arXiv:2607. 23018v1 Announce Type: cross Abstract: Nonstationary Gaussian process (GP) models are powerful tools for capturing input-dependent variability by adapting to observed data.
By Jeremy Ovadia
arXiv:2506. 19340v4 Announce Type: replace-cross Abstract: Whole-atmosphere models such as WACCM-X resolve coupling from the Earth surface to the Mesosphere-Lower-Thermosphere (MLT), and Ionosphere-Thermosphere (IT) systems with expensive computational costs.
By Jiahui Hu, Wenjun Dong
PISCES is a physics‑informed convolutional autoencoder designed to detect solar‑wind transients for space‑weather early warning. Trained on OMNI solar‑wind data without catalog labels, its loss incorporates magnetic field consistency, temperature‑velocity relations, the Parker spiral angle, and temporal smoothness penalties. During inference, PISCES decomposes the anomaly score into magnetic, plasma, physics‑relation, and residual components, enabling alarms that can precede observed sudden commencements and positive sudden impulses.
By Kevin Lee, Alison J. March
arXiv:2601. 12614v4 Announce Type: replace-cross Abstract: Hybrid-Vlasov simulations resolve ion-kinetic effects in the solar wind-magnetosphere interaction, but even 5D (2D + 3V) configurations are computationally expensive.
By Daniel Holmberg, Ivan Zaitsev, Markku Alho, Ioanna Bouri, Fanni Franssila, Haewon Jeong, Minna Palmroth, Teemu Roos
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
The paper presents a hierarchical ensemble for short‑term photovoltaic power forecasting that fuses temporal neural models, historical analogs, state climatology, and gradient‑boosted trees with horizon‑specific convex weights. Solar geometry and numerical weather forecasts provide expected generation conditions, while a calibration step corrects recent bias using historical forecast errors. Evaluated on PVDAQ and GEFCom2014 data, the ensemble reduces mean absolute error by up to 6% compared to strong individual models, though its advantage varies with dataset and horizon.
By Xu Yuqing, Zhou Liguo, Sun Ze, Yu Lei, Jiang Mingming