ABSTRACT

Argania spinosa also known as the argan tree is an endemic plant of Morocco. Despite having the ability to subsist in extreme drought conditions, it is threatened by soil land clearing, overexploitation, and absence of natural regeneration, causing a worrying decline in both spatial extent and density. The spatial extent of dryland forests is debated, as estimates of forest areas in drylands are uncertain. The present study aims to map and locate the spatial distribution of the argan trees at Smimou community located in Essaouira province, south-eastern Morocco, using satellite images and a double-classification process to overcome separability problems. The work focuses on the characterization and comparison of the unique phenological patterns of argan with the other present land-cover classes. NDVI products were derived from a Sentinel-2 time-series covering one year (2018 to 2019), then ground samples were used to extract phenological profiles at parcel level then at tree level, to feed representative calibration samples to Support Vector Machine classifier. The outcome was integrated with an elevation model in a Decision Tree to reclassify mixed areas. The results indicated an F1-score and an overall accuracy of 91.27% and 92.60% respectively, a promising technique for updating argan extent at national scale.

摘要

Argania spinosa 也被称为摩洛哥坚果树，是摩洛哥的特有植物。尽管有能力在极端干旱条件下生存，但它受到土壤开垦、过度开发和缺乏自然更新的威胁，导致空间范围和密度的下降令人担忧。由于对旱地森林面积的估计不确定，旱地森林的空间范围存在争议。本研究旨在绘制和定位位于摩洛哥东南部索维拉省 Smimou 社区的摩洛哥坚果树的空间分布，使用卫星图像和双重分类过程来克服可分离性问题。这项工作的重点是摩洛哥坚果的独特物候模式与其他目前的土地覆盖类别的特征和比较。NDVI 产品源自涵盖一年（2018 年至 2019 年）的 Sentinel-2 时间序列，然后使用地面样本在宗地级别和树木级别提取物候剖面，将代表性校准样本提供给支持向量机分类器。结果与决策树中的高程模型相结合，以对混合区域进行重新分类。结果表明 F1 分数和总体准确度分别为 91.27% 和 92.60%，这是一种在全国范围内更新摩洛哥坚果范围的有前途的技术。