5 papers
Understanding Perturbed Parameter Ensemble Sensitivities Using A Contrastive Learning Approach
Da Fan, David John Gagne, Gregory S Elsaesser +5
Perturbed parameter ensembles (PPEs) reveal how physics parameters affect climate simulations, but interpreting parameter sensitivities across multivariate, spatially structured ou…
TWIG: A Time-Causal Wavelet Operator for Autoregressive Forecasting on Irregular Graphs
Subashree Venkatasubramanian, David A. Barajas-Solano, Chuyang Liu +2
We introduce TWIG (Time-Causal Wavelet Operator for Irregular Graphs), a graph-native neural operator for autoregressive surrogate modeling on static irregular graphs. TWIG transfo…
Calibrating Geophysical Predictions under Constrained Probabilistic Distributions
Zhewen Hou, Jiajin Sun, Subashree Venkatasubramanian +3
Machine learning (ML) has shown significant promise in studying complex geophysical dynamical systems, including turbulence and climate processes. Such systems often display sensit…
Machine Learning Workflows in Climate Modeling: Design Patterns and Insights from Case Studies
Tian Zheng, Subashree Venkatasubramanian, Shuolin Li +5
Machine learning has been increasingly applied in climate modeling on system emulation acceleration, data-driven parameter inference, forecasting, and knowledge discovery, addressi…
Variational Encoder-Decoders for Learning Latent Representations of Physical Systems
Subashree Venkatasubramanian, David A. Barajas-Solano
We present a deep-learning Variational Encoder-Decoder (VED) framework for learning data-driven low-dimensional representations of the relationship between high-dimensional paramet…