Integrating SPOT-5 time series, crop growth modeling and expert knowledge for monitoring agricultural practices — The case of sugarcane harvest on Reunion Island

• Published in: Remote sensing of environment Vol. 113; no. 10; pp. 2052 - 2061
• Main Authors: El Hajj, Mahmoud, Bégué, Agnès, Guillaume, Serge, Martiné, Jean-François
• Format: Journal Article
• Language: English
• Published: New York, NY Elsevier Inc 01.10.2009; Elsevier
• Subjects: Agronomy. Soil science and plant productions; Applied geophysics; Biological and medical sciences; Change detection; Cropping system; Earth sciences; Earth, ocean, space; Environmental Sciences; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; Fusion; Fuzzy; Generalities. Biometrics, experimentation. Remote sensing; Internal geophysics; Multi-temporal; Mutli-source; NDVI; Remote sensing; Indian Ocean Islands; Mascarene Islands; Indian Ocean; Reunion Island; ISW, Indian Ocean, Mascarene Is., Reunion; Mutli-source; Change detection; Cropping system; Multi-temporal; Fuzzy; Fusion; NDVI; time series analysis; Monocotyledones; Vegetation index; Spot; Spatial scale; Information; Modeling; Gramineae; Angiospermae; radiometry; spatial resolution; Cultivated plant; Plant production; Cultural practice; Space remote sensing; Satellite observation; monitoring; Acquisition; decision support systems; Saccharum officinarum; Spermatophyta; Sugar cane; growth; Multidate observation; LA REUNION; CHANGE DETECTION; FUSION; SPOT5; MUTLI-SOURCE; FUZZY; CROPPING SYSTEM; MULTI-TEMPORAL
• ISSN: 0034-4257; 1879-0704
• DOI: 10.1016/j.rse.2009.04.009

Time series of optical satellite images acquired at high spatial resolution is a potentially useful source of information for monitoring agricultural practices. However, the information extracted from this source is often hampered by missing acquisitions or uncertain radiometric values. This paper presents a novel approach that addresses this issue by combining time series of satellite images with information from crop growth modeling and expert knowledge. In a fuzzy framework, a decision support system that combines multi-source information was designed to automatically detect the sugarcane harvest at field scale. The formalism that we used deals with the imprecision of the data and the approximation of expert reasoning. System performances were analyzed using a time series of SPOT-5 images. Results obtained were in substantial agreement with ground truth data: overall accuracy reached 97.80% with stability values exceeding 89.21% for all decisions. The contribution of fuzzy sets to overall accuracy reached 15.08%. The approach outlined in this paper is very promising and could be very useful for other agricultural applications.