Purdue University Graduate School
Browse
- No file added yet -

MULTI-LEVEL DEEP OPERATOR LEARNING WITH APPLICATIONS TO DISTRIBUTIONAL SHIFT, UNCERTAINTY QUANTIFICATION AND MULTI-FIDELITY LEARNING

Download (1.33 MB)
thesis
posted on 2024-05-07, 23:43 authored by Rohan Moreshwar DekateRohan Moreshwar Dekate

Neural operator learning is emerging as a prominent technique in scientific machine learn- ing for modeling complex nonlinear systems with multi-physics and multi-scale applications. A common drawback of such operators is that they are data-hungry and the results are highly dependent on the quality and quantity of the training data provided to the models. Moreover, obtaining high-quality data in sufficient quantity can be computationally prohibitive. Faster surrogate models are required to overcome this drawback which can be learned from datasets of variable fidelity and also quantify the uncertainty. In this work, we propose a Multi-Level Stacked Deep Operator Network (MLSDON) which can learn from datasets of different fidelity and is not dependent on the input function. Through various experiments, we demonstrate that the MLSDON can approximate the high-fidelity solution operator with better accuracy compared to a Vanilla DeepONet when sufficient high-fidelity data is unavailable. We also extend MLSDON to build robust confidence intervals by making conformalized predictions. This technique guarantees trajectory coverage of the predictions irrespective of the input distribution. Various numerical experiments are conducted to demonstrate the applicability of MLSDON to multi-fidelity, multi-scale, and multi-physics problems.

History

Degree Type

  • Master of Science in Mechanical Engineering

Department

  • Mechanical Engineering

Campus location

  • West Lafayette

Advisor/Supervisor/Committee Chair

Dr. Guang Lin

Additional Committee Member 2

Dr. Fabio Semperlotti

Additional Committee Member 3

Dr. Partha P. Mukherjee