Skip to main content
ARS Home » Southeast Area » Jonesboro, Arkansas » Delta Water Management Research » Research » Publications at this Location » Publication #354860

Research Project: Preserving Water Availability and Quality for Agriculture in the Lower Mississippi River Basin

Location: Delta Water Management Research

Title: Fusion of moderate resolution Earth observations for operational crop type mapping

Author
item Torbick, Nathan - Applied Geosolutions, Llc
item Huang, Xiaodong - Applied Geosolutions, Llc
item Ziniti, Beth - Applied Geosolutions, Llc
item Johnson, David - National Agricultural Statistical Service (NASS, USDA)
item Masek, Jeff - Nasa Goddard Institute For Space Studies
item Reba, Michele

Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/2/2018
Publication Date: 7/4/2018
Citation: Torbick, N., Huang, X., Ziniti, B., Johnson, D., Masek, J., Reba, M.L. 2018. Fusion of moderate resolution Earth observations for operational crop type mapping. Remote Sensing. 10(7):1-16. http://dx.doi.org/10.3390/rs10071058.
DOI: https://doi.org/10.3390/rs10071058

Interpretive Summary: Assessment and monitoring of crop type and extent is one of the most critical information needs for food security. Crop type inventory and within season estimates at moderate (<30m) resolution has been elusive in many regions due to lack of temporal frequency, clouds, and restrictive data policies. New opportunities exist from operational fusion of Landsat-8 Operational Land Imager (OLI), Sentinel-2 (A & B), and Sentinel-1 (A & B) which provide more frequent open access observations now that these satellites are fully operational. The goal of this research application was to compare Harmonized Landsat-8 Sentinel-2 (HLS), Sentinel-1 (S1), and combined radar and optical data in an operational, near-real time context. Outcomes show HLS achieved high accuracies and the ability to provide insight on crop location and extent within the crop season. Overall, the growth in availability of time dense moderate resolution data streams and different sensitivities of optical and radar data provide a mechanism for within season crop mapping and area estimates that can help improve food security.

Technical Abstract: Crop type inventory and within season estimates at moderate (<30m) resolution has been elusive in many regions due to lack of temporal frequency, clouds, and restrictive data policies. New opportunities exist from operational fusion of Landsat-8 Operational Land Imager (OLI), Sentinel-2 (A & B), and Sentinel-1 (A & B) which provide more frequent open access observations now that these satellites are fully operating. The overarching goal of this research application was to compare Harmonized Landsat-8 Sentinel-2 (HLS), Sentinel-1 (S1), and combined radar and optical data in an operational, near-real time context. We evaluated the ability of these EO across major crops in four case study regions in United States (US) production hot spots. Hindcast time series combinations of these EO were fed into random forest classifiers trained with crop cover type information from the Cropland Data Layer (CDL). Outcomes show HLS achieved high accuracies and the ability to provide insight on crop location and extent within the crop season. HLS fused with S1 had the highest accuracy although the contributions were minimal at times and crop dependent. Overall, the growth in availability of time dense moderate resolution data streams and different sensitivities of optical and radar data provide a mechanism for within season crop mapping and area estimates that can help improve food security.