Track D: Hidden Water and Extreme Events: HydroGEN, A Physically Rigorous Machine Learning Platform for Hydrologic Scenario Generation

轨道 D：隐藏的水和极端事件：HydroGEN，一个用于水文情景生成的物理严格的机器学习平台

• 批准号: 2134892
• 负责人: Laura Condon
• 金额: $ 500万
• 依托单位: University of Arizona
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2134892&HistoricalAwards=false
• 关键词: Track; Hidden; Water; Extreme; Events

Water is the driving force behind extreme events like floods, droughts and wildfires. These events have cost the US $234.3B in damages just in the past three years, and this figure is projected to increase. Recent events like the record setting wildfires in California and the mega drought on the Colorado river are merely the latest illustrations. Historical data are no longer a reliable guide for the risks we will face in the future. This project addresses the uncertainty that poses a huge challenge for decision makers. HydroGEN is a web-based machine learning (ML) platform that generates custom hydrologic scenarios on demand. It combines powerful physics-based simulations with ML and observations to provide customizable scenarios from the bedrock through the treetops. Without any prior modeling experience, water managers and planners can directly manipulate state-of-the-art tools to explore scenarios that matter to them.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

水是洪水、干旱和野火等极端事件背后的驱动力。这些事件仅在过去三年就造成了2343亿美元的损失，预计这一数字还会增加。最近发生的事件，如加州创纪录的野火和科罗拉多河的特大干旱，只是最新的例证。历史数据不再是我们未来面临的风险的可靠指南。该项目解决了对决策者构成巨大挑战的不确定性。HydroGEN是一个基于Web的机器学习（ML）平台，可按需生成自定义水文情景。它将强大的基于物理的模拟与ML和观察相结合，以提供从基岩到树梢的可定制场景。在没有任何建模经验的情况下，水资源管理者和规划者可以直接使用最先进的工具来探索对他们重要的情景。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的知识价值和更广泛的影响审查标准进行评估来支持。

项目成果

Training machine learning with physics-based simulations to predict 2D soil moisture fields in a changing climate

通过基于物理的模拟训练机器学习，以预测气候变化下的二维土壤湿度场

• DOI: 10.3389/frwa.2022.927113
• 发表时间: 2022
• 期刊: Frontiers in Water
• 影响因子: 2.9
• 作者: Leonarduzzi, Elena;Tran, Hoang;Bansal, Vineet;Hull, Robert B.;De la Fuente, Luis;Bearup, Lindsay A.;Melchior, Peter;Condon, Laura E.;Maxwell, Reed M.
• 通讯作者: Maxwell, Reed M.