Using Deep Learning for an Analysis of Atmospheric Rivers in a High‐Resolution Large Ensemble Climate Data Set

There is currently large uncertainty over the impacts of climate change on precipitation trends over the US west coast. Atmospheric rivers (ARs) are a significant source of US west coast precipitation and trends in ARs can provide insight into future precipitation trends. There are already a variety of different methods used to identify ARs, but many are used in contexts that are often difficult to apply to large climate datasets due to their computational cost and requirement of integrated vapor transport as an input variable, which can be expensive to compute in climate models at high temporal frequencies. Using deep learning (DL) to track ARs is a unique approach that can alleviate some of the computational challenges that exist in more traditional methods. However, some questions still remain regarding its flexibility and robustness. This research investigates the consistency of a DL methodology of tracking ARs with more established algorithms to demonstrate its high‐level performance for future studies. Plain Language Summary Atmospheric rivers (ARs) are long corridors of water vapor in the lower atmosphere that are associated with a large amount of precipitation on the US west coast. They are important to investigate in future climate change scenarios. To further understand them in climate change scenarios, they must be tracked in large datasets. We demonstrate the efficiency, effectiveness, and flexibility of a machine learning tracking method by comparing it to more established existing tracking methods. This method applies particularly well to large climate datasets and can be useful for future studies. Key Points CG‐Climate is an effective and efficient way to track atmospheric rivers in large datasets CG‐Climate is flexible with varying spatial resolutions and domains Human hand labels are effective in identifying atmospheric river events in the correct location, but have a spatial area bias