Probabilistic forecasting improves solar wind speed predictions at Earth
PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images
Machine Learning
Summary
Predicting strong gusts of solar wind that can disrupt technology on Earth is very difficult because uncertainties are rarely measured. The authors created a new AI model called PROSWIN that uses solar images and magnetic field data to predict solar wind speeds up to four days ahead with probabilities, not just single estimates. Their model better captures both the overall timeline and dangerous peak speeds, giving more reliable risk assessments. This approach also shows that certain solar imaging channels improve predictions and that their method could help other forecasting problems.
What this means in practice
- •For space weather forecasters: Provide better risk estimates for technology disruptions by delivering reliable probabilistic solar wind speed forecasts with multiple-day lead times.
- •For grid operators: Improve preparedness for solar wind-related impacts on power infrastructure by using probabilistic forecasts that accurately predict high-speed solar wind peaks.
Authors
Daniel Collin, Yuri Shprits, Luca Chiarabini, Stefan J. Hofmeister, Nadja Klein, Guillermo Gallego
Abstract
Accurately predicting fast solar wind conditions is challenging, as uncertainties are large and unquantified by traditional single-value prediction models. In particular, the risks of high-speed solar wind streams (HSSs), which can cause damage to technological infrastructure, cannot be reliably assessed without probabilistic forecasts. We present PROSWIN, a probabilistic machine learning model that forecasts the hourly solar wind speed (SWS) at Earth with a four-day lead time. The approach combines solar images and magnetograms using a deep neural network coupled to a distributional regression algorithm. Because standard error metrics underweight the relevance of HSS peaks, we further introduce the prediction score, a model-selection metric that jointly rewards timeline and HSS peak accuracy. On 14 years of data, our forecast achieves very well-calibrated uncertainties (<1% average deviation). Using the continuous ranked probability score (CRPS), a metric that assesses distributional accuracy, we obtain a timeline CRPS of 41.0 km/s, an HSS peak CRPS of 45.3 km/s, and a prediction score of 42.3 km/s. We find that the 171 Å channel is an important complement to the typically used 193 Å and 211 Å channels and that the prediction score for model selection improves the applicability of the model. Compared to selected models from the literature, ours is the only one that is accurate for both timeline and HSS peak values, rather than trading one off against the other. These results support the advantages of probabilistic over single-value solar wind models. The introduced methods are also transferable to other forecasting problems.