303 citations · 2.2k across the 86 of their papers we have counts for
10 papers · 1 filter
A Weak Penalty Neural ODE for Learning Chaotic Dynamics from Noisy Time Series
Xuyang Li, John Harlim, Dibyajyoti Chakraborty +1
The accurate forecasting of complex, high-dimensional dynamical systems from observational data is a fundamental task across numerous scientific and engineering disciplines. A sign…
Interpretable Diagnostics and Adaptive Data Assimilation for Neural ODEs via Discrete Empirical Interpolation
Hojin Kim, Romit Maulik
We present a framework that leverages the Discrete Empirical Interpolation Method (DEIM) for interpretable deep learning and dynamical system analysis. Although DEIM efficiently ap…
MoWE : A Mixture of Weather Experts
Dibyajyoti Chakraborty, Romit Maulik, Peter Harrington +3
Data-driven weather models have recently achieved state-of-the-art performance, yet progress has plateaued in recent years. This paper introduces a Mixture of Experts (MoWE) approa…
Localized PCA-Net Neural Operators for Scalable Solution Reconstruction of Elliptic PDEs
Mrigank Dhingra, Romit Maulik, Adil Rasheed +1
Neural operator learning has emerged as a powerful approach for solving partial differential equations (PDEs) in a data-driven manner. However, applying principal component analysi…
LUCIE-3D: A three-dimensional climate emulator for forced responses
Haiwen Guan, Troy Arcomano, Ashesh Chattopadhyay +1
We introduce LUCIE-3D, a lightweight three-dimensional climate emulator designed to capture the vertical structure of the atmosphere, respond to climate change forcings, and mainta…
FIGNN: Feature-Specific Interpretability for Graph Neural Network Surrogate Models
Riddhiman Raut, Romit Maulik, Shivam Barwey
This work presents a novel graph neural network (GNN) architecture, the Feature-specific Interpretable Graph Neural Network (FIGNN), designed to enhance the interpretability of dee…
Multimodal Atmospheric Super-Resolution With Deep Generative Models
Dibyajyoti Chakraborty, Haiwen Guan, Jason Stock +3
Score-based diffusion modeling is a generative machine learning algorithm that can be used to sample from complex distributions. They achieve this by learning a score function, i.e…
SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning
Xuyang Li, Romit Maulik
Modern deep reinforcement learning (DRL) methods have made significant advances in handling continuous action spaces. However, real-world control systems, especially those requirin…
CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints
Xin Wang, Jianda Chen, Juntao Yang +8
Accurate and efficient climate simulations are crucial for understanding Earth's evolving climate. However, current general circulation models (GCMs) face challenges in capturing u…
Binned Spectral Power Loss for Improved Prediction of Chaotic Systems
Dibyajyoti Chakraborty, Arvind T. Mohan, Romit Maulik
Forecasting multiscale chaotic dynamical systems, such as turbulent flows, with deep learning remains a formidable challenge due to the spectral bias of neural networks, which hind…