Research

CRS research stands out for its highly interdisciplinary and collaborative nature. We are unique in our approach, combining basic and applied research to support the application of Remote Sensing and Geospatial Artificial Intelligence (GeoAI) technologies in agriculture and natural resources, integrating ground-based and satellite data. This unique data-driven approach allows us to address critical challenges in agriculture, food security, and natural resources management in Florida and elsewhere.

• Our current research areas are not just theoretical but have practical applications of state, national, and global significance related to sustainable agriculture and natural resources:
• Our focus is on using remote sensing data and geospatial AI to enhance estimates of soil, nutrients, water, and vegetation properties.
• We work to enhance the understanding of soil moisture dynamics. Downscaling soil moisture data allows us to increase the level of detail in satellite data that covers extensive areas. This way, we get a more detailed picture of what's happening at the individual farm or agricultural field.
• Our data collection combines ground-based and satellite-based sensors to gather valuable information.
• Using visible and infrared observations, we analyze land cover changes, map crop yields, and monitor invasive species.
• We investigate the growth of bio-energy crops and develop models to accurately estimate their biomass.

By leveraging UF's high-performance computing capabilities and interdisciplinary strengths across fields, we advance agriculture-related remote sensing research.

Remote Sensing in Agriculture

Higher temperatures can prevent the growth and yield of many crops. As global temperatures rise due to climate change, ensuring enough food for a growing population becomes critical. Research on how soil moisture affects crop yields is more important than ever. By 2050, the global population is estimated to reach 9 billion, putting immense pressure on food production.

Our research combines satellite data, in-situ measurements, and machine learning AI-powered geospatial modeling with focused applications to major challenges in agriculture. Specifically, we use remote sensing to enhance our understanding of soil moisture, vegetation conditions, and irrigation demands in the context of sustainable agriculture practices and rising temperatures due to climate variability and change. Using satellite data, we develop methodologies to improve our knowledge of soil moisture, crop growth, water resources, and agricultural production.

Our research is centered on developing new methods and advanced algorithms for monitoring agriculture, soil, and water resources using remote sensing, GIS, and AI-based geospatial tools.

Key Components of Our Research:

• Remote Sensing Algorithms: We develop bio-physically-based algorithms for accurate remote sensing data extraction and analysis.
• Spatial Downscaling and Disaggregation: We refine coarse-resolution satellite data into fine-scale data using additional remote sensing and ground-based, in situ observations.
• Data Assimilation: We integrate satellite and sensor data into models to improve soil moisture, crop growth, and yield estimates.

Our research includes using microwave observations, which are highly sensitive to changes in soil and vegetation moisture. We also use ground-based microwave and micro-meteorological sensors to monitor dynamic changes in soil and vegetation conditions. Combining fine-resolution remote sensing observations with crop growth models enhances the accuracy of soil moisture and crop yield estimates.
 
Read below to learn more about our selected current and previous research projects.