Mahmoudi Sadaf, Moftakhari Hamed, Muñoz David F, Sweet William, Moradkhani Hamid
Center for Complex Hydrosystems Research, The University of Alabama, Tuscaloosa, AL, USA.
Department of Civil, Construction, and Environmental Engineering, The University of Alabama, Tuscaloosa, AL, USA.
Nat Commun. 2024 May 18;15(1):4251. doi: 10.1038/s41467-024-48545-1.
Sea level rise (SLR) affects coastal flood regimes and poses serious challenges to flood risk management, particularly on ungauged coasts. To address the challenge of monitoring SLR at local scales, we propose a high tide flood (HTF) thresholding system that leverages machine learning (ML) techniques to estimate SLR and HTF thresholds at a relatively fine spatial resolution (10 km) along the United States' coastlines. The proposed system, complementing conventional linear- and point-based estimations of HTF thresholds and SLR rates, can estimate these values at ungauged stretches of the coast. Trained and validated against National Oceanic and Atmospheric Administration (NOAA) gauge data, our system demonstrates promising skills with an average Kling-Gupta Efficiency (KGE) of 0.77. The results can raise community awareness about SLR impacts by documenting the chronic signal of HTF and providing useful information for adaptation planning. The findings encourage further application of ML in achieving spatially distributed thresholds.
海平面上升（SLR）影响着沿海洪水状况，并给洪水风险管理带来严峻挑战，在数据缺乏的海岸地区尤为如此。为应对在局部尺度监测海平面上升的挑战，我们提出了一种高潮洪水（HTF）阈值系统，该系统利用机器学习（ML）技术，以相对精细的空间分辨率（10公里）估算美国海岸线沿线的海平面上升和高潮洪水阈值。该系统对传统的基于线性和点的高潮洪水阈值及海平面上升速率估算起到补充作用，能够在数据缺乏的海岸段估算这些数值。通过针对美国国家海洋和大气管理局（NOAA）测量数据进行训练和验证，我们的系统表现出良好的性能，平均克林 - 古普塔效率（KGE）为0.77。这些结果通过记录高潮洪水的长期信号并为适应规划提供有用信息，可提高社区对海平面上升影响的认识。这些发现鼓励进一步应用机器学习来获取空间分布的阈值。
