Samuel Taylor is a doctoral student in the School of Earth, Environment, and Sustainability Sciences. His research focuses on remote sensing of inland water quality, with an emphasis on monitoring and predicting harmful algal blooms across optically complex lake systems. He integrates hyperspectral and multispectral imagery, in-situ spectroscopy, fluorescence probing, real-time sensor networks, and laboratory and decadal citizen-science water quality datasets into unified frameworks that leverage machine learning for more reliable bloom forecasting. By combining long-term water quality data with near-real-time satellite observations, his work aims to develop new monitoring strategies that help lake managers and communities respond more quickly to public health and ecological threats than current methods allow.

Samuel has experience as a research and teaching assistant at the University of Iowa. He has designed Python methods for measuring plant height in high-throughput, sub-centimeter resolution LiDAR datasets. He has also worked alongside the Donald Danforth Plant Science Center, where he contributed to the development of PlantCV-Geospatial, an open-source Python library for plant phenotyping and geospatial analysis. He has also used Google Earth Engine to create a time-series analysis of field-scale application of exogenous organic matter with multispectral satellite imagery. His past teaching experience at the University of Iowa includes Foundations of GIS, Introduction to Environmental Science, and Foundations of Environmental Science, and he has mentored student researchers through the Latham Science Engagement Initiative.