PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning
Abstract
Space weather early warning depends on detecting solar wind transients in in-situ measurements at the first Sun-Earth Lagrange point (L1), before they reach Earth. Fixed thresholds can miss combined magnetic and plasma structure, and many learning methods provide a single anomaly score. We present the Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather (PISCES), a convolutional autoencoder trained without catalog labels on OMNI solar wind measurements under physics constraints. Its loss includes magnetic field consistency, an empirical relation between temperature and velocity, the Parker spiral angle, and penalties on changes between consecutive one-minute samples in derived quantities calculated from the reconstruction. At inference, PISCES separates the anomaly score into magnetic and plasma reconstruction errors, physics relations, and residual corrections, and reports the magnitude of each contribution. Attenuation of the skip connections, selected on validation data, improves average precision for the trained models, while the untrained scores remain nearly the same. The trained models also give a more consistent ordering of these physical contributions. After smoothing with a trailing median, the alarms can precede independently observed sudden commencements, including positive sudden impulses.
Related
- Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data
- Major Space Weather Risks Identified via Coupled Physics‐Engineering‐Economic Modeling
- The CUSP CubeSat mission for space weather multi-physics analysis, design, and testing
- Metaheuristic physics-informed extreme-learning machine for initial orbit determination of near-Earth asteroids from too-short arcs
- Physics-Informed Multi-Task Surrogate Model for the Martian Nightside Thermosphere
BibTeX
@misc{lee2026pisces,
title = {{PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning}},
author = {Kevin Lee and Alison J. March},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28022},
eprint = {2609.28022},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28022},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning
AU - Kevin Lee
AU - Alison J. March
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.28022
UR - https://arxiv.org/abs/2609.28022
AB - Space weather early warning depends on detecting solar wind transients in in-situ measurements at the first Sun-Earth Lagrange point (L1), before they reach Earth. Fixed thresholds can miss combined magnetic and plasma structure, and many learning methods provide a single anomaly score. We present the Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather (PISCES), a convolutional autoencoder trained without catalog labels on OMNI solar wind measurements under physics constraints. Its loss includes magnetic field consistency, an empirical relation between temperature and velocity, the Parker spiral angle, and penalties on changes between consecutive one-minute samples in derived quantities calculated from the reconstruction. At inference, PISCES separates the anomaly score into magnetic and plasma reconstruction errors, physics relations, and residual corrections, and reports the magnitude of each contribution. Attenuation of the skip connections, selected on validation data, improves average precision for the trained models, while the untrained scores remain nearly the same. The trained models also give a more consistent ordering of these physical contributions. After smoothing with a trailing median, the alarms can precede independently observed sudden commencements, including positive sudden impulses.
ER -