Building a STEM research and education network of GIS and drone mapping for coastal seagrass monitoring

海草遭受多种威胁，包括可能损害生态系统的消耗性疾病，准确和最新的海草地图对于了解河口健康和对环境压力的适应能力至关重要。该项目推进了基础研究，使用无人机（无人机）绘制整个北方加州的海草地图，以检测疾病并分析海草健康和范围的时间趋势。该项目的一个重要重点是在少数民族服务机构和社区学院之间建立一个STEM网络，以促进合作和能力建设，每年在4年制大学和2年制社区学院培训和指导24名学生，为他们提供跨学科技能，如无人机驾驶，地理信息系统，海岸科学和科学传播。学生还发展专业网络和经验学习，促进长期参与STEM。目标是将这一培训计划扩展到社区组织、公民科学家和从业人员，旨在为沿海管理和海草保护做出贡献。有效、全面地监测海草疾病对海洋景观的影响，对于预测未来的生态影响和实施早期干预至关重要。然而，海草状况很少在空间和时间域中量化，并且传统的制图方法劳动密集型、昂贵或分辨率较粗。无人机成像结合地理信息系统是监测沿海海草生态系统的新兴技术，因为它们具有空间分辨率高，时间灵活性和成本效益。我们的项目利用带有可见光、多光谱和激光雷达传感器的多平台无人机系统，提供更准确的数据，以便更好地描绘和分类海草，并更有效地预测疾病。结合地面数据和现场采样，开发了基于无人机和GIS的海草生态系统综合监测平台。该平台有助于在重要的海草生境中检测单个叶片规模的疾病。我们的研究包括多平台无人机测绘，海草疾病的空间建模，海草床范围变化的时间分析，开发基于AI的图像分析用于物种分类和疾病检测，创建用于实时数据交换的云数据中心，该奖项反映了NSF的法定使命，并被认为值得支持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。

Seagrass suffers from several threats, including wasting disease, that could impair ecosystems, and accurate and up-to-date mapping of seagrass is critical for understanding estuary health and resilience to environmental stressors. This project advances fundamental research using Unmanned Aerial Vehicles (UAVs) to map seagrass across Northern California to detect disease and analyze temporal trends in seagrass health and extent. A significant focus of this project is creating a STEM network between minority-serving institutions and community colleges to foster collaborations and build capacity, training and mentoring 24 students in 4-year university and 2-year community colleges annually, providing them with interdisciplinary skills such as UAV piloting, GIS, coastal science, and scientific communication. Students also develop professional networks and experience study, promoting long-term engagement in STEM. The goal is to extend this training program to community organizations, citizen scientists, and practitioners, aiming to contribute to coastal management and seagrass conservation. Efficient, comprehensive monitoring of the seascape-scale impact of seagrass disease is essential to predict future ecological impacts and implement early interventions. However, seagrass conditions are rarely quantified in spatial and temporal domains, and traditional mapping methods are labor-intensive, expensive, or have a coarse resolution. UAV imaging combined with GIS are emerging technologies for monitoring coastal seagrass ecosystems because of their spatial high-resolution, temporal flexibility, and cost-efficiency. Our project utilizes multi-platform UAV systems with visible, multispectral, and LiDAR sensors to provide more accurate data for better delineation and classification of seagrass and predicting disease more effectively. Combined with ground data and in situ sampling, we develop a UAV and GIS-based platform for comprehensive monitoring of seagrass ecosystems. The platform aid in the detection of diseases at an individual leaf scale in prominent seagrass habitats. Our research includes multi-platform UAV mapping, spatial modeling of the seagrass disease, temporal analysis of seagrass bed extent changes, development of AI-based image analysis for species classification and disease detection, creation of a cloud data hub for real-time data exchange, and provision of research training and professional development opportunities for students.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.