ACE Metric: Advection and Convection Evaluation for Accurate Weather Forecasting
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.
Code (0)
등록된 구현이 없습니다.
Tasks
SSIMWeather ForecastingSimilar Papers 제목 키워드 기반
Decomposing weather forecasting into advection and convection with neural networks
Operational weather forecasting models have advanced for decades on both the explicit numerical solvers and the empirical physical parameterization schemes. However, the involved high computational costs and uncertaintie…
Graph AttentionWeather ForecastingPhysics-Assisted and Topology-Informed Deep Learning for Weather Prediction
Although deep learning models have demonstrated remarkable potential in weather prediction, most of them overlook either the \textbf{physics} of the underlying weather evolution or the \textbf{topology} of the Earth's su…
Deep LearningGraph Neural NetworkPredictionAnalyzing High-Resolution Clouds and Convection using Multi-Channel VAEs
Understanding the details of small-scale convection and storm formation is crucial to accurately represent the larger-scale planetary dynamics. Presently, atmospheric scientists run high-resolution, storm-resolving simul…
Vocal Bursts Intensity PredictionBreaking the Statistical Similarity Trap in Extreme Convection Detection
Current evaluation metrics for deep learning weather models create a "Statistical Similarity Trap", rewarding blurry predictions while missing rare, high-impact events. We provide quantitative evidence of this trap, show…
Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model
An ensemble post-processing method is developed for the probabilistic prediction of severe weather (tornadoes, hail, and wind gusts) over the conterminous United States (CONUS). The method combines conditional generative…
Uncertainty Quantification