Deep Learning Image Segmentation for Atmospheric Rivers

Abstract

The identification of atmospheric rivers (ARs) is crucial for weather and climate predictions as they are often associated with severe storm systems and extreme precipitation, which can cause large impacts on the society. This study presents a deep learning model, termed ARDetect, for image segmentation of ARs using ERA5 data from 1960 to 2020 with labels obtained from the TempestExtremes tracking algorithm. ARDetect is a CNN-based UNet model, with its structure having been optimized using automatic hyperparameter tuning. Inputs to ARDetect were selected to be the integrated water vapour transport (IVT) and total column water (TCW) fields, as well as the AR mask from TempestExtremes from the previous timestep to the one being considered. ARDetect achieved a mean intersection-over-union (mIoU) rate of 89.04% for ARs, indicating its high accuracy in identifying these weather patterns and a superior performance than most deep learning-based models for AR detection. In addition, ARDetect can be executed faster than the TempestExtremes method (seconds vs minutes) for the same period. This provides a significant benefit for online AR detection, especially for high-resolution global models. An ensemble of 10 models, each trained on the same dataset but having different starting weights, was used to further improve on the performance produced by ARDetect, thus demonstrating the importance of model diversity in improving performance. ARDetect provides an effective and fast deep learning-based model for researchers and weather forecasters to better detect and understand ARs, which have significant impacts on weather-related events such as floods and droughts.

A derecho climatology (2004–2021) in the United States based on machine learning identification of bow echoes

“…U-Net models were originally developed for the segmentation of biomedical imagery but have been applied to image segmentation problems in other fields and are broadly useful for any image-to-image mapping tasks where the input and target data are the same (or similar) size and shape and merging multiresolution information from the input data is important. U-Net CNNs have been applied to a myriad of problems in the atmospheric sciences, such as segmentation (Galea et al, 2024;Kumler-Bonfanti et al, 2020), super resolution (Geiss and Hardin, 2020;White et al, 2024), physics parameterization (Lagerquist et al, 2021), downscaling (Sha et al, 2020), and weather forecasting (Weyn et al, 2021).…”