Open-source software for satellite-based crop health monitoring

Authors: Kim, James

Submitted to: Journal of Biosystems Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/13/2024
Publication Date: 11/27/2024
Citation: Kim, J.Y. 2024. Open-source software for satellite-based crop health monitoring. Journal of Biosystems Engineering. 2024. https://doi.org/10.1007/s42853-024-00242-z.
DOI: https://doi.org/10.1007/s42853-024-00242-z

Interpretive Summary: Satellites can cover a large area in a short time with spectral, spatial, and temporal ranges of images and thus are suitable for agriculture applications in spatiotemporal assessment of crop fields, wildlife conservation, and natural disasters. Transforming satellite imagery to gain insight into crop health is challenging due to the abundance of small satellite imagery and inconsistent spectral signature in time-series images due to the atmospheric interference. In this study, image data was refined by features of time and area of interest and cloudy covers. Open-source software called iCalendar was developed for crop health monitoring by automating data processing of satellite images and creating a seasonal vegetation profile and a field map calendar. This monitoring system offers significant improvement to in-season crop health assessment, thereby promoting new management for crop productivity and protection.

Technical Abstract: Timely information on agricultural crops is essential to support informed crop management decisions. Satellite remote sensing technology offers a new paradigm for monitoring agricultural crops at large scale. Landsat, Sentinel, and Planet Scope 2 (PS2) imagery offer global imagery data in various spectrums with up to 3-m resolution and facilitates agricultural assessment for markets and food security. Daily access to satellite imagery from PS2 allows opportunities to continuously monitor agricultural fields for the crop heath and disease progress. Application programing interface (API) was used to automate the image queuing, activation, and download based on user-defined time and area of interest and field borders. The API was refined to filter unusable data such as multiples of clipped images and duplicates of tile images. Open-source software, iCalendar, was developed for high throughput image analysis and visualization of a vegetation profile and a field map calendar that are key sources of crop production cycle. The satellite image-based plant monitoring system provided a sustainable solution for spatiotemporal field observation to monitor plant health and stress progression, and thus helps enabling large scale crop monitoring for end-users to remotely monitor fields with a crop health alert.