Temporal dynamic analysis of a mountain ecosystem based on multi‐source and multi‐scale remote sensing data

Abstract

Abstract During the last decades, ecosystems have suffered a decline in natural resources due to climate change and anthropogenic pressure. Specifically, the European rabbit introduced by humans, as well as drought episodes, have led to a change in the vegetation structure of a mountainous ecosystem: Teide National Park in Spain. Teide managers studied, with field‐based traditional methods, how the two keystone vegetation species, Spartocytisus supranubius and Pterocephalus lasiospermus, have changed their dynamics in this vulnerable and heterogenic ecosystem. However, remote sensing is an important tool for classifying, monitoring, and managing large areas in a fast and economic way. This work proposes a methodological framework to monitor the changes produced in this protected area using multi‐source remote sensing imagery. The results strengthen and extend the analysis followed by the National Park managers, demonstrating that S. supranubius has decreased its population while P. lasiospermus has increased. Moreover, this study presents thematic maps of the species of interest, as well as its specific coverage at different dates, providing quantitative data difficult to get with traditional approaches.

Keywords

• change detection
• hyperspectral imagery
• invasive species
• multispectral imagery
• remote sensing imagery
• support vector machine