Excellence in Research: Understanding the interactions of terrestrial and freshwater systems for developing a data-driven decision-making framework to manage Algal Blooms

人类的营养物来源，如污水处理厂的点排放，以及农业和城市地区富含营养物的径流，是有害藻华的驱动因素。保护实践，也称为最佳管理实践，有时也称为绿色基础设施，是减少城市流域径流和养分负荷的战略。最佳管理做法有可能通过减少上游城市流域的营养物质输出来控制淡水湖中的有害藻华。然而，人们对最佳管理实践的实施、营养物的景观输出和有害藻华的发生之间的关系缺乏了解。本研究的总体目标是了解水文、气象、生物、物理和地球化学过程对营养物质景观输出的影响，并评估最佳管理措施对有害藻华发生的影响。该项目旨在创建一个决策支持工具，为城市流域确定最具成本效益的最佳管理实践，以减少营养物质的流失，并随后控制有害的藻华。该项目将在整个规划过程中涉及主要合作伙伴、社区成员和利益相关者，以确保最终战略计划的广泛效用。该项目还将为来自历史上代表性不足的群体的研究生和本科生提供教育活动，目标是培养下一代专业人士的多样性。该项目的成果将纳入PI协调的教育活动中，对佛罗里达州的K-12教育工作者进行可持续水管理教育，目标是开发一套课程，供佛罗里达州农村地区资源不足的中学教师使用。本提案的研究目标是：目标1 -更好地了解影响淡水湖景观养分输出的关键水文、气象、生物、物理和地球化学过程；目标2 -利用物理信息的机器学习，根据从陆地系统中了解到的养分通量和养分污染之间的关系，预测有害藻华的发生；目标3 -设计一个创新的数据驱动的决策框架，以评估下游水体中有害藻华管理的保护措施的有效性。本研究的目标是通过应用物理知识的机器学习和开发数据驱动的决策框架，揭示影响陆地系统向淡水湖输送和通量的相互作用的水文、气象、生物、物理和地球化学过程。该项目将为陆地系统制定水质保护战略，促进淡水生态系统的可持续性。该项目将水文学、数据科学和数学优化的学科研究联系起来。研究小组将采用一种系统级方法，通过趋同合作推动，目标是全面了解综合陆地淡水系统。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。

Human sources of nutrients, such as point discharges from wastewater treatment plants, and nutrient rich runoff from agriculture and urban areas, are driving factors of harmful algal blooms. Conservation practices, also called best management practices and sometimes green infrastructure, are strategies to reduce runoff and nutrient loads from urban watersheds. Best management practices have the potential to control harmful algal blooms in freshwater lakes by reducing nutrient exports in upstream urban watersheds. However, there is a lack of understanding of the relationships among the implementation of best management practices, landscape export of nutrients, and the occurrences of harmful algal blooms. The overarching goal of this research is to understand the hydrological, meteorological, biological, physical, and geochemical processes affecting the landscape export of nutrients and to evaluate the effects of best management practices on the occurrence of harmful algal blooms. This project aims to create a decision support tool for determining the most cost-effective best management practices for urban watersheds to reduce nutrient escape and subsequently control harmful algal blooms. The project will involve key partners, community members, and stakeholders throughout the planning process to ensure broad utility of the resulting strategic plan. The project will also provide educational activities for graduate and undergraduate students from historically underrepresented groups, with the goal of cultivating diversity for the next generation of professionals. The outcome of this project will be incorporated into the educational activities coordinated by the PI to educate the K-12 educators in Florida on sustainable water management with the goal of developing a curriculum that can be used by teachers from under-resourced middle schools in rural areas of Florida.The research objectives of this proposal are: Objective 1 - provide a better understanding of the key hydrological, meteorological, biological, physical, and geochemical processes affecting landscape nutrient export in freshwater lakes; Objective 2 - predict occurrences of harmful algal blooms based on learned relationships between nutrient fluxes and nutrient pollution from a terrestrial system using physics-informed machine learning; and Objective 3 - design an innovative data-driven decision-making framework for evaluating the effectiveness of conservation practices in managing harmful algal blooms in downstream water bodies. This research targets shedding light on the interactive hydrological, meteorological, biological, physical, and geochemical processes affecting the transport and flux of nutrients from terrestrial systems to freshwater lakes, by applying physics-informed machine learning and developing data-driven decision-making frameworks. The project will formulate water quality protection strategies for terrestrial systems that promote sustainability of freshwater ecosystems. The project will bridge disciplinary research on hydrology, data science, and mathematical optimization. The research team will use a system-level approach driven through convergent collaboration with the goal of providing a comprehensive understanding of integrated terrestrial freshwater systems.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.