CAS-Climate: CAREER: Analytical methods for understanding and predicting agricultural flash droughts in a changing climate

突发性干旱是一种极端水文气候事件，具有突然发生、迅速加剧和对社区造成破坏性影响的特点。它迅速耗尽土壤水分，对非灌溉土地上的植物生长和农业生产造成严重的水和热压力。由于突发性干旱的发生和发展速度快，导致或影响其形成的陆-海-气因素复杂，因此预测具有挑战性。这个相互关联的活动项目研究突发性干旱的原因和可预测性，改进其预测和预测，评估其对气候变化的影响，并促进教育和外联活动。拟议的研究和教育项目将造福社会，特别是易受干旱影响的农业社区，并为更明智的干旱管理、气候适应和提高抗灾能力铺平道路。该研究将利用基于机器学习的因果推理分析来解开农业突发性干旱的潜在驱动因素，利用深度学习方法开发和评估亚季节时间尺度上的农业突发性干旱预测，并基于耦合环流模型大集合评估当代和未来气候下农业突发性干旱的变化。这些研究目标将与一项教育计划相结合，重点是通过4-H（“头脑、心灵、手和健康”）计划开发和实施关于干旱的创新课程，通过气候学习网络与农业利益相关者一起举办分季节预报和决策研讨会，指导本科生和研究生，并让研究生参与除研究外的教育活动。该项目的成果将有助于提高对区域尺度干旱的认识和预测，并将为分析更广泛类别的极端气候事件提供一个框架，该框架将广泛适用于世界各地的不同地点。该奖项由水文科学、气候和大规模动力学项目共同资助。该奖项反映了美国国家科学基金会的法定使命，并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，被认为值得支持。

Flash drought is an extreme hydro-climate event characterized by sudden onset, rapid intensification, and devastating impact on communities. It rapidly depletes soil moisture, posing significant water and heat stresses for plant growth and agricultural productions over non-irrigated lands. Flash drought is challenging to predict because of its fast onset and development, and complex land-ocean-atmosphere factors that contribute to or affect their formation. This project of interlinked activities study the causes and predictability of flash droughts, improve their forecasts and projections, assess their impact on climate change, and promote education and outreach. The proposed research and educational programs will benefit society, especially agricultural communities vulnerable to droughts, and pave the way towards better-informed drought management, climate adaptation and improved resilience.The research will disentangle underlying drivers of agricultural flash droughts using machine learning-based causal inference analysis, develop and evaluate agricultural flash drought forecasts at the sub-seasonal timescale using deep learning approaches, and assess changes in agricultural flash drought under contemporary and future climate, based on coupled general circulation models large ensembles. These research objectives will be integrated with an education plan focusing on developing and implementing innovative lessons on drought through the 4-H (“head, heart, hands, and health”) program, conducting workshops on sub-seasonal forecasts and decision making with agricultural stakeholders through the climate learning network, mentoring undergraduate and graduate students, and involving graduate students in educational activities besides research. Deliverables from this project will contribute to an improved understanding and predictions of droughts at the regional scale and will provide a framework for analyses of a broader class of extreme climate events, which will be broadly applicable at different locations around the world. This award is co-funded by the Hydrologic Sciences and Climate and Large-Scale Dynamics programs.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.