Constructing custom thermodynamics using deep learning

• Main Authors: Chen, Xiaoli, Soh, Beatrice W., Ooi, Zi-En, Vissol-Gaudin, Eleonore, Yu, Haijun, Novoselov, Kostya S., Hippalgaonkar, Kedar, Li, Qianxiao
• Other Authors: School of Materials Science and Engineering
• Format: Article
• Language: English
• Published: 2024
• Subjects: Engineering; Applied field; Dissipative systems
• Online Access: https://hdl.handle.net/10356/176204
• Institution: Nanyang Technological University

One of the most exciting applications of artificial intelligence is automated scientific discovery based on previously amassed data, coupled with restrictions provided by known physical principles, including symmetries and conservation laws. Such automated hypothesis creation and verification can as...