Remote monitoring of agricultural systems using NDVI time series and machine learning methods: a tool for an adaptive ag
- PDF / 14,466,167 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 21 Downloads / 186 Views
ORIGINAL PAPER
Remote monitoring of agricultural systems using NDVI time series and machine learning methods: a tool for an adaptive agricultural policy Youssef Lebrini 1,2 & Abdelghani Boudhar 1,3 & Abdelaziz Htitiou 1,2 Lahouari Bounoua 4 & Tarik Benabdelouahab 2
&
Rachid Hadria 2
&
Hayat Lionboui 2 &
Received: 12 October 2019 / Accepted: 29 July 2020 # Saudi Society for Geosciences 2020
Abstract This study aims to provide accurate information about changes in agricultural systems (AS) using phenological metrics derived from the NDVI time series. Use of such information could help land managers optimize land use choices and monitor the status of agricultural lands, under a variety of environmental and socioeconomic conditions. For this purpose, the Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI data were used to derive phenological metrics over the Oum Er-Rbia basin (central Morocco). Random forest (RF), support vector machine (SVM), and K-nearest neighbor (KNN) classifiers were explored and compared on their ability to classify AS classes over the study area. Four main AS classes have been considered: (1) irrigated annual crop (IAC), (2) irrigated perennial crop (IPC), (3) rainfed area (RA), and (4) fallow (FA). By comparing the accuracy of the three classifiers, the RF method showed the best performance with an overall accuracy of 0.97 and kappa coefficient of 0.96. The RF method was then chosen to examine time variations in AS over a 16-year period (2000–2016). The AS main variations were detected and evaluated for the four AS classes. These variations have been found to be linked well with other indicators of local agricultural land management, as well as the historical agricultural drought changes over the study area. Overall, the results present a tool for decision makers to improve agricultural management and provide a different perspective in understanding the spatiotemporal dynamics of agricultural systems. Keywords Agricultural systems . Change monitoring . Phenological metrics . NDVI time series . Machine learning . MODIS
Introduction Monitoring agricultural systems (AS) is a major task, particularly in arid and semi-arid regions where water scarcity and droughts are frequent (Benabdelouahab et al. 2020; Gu et al. Responsible Editor: Biswajeet Pradhan * Youssef Lebrini [email protected] 1
Water Resources Management and Valorization and Remote Sensing Team, Faculty of Sciences and Techniques, Sultan Moulay Slimane University, Beni Mellal, Morocco
2
National Institute of Agronomic Research, Rabat, Morocco
3
Center for Remote Sensing Applications (CRSA), Mohammed VI Polytechnic University, Ben Guerir, Morocco
4
Biospheric Sciences Laboratory, Code 618, NASA, Goddard Space Flight Center, Greenbelt, MD, USA
2007; Winkler et al. 2017). However, large-scale information about agricultural systems is essential for land use monitoring and management besides making an informed decision on food security and sustainability (Benabdelouahab et al. 2019b; Hentze et al. 2016; Lebrini et al
Data Loading...
