Synthetic aperture radar (SAR) is a novel dataset that enables deep exploration across a broad range of agricultural applications. But working with powerful SAR sensors like Sentinel-1 can be challenging, often requiring significant processing to derive valuable insights.
In this recorded technical workshop, we explore globally processed Sentinel-1 (S1) SAR and InSAR data products available on the Descartes Labs Platform. We've simplified working with S1 data by processing the entire catalog available from the European Space Agency (ESA), from raw data (SLCs) to a variety of derived level 1 and 2 data products. These data products enable rapid iteration in research and development workflows. We examine how users can best access and interact with them to build meaningful agronomic applications.
Register to access this on-demand recording.
Dylan is an applied scientist focused on process, visualization, and storytelling. He's passionate about creating value for end-users and creating compelling data driven narratives. Dylan studied at Seattle University and the University of Maryland Baltimore County, and has a background in mathematics and environmental science.
Tom leads Descartes Labs’ Agriculture business, bringing the benefits of geospatial data science to merchant traders and inputs players. Prior to Descartes Labs, Tom led global business development and the US office of Coalition, an S&P Global company. He has a degree in history and political science from Oxford University.
As a geospatial data engineer, Piyush applies concepts from Mathematics and Engineering to solve complex Earth Science problems. His focus is on radar imaging systems and radar interferometry, with experience in spatial databases, mapping, real-time GPS tracking. Piyush holds a PhD from Stanford.
Sentinel-1 Gamma0 RVI time series clusters compared to the USDA cropland data layer. These clusters demonstrate the ability of S1 Gamma0 to differentiate between land cover types (in this case crops).
Sentinel-1 InSAR coherence time series for corn and soy pixels over the agricultural area of interest. Peaks in coherence likely represent times when the soil is undisturbed (for example the period of time between tilling and planting). Troughs in coherence over agricultural land cover typically represent periods of time where vegetation is exposed.