Surya: Foundation Model for Heliophysics
read the original abstract
Heliophysics is central to understanding and forecasting space weather events and solar activity. Despite decades of high-resolution observations from the Solar Dynamics Observatory (SDO), most models remain task-specific and constrained by scarce labeled data, limiting their capacity to generalize across solar phenomena. We introduce Surya, a 366M parameter foundation model for heliophysics designed to learn general-purpose solar representations from multi-instrument SDO observations, including eight Atmospheric Imaging Assembly (AIA) channels and five Helioseismic and Magnetic Imager (HMI) products. Surya employs a spatiotemporal transformer architecture with spectral gating and long--short range attention, pretrained on high-resolution solar image forecasting tasks and further optimized through autoregressive rollout tuning. Zero-shot evaluations demonstrate its ability to forecast solar dynamics and flare events, while downstream fine-tuning with parameter-efficient Low-Rank Adaptation (LoRA) shows strong performance on solar wind forecasting, active region segmentation, solar flare forecasting, and EUV spectra. Surya is the first foundation model in heliophysics that uses time advancement as a pretext task on full-resolution SDO data. Its novel architecture and performance suggest that the model is able to learn the underlying physics behind solar evolution.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Forecasting megaelectron-volt electron flux in the Earth's outer radiation belt using supervised machine learning algorithms and a timeseries foundation model
Hybrid TimesFM plus ridge regression on covariates forecasts 1-MeV electron flux with average R² of 0.9 on out-of-sample 2024 data, outperforming linear regression, CNN, LSTM and Transformer models.
-
Improving Solar Flare Soft X-ray Classification With FOXES: A Framework For Operational X-ray Emission Synthesis
FOXES is a Vision Transformer framework that predicts solar soft X-ray irradiance from EUV observations with 0.051 dex mean absolute error while providing spatial attribution of emission sources.
-
Contrastive Heliophysical Image Pretraining for Solar Dynamics Observatory Records
SolarCHIP contrastively pretrains CNN and Vision Transformer backbones on SDO AIA-HMI data with multi-granularity objectives, achieving SOTA on cross-modal translation and flare classification especially in low-resour...
-
Predicting the thermodynamics in the chromosphere from the translation of SDO data into the IRIS$^{2}$ inversion results using a visual transformer model
A visual transformer model trained on IRIS inversions predicts chromospheric temperature and density from SDO data with correlations around 0.8 on 80% of test cases.
-
Prediction of Magnetic Flux Evolution During Solar Active Region Emergence using Long Short-Term Memory Networks
Standard LSTM networks predict solar active region magnetic flux evolution 3-10 hours ahead from intensity and oscillation maps, outperforming encoder-decoder variants on held-out test regions.
-
Towards a Foundation Model for the Martian Atmosphere
The paper reviews data sources, physical models, downstream applications, and AI techniques to outline considerations for building a foundation model for the Martian atmosphere.
-
Review of Machine Learning Models for Solar Energetic Particle Prediction
A review of ML models for SEP prediction that compares architectures, datasets, inputs and outputs while recommending good practices for future work.
-
The Solar Dynamics Observatory in the Living With a Star Era: From Solar Observations to Predictive Heliophysics
SDO's high-cadence full-disk observations enable treating the solar atmosphere as an evolving dynamical system with applications to predictive space weather and heliophysics modeling.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.