{"ID":2872812,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09052","arxiv_id":"2509.09052","title":"MoWE : A Mixture of Weather Experts","abstract":"Data-driven weather models have recently achieved state-of-the-art performance, yet progress has plateaued in recent years. This paper introduces a Mixture of Experts (MoWE) approach as a novel paradigm to overcome these limitations, not by creating a new forecaster, but by optimally combining the outputs of existing models. The MoWE model is trained with significantly lower computational resources than the individual experts. Our model employs a Vision Transformer-based gating network that dynamically learns to weight the contributions of multiple \"expert\" models at each grid point, conditioned on forecast lead time. This approach creates a synthesized deterministic forecast that is more accurate than any individual component in terms of Root Mean Squared Error (RMSE). Our results demonstrate the effectiveness of this method, achieving up to a 10% lower RMSE than the best-performing AI weather model on a 2-day forecast horizon, significantly outperforming individual experts as well as a simple average across experts. This work presents a computationally efficient and scalable strategy to push the state of the art in data-driven weather prediction by making the most out of leading high-quality forecast models.","short_abstract":"Data-driven weather models have recently achieved state-of-the-art performance, yet progress has plateaued in recent years. This paper introduces a Mixture of Experts (MoWE) approach as a novel paradigm to overcome these limitations, not by creating a new forecaster, but by optimally combining the outputs of existing m...","url_abs":"https://arxiv.org/abs/2509.09052","url_pdf":"https://arxiv.org/pdf/2509.09052v1","authors":"[\"Dibyajyoti Chakraborty\",\"Romit Maulik\",\"Peter Harrington\",\"Dallas Foster\",\"Mohammad Amin Nabian\",\"Sanjay Choudhry\"]","published":"2025-09-10T23:15:59Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"physics.ao-ph\",\"physics.geo-ph\"]","methods":"[\"Vision Transformer\",\"Mixture of Experts\",\"Transformer\"]","has_code":false}