Publications

Luciani, R; Laneve, G; JahJah, M (2019). Agricultural Monitoring, an Automatic Procedure for Crop Mapping and Yield Estimation: The Great Rift Valley of Kenya Case. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 12(7), 2196-2208.

Abstract
Agricultural activities conducted in the Great Rift Valley of Kenya show a significant decline of productivity levels. This phenomenon is mainly related to limited availability of water resources, lack of supporting irrigation, and harvesting techniques ineffectiveness. Production risks reduction is closely related with a better use of water resources and a better understanding of the effects resulting from the multiple interactions between climate, agricultural vegetation, soil type, and crops management techniques. In this paper, 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 information extracted from satellite imagery combined with crop calendar and supported by agro-ecological zoning (AEZ) in accurate crop classification and monitoring. Vegetation indices extracted from Landsat 8 imagery are capable to track the vegetation development through the year, then phenological profiles can be extracted and implemented into a multitemporal automatic classification process to detect agricultural areas and to discriminate among different crop species. The phenological profiles extracted by satellite imagery are compared with crop calendar data compiled by FAO for the area of interest. The classification procedure is supported by AEZs based on crop modeling and environmental matching procedures in order to identify crop-specific environmental limitations under assumed levels of inputs and management conditions. The FAO crop water productivity model AquaCrop is calibrated for wheat and maize yield mapping in the central highland of Kenya, handling both environmental and phenological data. The combined use of phenological data and AEZs results in a robust methodology with a classification overall accuracy of 91.35%. A good model performance is obtained relative to yield predictions, with R of 0.69 and 0.72.

DOI:
10.1109/JSTARS.2019.2921437

ISSN:
1939-1404