Mapping crop based on phenological characteristics using time-series NDVI of operational land imager data in Tadla irrigated perimeter, Morocco

Jamal-eddine Ouzemou; Abderrazak El Harti; Ali EL Moujahid; Naima Bouch; Rabii El Ouazzani; Rachid Lhissou; El Mostafa Bachaoui

doi:10.1117/12.2194466

14 October 2015 Mapping crop based on phenological characteristics using time-series NDVI of operational land imager data in Tadla irrigated perimeter, Morocco

Jamal-eddine Ouzemou, Abderrazak El Harti, Ali EL Moujahid, Naima Bouch, Rabii El Ouazzani, Rachid Lhissou, El Mostafa Bachaoui

Author Affiliations +

Proceedings Volume 9637, Remote Sensing for Agriculture, Ecosystems, and Hydrology XVII; 96372G (2015) https://doi.org/10.1117/12.2194466
Event: SPIE Remote Sensing, 2015, Toulouse, France

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.

Citation Download Citation

Jamal-eddine Ouzemou, Abderrazak El Harti, Ali EL Moujahid, Naima Bouch, Rabii El Ouazzani, Rachid Lhissou, and El Mostafa Bachaoui "Mapping crop based on phenological characteristics using time-series NDVI of operational land imager data in Tadla irrigated perimeter, Morocco", Proc. SPIE 9637, Remote Sensing for Agriculture, Ecosystems, and Hydrology XVII, 96372G (14 October 2015); https://doi.org/10.1117/12.2194466

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available