清理数据泄露后，用三阶段模型预测带隙，树模型准确率达0.88~0.90。
Leakage-Aware Bandgap Prediction on the JARVIS-DFT Dataset: A Phase-Wise Feature Analysis
- 分三阶段逐步加入物理、工程和成分特征，控制数据泄露
- 树模型在2280个材料上达到R² 0.88~0.90，提升空间有限
- 揭示介电张量是影响带隙预测的关键因素，适合材料设计研究
本研究对JARVIS-DFT带隙数据集进行系统分析，识别并剔除可能隐含能带信息的描述符（如有效质量），得到包含2280种材料的去泄露子集。基于该数据集，构建三阶段建模框架，逐步引入基础物理特征、工程化特征和成分属性。结果表明，在控制泄露的前提下，树模型在各阶段均实现R²约为0.88至0.90，说明扩展特征空间对预测精度提升有限。SHAP分析一致指出介电张量分量为最主要贡献因子。本工作提供了可用于未来泄漏感知带隙预测研究的清洗数据集与基准性能指标。
原文摘要 · Abstract (English)
In this study, we perform a systematic analysis of the JARVIS-DFT bandgap dataset and identify and remove descriptors that may inadvertently encode band-structure information, such as effective masses. This process yields a curated, leakage-controlled subset of 2280 materials. Using this dataset, a three-phase modeling framework is implemented that incrementally incorporates basic physical descriptors, engineered features, and compositional attributes. The results show that tree-based models achieve R2 values of approximately 0.88 to 0.90 across all phases, indicating that expanding the descriptor space does not substantially improve predictive accuracy when leakage is controlled. SHAP analysis consistently identifies the dielectric tensor components as the dominant contributors. This work provides a curated dataset and baseline performance metrics for future leakage-aware bandgap prediction studies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。