303 citations · 2.2k across the 86 of their papers we have counts for
28 papers · 1 filter
Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces
Yang Xu, Dibyajyoti Chakraborty, Haiwen Guan +2
Atmospheric observations are sparse, heterogeneous, and unevenly distributed, whereas many generative atmospheric models learn distributions over regularly gridded multivariate sta…
Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Video Flow-matching
Dibyajyoti Chakraborty, Romit Maulik
Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data. In this study, we propose a fundamentally different, unified ap…
Scale-Aware Learning of Chaotic Dynamics on Unstructured Meshes via Binned Spectral Losses
Kanad Sen, Romit Maulik
Surrogate modeling for high-dimensional nonlinear dynamical systems that exhibit chaos requires mechanisms that preserve not only pointwise accuracy but also the scale-dependent st…
Adaptive Diffusion Posterior Sampling for Data and Model Fusion of Complex Nonlinear Dynamical Systems
Dibyajyoti Chakraborty, Hojin Kim, Romit Maulik
High-fidelity numerical simulations of chaotic, high dimensional nonlinear dynamical systems are computationally expensive, necessitating the development of efficient surrogate mod…
High-Resolution Climate Projections Using Diffusion-Based Downscaling of a Lightweight Climate Emulator
Haiwen Guan, Dibyajyoti Chakraborty, Moein Darman +3
The proliferation of data-driven models in weather and climate sciences has marked a significant paradigm shift, with advanced models demonstrating exceptional skill in medium-rang…
SC3D: Dynamic and Differentiable Causal Discovery for Temporal and Instantaneous Graphs
Sourajit Das, Dibyajyoti Chakraborty, Romit Maulik
Discovering causal structures from multivariate time series is a key problem because interactions span across multiple lags and possibly involve instantaneous dependencies. Additio…
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…
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…
Semi-Implicit Neural Ordinary Differential Equations
Hong Zhang, Ying Liu, Romit Maulik
Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in…
Improved deep learning of chaotic dynamical systems with multistep penalty losses
Dibyajyoti Chakraborty, Seung Whan Chung, Ashesh Chattopadhyay +1
Predicting the long-term behavior of chaotic systems remains a formidable challenge due to their extreme sensitivity to initial conditions and the inherent limitations of tradition…
Higher order quantum reservoir computing for non-intrusive reduced-order models
Vinamr Jain, Romit Maulik
Forecasting dynamical systems is of importance to numerous real-world applications. When possible, dynamical systems forecasts are constructed based on first-principles-based model…
LUCIE: A Lightweight Uncoupled ClImate Emulator with long-term stability and physical consistency for O(1000)-member ensembles
Haiwen Guan, Troy Arcomano, Ashesh Chattopadhyay +1
We present a lightweight, easy-to-train, low-resolution, fully data-driven climate emulator, LUCIE, that can be trained on as low as years of -hourly ERA5 data. Unlike most…
Leveraging Interpolation Models and Error Bounds for Verifiable Scientific Machine Learning
Tyler Chang, Andrew Gillette, Romit Maulik
Effective verification and validation techniques for modern scientific machine learning workflows are challenging to devise. Statistical methods are abundant and easily deployed, b…
Interpretable A-posteriori Error Indication for Graph Neural Network Surrogate Models
Shivam Barwey, Hojin Kim, Romit Maulik
Data-driven surrogate modeling has surged in capability in recent years with the emergence of graph neural networks (GNNs), which can operate directly on mesh-based representations…
Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles
Romit Maulik, Romain Egele, Krishnan Raghavan +1
Classical problems in computational physics such as data-driven forecasting and signal reconstruction from sparse sensors have recently seen an explosion in deep neural network (DN…
Multiscale Graph Neural Network Autoencoders for Interpretable Scientific Machine Learning
Shivam Barwey, Varun Shankar, Venkatasubramanian Viswanathan +1
The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here…
Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems
Alec J. Linot, Joshua W. Burby, Qi Tang +3
In data-driven modeling of spatiotemporal phenomena careful consideration often needs to be made in capturing the dynamics of the high wavenumbers. This problem becomes especially…