Tushar Mittal

TIP-INN: A thermodynamics-informed machine learning framework for the mechanical behavior of rocks

Abstract Modeling the mechanical deformation of geological materials across relevant thermodynamic conditions and dynamic processes remains a fundamental challenge in Earth sciences. Conventional rheological models rely on isolated disciplinary approaches and hard-coded iterative...

Spec2VEC : Interpretable Spectral Representations of Planetary Signals in Vector Spaces

Summary The application of machine learning to planetary geophysics is frequently bottlenecked by a scarcity of labeled data and the complexity of non-stationary seismo-acoustic signals. While deep learning offers powerful feature extraction, it requires massive datasets that are...

Seismic and Aseismic Slip Compete to Regulate Permeability Evolution During Fault Reactivation

Abstract Crustal permeability can be created through microearthquakes as observed at field and laboratory scales. The respective roles of seismic and aseismic slip in governing permeability evolution remain ill‐constrained. Here, we present observations of controlled pore pressur...

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

Abstract 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 ext...