The paper proposes a method for predicting future snow water equivalent (SWE) across the Western United States by first removing spatial correlations using a Gaussian Process-based linear transformation, then training a long short-term memory (LSTM) neural network on the decorrelated data. This separation of spatial and temporal components improves predictive accuracy compared to baseline models. Additionally, the authors incorporate conformal prediction to provide distribution‑free uncertainty estimates for SWE forecasts.
By Colin Fenster, Adrienne Marshall, Soutir Bandyopadhyay, Daniel McKenzie
arXiv:2606. 19026v1 Announce Type: cross Abstract: Forecast errors in high-resolution numerical weather prediction (NWP) systems are often linked to unresolved planetary boundary layer (PBL) processes, convection, terrain-induced circulations, and other vertically structured atmospheric phenomena.
By David Aaron Evans, Jay C. Rothenberger, Kara J. Sulia, Nick P. Bassill, Chris D. Thorncroft
arXiv:2607. 10410v1 Announce Type: cross Abstract: Reliable forecasting of several interrelated environmental variables - such as regional precipitation and temperature, or other correlated geophysical fields - across many locations calls for accurate predictions accompanied by trustworthy statements of their uncertainty.
By Jongwook Kim, Jong-Min Kim
The paper presents a two‑stage residual learning approach for solar irradiance forecasting that separately predicts the expected irradiance with an LSTM and models the forecast error distribution with a second network. This method improves uncertainty estimation, reducing the deviation between predicted and historical standard deviations by 34.6 % for a standalone LSTM and 56.5 % when combined with Gaussian process regression. The approach captures total forecast error, providing more reliable uncertainty estimates for decision‑making.
By RR Flanagan, E Kasha, PW Talbot, AS Epiny, MR Deinert
arXiv:2607. 21080v1 Announce Type: new Abstract: Long-horizon weather forecasting is a fundamental challenge in atmospheric science, for which autoregressive Deep Learning Weather Prediction (DLWP) has emerged as the primary paradigm.
By Yun-Ye Cai, Hsuan-Tien Lin
arXiv:2607. 00197v1 Announce Type: new Abstract: Long-horizon multivariate time series forecasting (LTSF) remains challenging due to non-stationarity, regime shifts, and error accumulation.
By Haroon Gharwi, Yue Dai, Kai Shu
arXiv:2606. 17413v1 Announce Type: new Abstract: Space-based monitoring of atmospheric carbon dioxide (CO2) is essential for constraining the global carbon budget.
By Alejandro Calle-Saldarriaga, Felix Jimenez, Jack Grosskreuz, Jiazheng Wang, Jonathan Hobbs, Matthias Katzfuss
arXiv:2609.13345v1 Announce Type: cross
Abstract: Probabilistic forecasting is central to decision-making under uncertainty, yet its methodological landscape has become increasingly fragmented across...
By Donia Besher, Rajdeep Pathak, Madhurima Panja, Tanujit Chakraborty
arXiv:2605. 05540v2 Announce Type: replace Abstract: Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently while preserving the statistical structure of long trajectories.
By Tianyue Yang, Xiao Xue
PROSWIN is a probabilistic machine learning model that forecasts hourly solar wind speed at Earth up to four days ahead, using solar images and magnetograms processed by a deep neural network and distributional regression. It introduces a prediction score metric that rewards both timeline and high‑speed solar wind peak accuracy, achieving well‑calibrated uncertainties and superior performance on 14 years of data compared to existing models. The study highlights the importance of the 171 Å channel and demonstrates that probabilistic forecasts outperform single‑value models for both overall timelines and peak events.
By Daniel Collin, Yuri Shprits, Luca Chiarabini, Stefan J. Hofmeister, Nadja Klein, Guillermo Gallego
BEAST is the first Bayesian Swin Transformer for atmospheric forecasting at 0.25° global resolution, capable of quantifying both aleatoric and epistemic uncertainty. The authors introduce a 4D‑parallelization scheme with domain‑tensor‑parallelism and a novel uncertainty parallel method, allowing a 2.4‑billion‑parameter model to reach 3.96 EFLOP/s on 20,480 NVIDIA GH200 GPUs. A 700‑million‑parameter BEAST trained on 40 years of data achieves predictive skill comparable to state‑of‑the‑art probabilistic AI models, predicts extreme events with high accuracy, and generates large ensembles 3–4× faster than the current best AI model.
By Deifilia Kieckhefen, Juan Pedro Guti\'errez Hermosillo Muriedas, Lars Helge Heyen, Mathis Bode, Iida Hakulinen, Andreas Herten, Chelsea Maria John, Thorsten Kurth, Anni Moisala, Asena Karolin \"Ozdemir, Kaleb Phipps, Oskar Taubert, Arvid Weyrauch, Markus G\"otz, Charlotte Debus
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