JPhys Energy&MLST联合特刊精选|聚焦于在能源应用的实验材料科学中弥合机器学习理论与实践之间的差距

特刊详情

客座编辑

• Prashun Gorai，美国伦斯勒理工学院
• Qian Yang，美国康涅狄格大学
• Victor Fung，美国佐治亚理工学院

主题范围

Bridging the gap between experimental and theoretical materials science for energy applications is a longstanding problem in the field. Recent advances in machine learning (ML) have provided many potential solutions to solving this problem, but the application of ML-based approaches has also revealed new challenges when bridging ML theory with the practical aspects of data-driven problems in computational and experimental materials science and its application in energy research. This focus issue aims to highlight the latest developments in methodology and demonstrations towards bridging these gaps, as well as provide complementary perspectives from experimentalists and ML scientists on current challenges and needs moving forward.

Topics of interest include but are not limited to:

• Solving inverse problems with ML relating to materials characterization to materials structure
• Fundamental methodologies that can enable automation in experiments
• Approaches for reliable solid-state synthesis predictions
• Experimental design with reinforcement learning or active learning
• Moving from computational materials discovery to actionable experimental guidance