Spherical spiral network improves global weather forecast accuracy
S$^3$N: A Spherical Spiral Scanning Network for Weather Forecasting
Machine Learning
Summary
Weather forecasting models use grids to divide the Earth and make predictions, but traditional grids can cause errors near the poles. The authors introduced a new method that uses a spherical spiral pattern to better connect grid points and share data across regions smoothly. They also created a precise way to convert data between curved and flat grid views. Their approach leads to more accurate weather forecasts up to 10 days in advance with slower error growth over time.
What this means in practice
- •For weather prediction teams: Improve medium and long-term global weather forecasts by using the spherical spiral scanning approach for better accuracy and smoother data propagation.
- •For climate modeling engineers: Integrate the spherical spiral scanning network to reduce reconstruction errors in atmospheric data grids, enhancing climate simulation fidelity.
Authors
Fan Yan, Chen Hui, Weisi Lin, Haiqi Zhu, Feng Jiang, Sun-Yuan Kung, Wei Zhang
Abstract
Machine learning-based weather prediction (MLWP) has achieved strong performance in global weather forecasting. Recent Hierarchical Equal Area isoLatitude Pixelation (HEALPix)-based methods use the HEALPix (HP) grid to avoid area distortion near the poles of conventional latitude-longitude (LL) grids. However, existing HP-based approaches often use pointwise mapping methods and process HP pixels within separate base faces or local windows. Consequently, the mapping may introduce reconstruction errors and cross-face communication depends on handcrafted boundary handling or shifted windows. We propose the Spherical Spiral Scanning Network (S$^3$N) to address both limitations. First, L2Proj provides a bidirectional method for mapping atmospheric fields between the LL and HP grids through an $L^2$ projection of their continuous finite-element representations. Second, the Attention-Guided Quad-Spiral State-Space Scanning (AQSS) block uses cross-latitude attention to guide selective state-space updates along four global pole-to-pole spiral paths. This design enables continuous information propagation across HP base-face boundaries without additional boundary-processing mechanisms. Experiments show that S$^3$N achieves better results at 4-, 7-, and 10-day lead times, and exhibits slower error growth in long-range forecasting.