Benjamin K. Holtzman

How Much Physics Should a Neural Network Know? Thermodynamics‐Informed Neural Networks for Rock Constitutive Modeling With Epistemic Uncertainty

Machine learning offers a flexible route to constitutive modeling, with two emergent questions for geoscience applications: what level of thermodynamic constraint should be embedded in the network architecture, and how should predictive uncertainty be quantified when extrapolating from laboratory to field conditions?...