MoWE : A Mixture of Weather Experts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909781354086400 |
|---|---|
| author | Chakraborty, Dibyajyoti Maulik, Romit Harrington, Peter Foster, Dallas Nabian, Mohammad Amin Choudhry, Sanjay |
| author_facet | Chakraborty, Dibyajyoti Maulik, Romit Harrington, Peter Foster, Dallas Nabian, Mohammad Amin Choudhry, Sanjay |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09052 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoWE : A Mixture of Weather Experts Chakraborty, Dibyajyoti Maulik, Romit Harrington, Peter Foster, Dallas Nabian, Mohammad Amin Choudhry, Sanjay Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics Geophysics 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. |
| title | MoWE : A Mixture of Weather Experts |
| topic | Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics Geophysics |
| url | https://arxiv.org/abs/2509.09052 |