph Neural Network (GNN) to predict band gaps using the expt_gap dataset from the Matminer library, which contains experimental band gap values for 6,354 inorganic semiconductors. Following rigorous preprocessing and extraction of composition-based descriptors via the Magpie featurizer, the models were evaluated using a unified fivefold cross-validation protocol applied consistently to all five model classes. The Random Forest model achieved the highest predictive accuracy with a Mean Absolute Error (MAE) of 0.2836 eV, closely followed by the ANN (0.3321 eV) and XGBoost (0.3575 eV). These results significantly outperform the Linear Regression baseline (MAE: 0.5718 eV) and demonstrate the effectiveness of non-linear ensemble and deep learning architectures in capturing the complex, multi-dimensional relationships between chemical composition and electronic properties. The competitive performance of the GNN (MAE: 0.3978 eV) further highlights the potential of graph-based representations in materials informatics. These findings underscore the capacity of advanced ML and DL frameworks to accelerate materials discovery by providing accurate, scalable, and computationally efficient band gap predictions.