ACE Metric: Advection and Convection Evaluation for Accurate Weather Forecasting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916279491756032 |
|---|---|
| author | Kim, Doyi Seo, Minseok Choi, Yeji |
| author_facet | Kim, Doyi Seo, Minseok Choi, Yeji |
| contents | Recently, data-driven weather forecasting methods have received significant attention for surpassing the RMSE performance of traditional NWP (Numerical Weather Prediction)-based methods. However, data-driven models are tuned to minimize the loss between forecasted data and ground truths, often using pixel-wise loss. This can lead to models that produce blurred outputs, which, despite being significantly different in detail from the actual weather conditions, still demonstrate low RMSE values. Although evaluation metrics from the computer vision field, such as PSNR, SSIM, and FVD, can be used, they are not entirely suitable for weather variables. This is because weather variables exhibit continuous physical changes over time and lack the distinct boundaries of objects typically seen in computer vision images. To resolve these issues, we propose the advection and convection Error (ACE) metric, specifically designed to assess how well models predict advection and convection, which are significant atmospheric transfer methods. We have validated the ACE evaluation metric on the WeatherBench2 and MovingMNIST datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04678 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ACE Metric: Advection and Convection Evaluation for Accurate Weather Forecasting Kim, Doyi Seo, Minseok Choi, Yeji Computer Vision and Pattern Recognition Recently, data-driven weather forecasting methods have received significant attention for surpassing the RMSE performance of traditional NWP (Numerical Weather Prediction)-based methods. However, data-driven models are tuned to minimize the loss between forecasted data and ground truths, often using pixel-wise loss. This can lead to models that produce blurred outputs, which, despite being significantly different in detail from the actual weather conditions, still demonstrate low RMSE values. Although evaluation metrics from the computer vision field, such as PSNR, SSIM, and FVD, can be used, they are not entirely suitable for weather variables. This is because weather variables exhibit continuous physical changes over time and lack the distinct boundaries of objects typically seen in computer vision images. To resolve these issues, we propose the advection and convection Error (ACE) metric, specifically designed to assess how well models predict advection and convection, which are significant atmospheric transfer methods. We have validated the ACE evaluation metric on the WeatherBench2 and MovingMNIST datasets. |
| title | ACE Metric: Advection and Convection Evaluation for Accurate Weather Forecasting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.04678 |