Share Email Print
cover

Proceedings Paper

Mapping crop based on phenological characteristics using time-series NDVI of operational land imager data in Tadla irrigated perimeter, Morocco
Author(s): Jamal-eddine Ouzemou; Abderrazak El Harti; Ali EL Moujahid; Naima Bouch; Rabii El Ouazzani; Rachid Lhissou; El Mostafa Bachaoui
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Morocco is a primarily arid to semi-arid country. These climatic conditions make irrigation an imperative and inevitable technique. Especially, agriculture has a paramount importance for the national economy. Retrieving of crops and their location as well as their spatial extent is useful information for agricultural planning and better management of irrigation water resource. Remote sensing technology was often used in management and agricultural research. Indeed, it's allows crops extraction and mapping based on phenological characteristics, as well as yield estimation. The study area of this work is the Tadla irrigated perimeter which is characterized by heterogeneous areas and extremely small size fields. Our principal objectives are: (1) the delimitation of the major crops for a good water management, (2) the insulation of sugar beet parcels for modeling its yields. To achieve the traced goals, we have used Landsat-8 OLI (Operational Land Imager) data pan-sharpened to 15 m. Spectral Angle Mapper (SAM) and Support Vector Machine (SVM) classifications were applied to the Normalized Difference Vegetation Index (NDVI) time-series of 10 periods. Classifications were calculated for a site of more than 124000 ha. This site was divided into two parts: the first part for selecting, training datasets and the second one for validating the classification results. The SVM and SAM methods classified the principal crops with overall accuracies of 85.27% and 57.17% respectively, and kappa coefficient of 80% and 43% respectively. The study showed the potential of using time-series OLI NDVI data for mapping different crops in irrigated, heterogeneous and undersized parcels in arid and semi-arid environment.

Paper Details

Date Published: 14 October 2015
PDF: 7 pages
Proc. SPIE 9637, Remote Sensing for Agriculture, Ecosystems, and Hydrology XVII, 96372G (14 October 2015); doi: 10.1117/12.2194466
Show Author Affiliations
Jamal-eddine Ouzemou, Faculty of Science and Technology Beni Mellal (Morocco)
Abderrazak El Harti, Faculty of Science and Technology Beni Mellal (Morocco)
Ali EL Moujahid, COSUMAR SUTA (Morocco)
Naima Bouch, COSUMAR SUTA (Morocco)
Rabii El Ouazzani, COSUMAR SUTA (Morocco)
Rachid Lhissou, Faculty of Science and Technology Beni Mellal (Morocco)
El Mostafa Bachaoui, Faculty of Science and Technology Beni Mellal (Morocco)


Published in SPIE Proceedings Vol. 9637:
Remote Sensing for Agriculture, Ecosystems, and Hydrology XVII
Christopher M. U. Neale; Antonino Maltese, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray