Insights into ensemble learning-based data-driven model for safety-related property of chemical substances
Chemical Engineering Science(2022)
摘要
•Stacking-based ensemble learning is deployed with heterogeneous ML methods.•Individual and ensemble ML models are comprehensively studied and compared.•Ensemble models present improved predictive accuracy than individual models.•Model reliability is analyzed with structural feature-based data-driven categories.
更多查看译文
关键词
Machine learning,Predictive modeling,Molecular feature,Flash point
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要