Prof S Gopalkrishnan, IISc, Bangalore

Hybrid Physics-Data Driven Models for Solution of Inverse Problems in NDE
Professor, Department of Aerospace Engineering, Indian Institute of Science, Bangalore 560012
krishnan@iisc.ac.in
Abstract
Inverse problems pose a significant challenge as they aim to estimate the causal factors that result in a measured response. However, the responses are often truncated, partially available, and corrupted by measurement noise, rendering the problems ill-posed, and may have multiple or no solutions. While physics-based models are interpretable, they operate under approximations and assumptions. Data-driven models such as machine learning and deep learning have shown promise in solving inverse problems, especially in NDE, but they lack robustness, convergence, and generalization when operating under partial information, compromising the interpretability and explainability of their predictions. To overcome these challenges, This talk will present the hybrid physics-data-driven models that is formulated by integrating prior knowledge of physical laws, expert knowledge, spatial invariances, empirically validated rules, etc., acting as a regularizing agent to select a more feasible solution space. This approach improves prediction accuracy, robustness, generalization, interpretability, and explainability of the data-driven models. In this talk, I will present various physics-data-driven models to solve inverse problems related to NDE by integrating prior knowledge and its representation into a data-driven pipeline at different stages. In this talk several hybrid models will be presented to solve inverse problems such as leakage estimation of a pressurized habitat, estimating dispersion relations of a waveguide, structural damage identification, filtering temperature effects in guided waves, material property prediction, and guided wave generation and material design.