Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911055883534336 |
|---|---|
| author | Cheon, Minjong Goo, Eunhan Shin, Su-Hyeon Ahmed, Muhammad Kim, Hyungjun |
| author_facet | Cheon, Minjong Goo, Eunhan Shin, Su-Hyeon Ahmed, Muhammad Kim, Hyungjun |
| contents | Recently, AI-based weather forecast models have achieved impressive advances. These models have reached accuracy levels comparable to traditional NWP systems, marking a significant milestone in data-driven weather prediction. However, they mostly leverage Transformer-based architectures, which often leads to high training complexity and resource demands due to the massive parameter sizes. In this study, we introduce a modernized CNN-based model for global weather forecasting that delivers competitive accuracy while significantly reducing computational requirements. To present a systematic modernization roadmap, we highlight key architectural enhancements across multiple design scales from an earlier CNN-based approach. KAI-a incorporates a scale-invariant architecture and InceptionNeXt-based blocks within a geophysically-aware design, tailored to the structure of Earth system data. Trained on the ERA5 daily dataset with 67 atmospheric variables, the model contains about 7 million parameters and completes training in just 12 hours on a single NVIDIA L40s GPU. Our evaluation shows that KAI-a matches the performance of state-of-the-art models in medium-range weather forecasting, while offering a significantly lightweight design. Furthermore, case studies on the 2018 European heatwave and the East Asian summer monsoon demonstrate KAI-a's robust skill in capturing extreme events, reinforcing its practical utility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10893 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency Cheon, Minjong Goo, Eunhan Shin, Su-Hyeon Ahmed, Muhammad Kim, Hyungjun Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Atmospheric and Oceanic Physics Recently, AI-based weather forecast models have achieved impressive advances. These models have reached accuracy levels comparable to traditional NWP systems, marking a significant milestone in data-driven weather prediction. However, they mostly leverage Transformer-based architectures, which often leads to high training complexity and resource demands due to the massive parameter sizes. In this study, we introduce a modernized CNN-based model for global weather forecasting that delivers competitive accuracy while significantly reducing computational requirements. To present a systematic modernization roadmap, we highlight key architectural enhancements across multiple design scales from an earlier CNN-based approach. KAI-a incorporates a scale-invariant architecture and InceptionNeXt-based blocks within a geophysically-aware design, tailored to the structure of Earth system data. Trained on the ERA5 daily dataset with 67 atmospheric variables, the model contains about 7 million parameters and completes training in just 12 hours on a single NVIDIA L40s GPU. Our evaluation shows that KAI-a matches the performance of state-of-the-art models in medium-range weather forecasting, while offering a significantly lightweight design. Furthermore, case studies on the 2018 European heatwave and the East Asian summer monsoon demonstrate KAI-a's robust skill in capturing extreme events, reinforcing its practical utility. |
| title | Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2507.10893 |