Deep Learning for Downscaling Tropical Cyclone Rainfall to Hazard-Relevant Spatial Scales
Deep Learning for Downscaling Tropical Cyclone Rainfall to Hazard-Relevant Spatial Scales
复制标题
DOI：
10.1029/2022jd038163
复制
发表时间：
2023-05-27
影响因子：
4.4
通讯作者：
Mitchell，Dann
中科院分区：
文献类型：
--
作者：
Vosper，Emily;Watson，Peter;Mitchell，Dann
洪水，部分由强降雨驱动，是最强烈的热带气旋（TC）造成死亡和损失的主要原因。由于热带气旋的降雨量在人为气候变化下将增加，因此准确估计极端降雨量以更好地支持短期和长期的抗灾工作至关重要。虽然高分辨率气候模型比低分辨率模型更好地捕捉TC统计数据，但它们的计算成本很高。这导致了准确捕获TC特征和生成足够大的模拟数据集以充分采样高影响，低概率事件之间的权衡。降尺度可以通过从相对便宜的低分辨率模型预测高分辨率特征来提供帮助。在这里，我们开发并评估了一组三个深度学习模型，用于将TC降雨降尺度到与灾害相关的空间尺度。我们使用多源加权加密降水观测产品的降雨，粗化分辨率为100 km，并应用我们的降尺度模型重现原始分辨率为100 km。我们发现，Wasserstein生成对抗网络能够捕获真实的空间结构和功率谱，并且整体表现最好，平均偏差在5%的观测值范围内。我们还表明，该模型可以很好地外推到最极端的风暴，这在训练中没有使用。
Flooding, driven in part by intense rainfall, is the leading cause of mortality and damages from the most intense tropical cyclones (TCs). With rainfall from TCs set to increase under anthropogenic climate change, it is critical to accurately estimate extreme rainfall to better support short‐term and long‐term resilience efforts. While high‐resolution climate models capture TC statistics better than low‐resolution models, they are computationally expensive. This leads to a trade‐off between capturing TC features accurately, and generating large enough simulation data sets to sufficiently sample high‐impact, low‐probability events. Downscaling can assist by predicting high‐resolution features from relatively cheap, low‐resolution models. Here, we develop and evaluate a set of three deep learning models for downscaling TC rainfall to hazard‐relevant spatial scales. We use rainfall from the Multi‐Source Weighted‐Ensemble Precipitation observational product at a coarsened resolution of ∼100 km, and apply our downscaling model to reproduce the original resolution of ∼10 km. We find that the Wasserstein Generative Adversarial Network is able to capture realistic spatial structures and power spectra and performs the best overall, with mean biases within 5% of observations. We also show that the model can perform well at extrapolating to the most extreme storms, which were not used in training.