42 citations · 155 across the 16 of their papers we have counts for
7 papers · 1 filter
A Multimodal Conditional Mixture Model with Distribution-Level Physics Priors
Jinkyo Han, Bahador Bahmani
Many scientific and engineering systems exhibit intrinsically multimodal behavior arising from latent regime switching and non-unique physical mechanisms. In such settings, learnin…
A Physics-informed Multi-resolution Neural Operator
Sumanta Roy, Bahador Bahmani, Ioannis G. Kevrekidis +1
The predictive accuracy of operator learning frameworks depends on the quality and quantity of available training data (input-output function pairs), often requiring substantial am…
A Resolution Independent Neural Operator
Bahador Bahmani, Somdatta Goswami, Ioannis G. Kevrekidis +1
The Deep Operator Network (DeepONet) is a powerful neural operator architecture that uses two neural networks to map between infinite-dimensional function spaces. This architecture…
Manifold embedding data-driven mechanics
Bahador Bahmani, WaiChing Sun
This article introduces a new data-driven approach that leverages a manifold embedding generated by the invertible neural network to improve the robustness, efficiency, and accurac…
Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
Bahador Bahmani, WaiChing Sun
This paper presents a PINN training framework that employs (1) pre-training steps that accelerates and improve the robustness of the training of physics-informed neural network wit…
Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation
Xiao Sun, Bahador Bahmani, Nikolaos N. Vlassis +2
This paper presents a computational framework that generates ensemble predictive mechanics models with uncertainty quantification (UQ). We first develop a causal discovery algorith…
An accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data
Bahador Bahmani, WaiChing Sun
We present a hybrid model/model-free data-driven approach to solve poroelasticity problems. Extending the data-driven modeling framework originated from Kirchdoerfer and Ortiz (201…