Crop Fields Classification Based on in Situ Phenological Metrics

Abstract

Agricultural activities conducted in the Great Rift Valley of Kenya, show a significant decline of productivity levels. In this study, a remote and automatic agricultural monitoring system is presented as an effective alternative to the most traditional in situ measurements and observations. We investigated the use of phenological variables and metrics extracted from satellite in accurate crop classification and monitoring. Vegetation indices extracted from Landsat 8 imagery are capable to track the vegetation development through the year and from them the phenological profile can be retrieved and implemented into a multi-temporal automatic classification process to detect agricultural vegetated areas and to discriminate among different crop species. The phenological profiles extracted by satellite images were compared with crop calendar data, compiled by FAO for the area of interest.