Abubakar, M.A.; Chanzy, A.; Flamain, F.; Pouget, G.; Courault, D. Delineation of Orchard, Vineyard, and Olive Trees Based on Phenology Metrics Derived from Time Series of Sentinel-2. Remote Sens.2023, 15, 2420.
Abubakar, M.A.; Chanzy, A.; Flamain, F.; Pouget, G.; Courault, D. Delineation of Orchard, Vineyard, and Olive Trees Based on Phenology Metrics Derived from Time Series of Sentinel-2. Remote Sens. 2023, 15, 2420.
Cite as:
Abubakar, M.A.; Chanzy, A.; Flamain, F.; Pouget, G.; Courault, D. Delineation of Orchard, Vineyard, and Olive Trees Based on Phenology Metrics Derived from Time Series of Sentinel-2. Remote Sens.2023, 15, 2420.
Abubakar, M.A.; Chanzy, A.; Flamain, F.; Pouget, G.; Courault, D. Delineation of Orchard, Vineyard, and Olive Trees Based on Phenology Metrics Derived from Time Series of Sentinel-2. Remote Sens. 2023, 15, 2420.
Abstract
The characteristics of the Sentinel-2 mission with a decametric resolution and frequent acquisitions allow to improve the identification of crops. The majority of the studies on crop classification using RS were targeted at herbaceous and gramineous crop classes while fewer results were obtained on woody crops which present a strong variability in management practices that make their identification difficult. Thus, this study aimed to propose a rapid, accurate, and cost-effective analytical approach for the delineation of fruit orchards (OC), vineyards (VY), and olive groves (OL) in the Mediterranean (Southern France) considering two locations. A classification based on phenology metrics (PM) de-rived from temporal Sentinel-2 time series was developed to perform the classification. The PM were computed by fitting a double logistic model on temporal profiles of vegeta-tion indices to delineate OC, VY, and a DC class gathering all remaining surfaces. The generated PM were introduced in a random forest (RF) algorithm to identify woody crops across the two sites. The method was tested on different vegetation indices, the best results being obtained with the leaf area index (LAI). To delineate OL in the DC class, the tem-poral features of the green chlorophyll vegetation index (GCVI) were found to be the most appropriated with a typical drop of the signal during the mid-season (DOY 150-250). As a final result, we obtained an overall accuracy ranging from 89-96% and Kappa of 0.86-0.95 by considering each study site and year (2016-2021), separately. This accuracy is much better than applying the RF algorithm on the LAI times series, which led to a Kappa rang-ing between 0.3 and 0.52 and demonstrates the interest of using phenological traits rather than the raw time series of the RS data. The method can be well reproduced from one year to another. Moreover, it is possible to apply the classification model of a given year to an-other, keeping good accuracy. This is an interesting feature to reduce the burden of col-lecting ground truth information. On the contrary, the use of a classification model cali-brated in one site and applied to another led to a strong degradation of the classification accuracy. Woody crop phenology is dependent on site climatic conditions as well as the cultivar and management practices that can differ from one site to another.
Environmental and Earth Sciences, Environmental Science
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
