Detection of Yucca gloriosa in Mediterranean coastal dunes: A comparative analysis of field-based sampling, human interpretation of UAV imagery and deep learning to develop an effective tool for controlling invasive plants

Massetti, Luciano; Mo, Alessio; Cini, Elena; Paterni, Marco; Merlino, Silvia; Ciccarelli, Daniela

doi:10.1016/j.rsma.2023.103265

Cited by 2 publications

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

DEM‐based sand dune analysis: Identification and morphological regionalization in the Grand Erg Oriental

Zhu,

Chen,

Yang

et al. 2024

Earth Surf Processes Landf

View full text Add to dashboard Cite

Sand dunes are predominantly distributed in arid regions. Automatic mapping and regionalization of sand dunes in large‐scale areas are crucial to understanding the evolution trends of aeolian sand environments. Different from existing studies primarily focused on mapping the extent of desert areas, this study proposes a framework for automatic identification and comprehensive regionalization based on dunes morphology. First, the basal terrain of the dune area is constructed, and the difference between this basal terrain and the DEM is calculated using threshold segmentation to delineate the extent of dunes. Further, some landscape metrics are selected to quantify the collective morphological characteristics of sand dunes. Then, a spatially constrained multivariate clustering method is applied to regionalize dunes comprehensively. Compared to existing DEM‐based dune extraction methods, this method can represent dune characteristics more accurately. The application in the Grand Erg Oriental achieved a high extraction accuracy of 94.17%, indicating its suitability for identifying dunes with diverse types in large‐scale areas. a six‐region map is generated that can clearly demonstrate diverse landscape patterns of dunes. The results indicate that the subregions containing branching linear dunes and network dunes have the highest area proportions, accounting for 27.68% and 26.83% of the total study area, respectively. This study provides valuable reference for aeolian geomorphology research specifically offering support for studies in the Grand Erg Oriental region.

show abstract