TIP-INN: A thermodynamics-informed machine learning framework for the mechanical behavior of rocks
TIP-INN (Thermodynamics of Irreversible Processes Informed Neural Network) is presented, a thermodynamically consistent machine learning framework grounded in the Generalized Standard Materials (GSM) formalism, enabling stable, rapid training across complex rheologies.
Kan-Gan Li, T. Mittal, Benjamin K. Holtzman et al.
· PNAS Nexus · 1 citation