1.7k citations · 2.5k across the 48 of their papers we have counts for
3 papers · 1 filter
Multi-task Learning for Source Attribution and Field Reconstruction for Methane Monitoring
Arka Daw, Kyongmin Yeo, Anuj Karpatne +1
Inferring the source information of greenhouse gases, such as methane, from spatially sparse sensor observations is an essential element in mitigating climate change. While it is w…
Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling
Arka Daw, Jie Bu, Sifan Wang +2
Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution…
Physics-Guided Problem Decomposition for Scaling Deep Learning of High-dimensional Eigen-Solvers: The Case of Schrödinger's Equation
Sangeeta Srivastava, Samuel Olin, Viktor Podolskiy +3
Given their ability to effectively learn non-linear mappings and perform fast inference, deep neural networks (NNs) have been proposed as a viable alternative to traditional simula…