arXiv Machine Learning By Anthony Zhou, Alexander Wikner, Amaury Lancelin, Pedram Hassanzadeh, Amir Barati Farimani

Benchmarking Stochastic Interpolants for Modeling Physical Systems

Read the original on arXiv Machine Learning →

The paper benchmarks generative models that use stochastic interpolants against traditional Gaussian-denoising frameworks for modeling fluid and climate systems. It shows that stochastic interpolants can match or surpass Gaussian-denoising baselines in pointwise accuracy, spectral fidelity, and probabilistic skill. The study also highlights a tradeoff between deterministic and stochastic sampling, noting that deterministic sampling improves pointwise accuracy but smooths predictions, while stochastic sampling preserves spectral content and calibration but requires more evaluations and ensemble averaging.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Oct 5

Reliability of Probabilistic Emulation of Physical Systems

The paper compares two main strategies for producing probabilistic forecasts of physical systems: generative models (e.g., diffusion or flow matching) and ensembles of deterministic models trained with the continuous ranked probability score (CRPS). It introduces a framework that evaluates both methods on diverse 2‑D spatiotemporal systems, measuring empirical coverage of predictive intervals, accuracy, and computational efficiency. The study finds that CRPS‑trained ensembles generally provide more reliable uncertainties and faster inference, while generative models trained in ambient space can match coverage but at higher latency. The authors also release AutoCast, a modular framework for both approaches, and AutoSim, a dataset generation tool.

By Sam F. Greenbury, Radka Jersakova, Paolo Conti, Marjan Famili, Christopher Iliffe Sprague, Edwin Brown, Farhan Feroz, Jason D. McEwen
arXiv Machine Learning
Aug 28

SimCast-S2S: An Efficient Generative Model for Subseasonal Precipitation Forecasting via Transfer Learning from Climate Simulations

SimCast‑S2S is a generative latent‑diffusion model designed for probabilistic subseasonal‑to‑seasonal precipitation forecasting. It tackles three key challenges: it uses a diffusion pipeline to capture uncertainty, operates in a compact latent space to enable efficient large‑ensemble generation, and leverages transfer learning with low‑rank adaptation to train on limited reanalysis data after pretraining on climate simulations. The model outperforms deep‑learning baselines and competes with, or surpasses, operational systems such as the ECMWF‑S2S baseline without requiring extensive post‑processing.

By Hiep V. Dang, Antonios Mamalakis
arXiv Machine Learning
Aug 7

Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations

arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.

By Guillaume Couairon, Alexis Jacq, Yu-Han Wu, Renu Singh, Yana Hasson, Quentin Berthet, Romuald Elie
arXiv Machine Learning
Jul 2

TRIE: An Evaluation Framework for Stochastic PDE Surrogates

arXiv:2607. 00196v1 Announce Type: new Abstract: Many scientific systems exhibit uncertainty from stochastic forcing, unresolved degrees of freedom, or imperfect observations, making reliable surrogate forecasting fundamentally distributional rather than pointwise.

By Bharat Srikishan, Javier E. Santos, Nikhil Muralidhar, Charles D. Young
arXiv Machine Learning
Sep 4

SimCast-S2S: A Computationally Efficient Diffusion Model for Subseasonal Precipitation Forecasting

SimCast‑S2S is a generative latent‑diffusion framework designed for probabilistic subseasonal‑to‑seasonal precipitation forecasting. It tackles three key challenges: it uses a diffusion‑based generative pipeline for uncertainty quantification, operates in a compact latent space learned by VAEs for efficient large‑ensemble generation, and employs transfer learning with LoRA to overcome limited training data. On reanalysis data, it outperforms deep‑learning baselines and competes with or surpasses state‑of‑the‑art operational systems such as ECMWF‑S2S.

By Hiep V. Dang, Antonios Mamalakis