How is the vegetation distribution influencing the erosion and surface formation in the different eco zones of Chile? To answer this question, it is mandatory to possess fundamental knowledge about plant species habitats, occurrence and their dynamics. In his study Christian Bödinger utilizes satellite imagery in combination with machine learning to derive maps of land use and land cover (LULC) in four study sites along a climatic gradient and to monitor vegetation using monthly Normalized Difference Vegetation Index (NDVI) time series. The findings contribute to a better understanding of climate impacts on Chilean vegetation and serve as a basis of landscape evolution models. Contents

TanDEM-X DEM, Sentinel Optical and Radar Data, Landsat Surface Reflectance
Machine Learning Using SVMs and Random Forest
Statistical Time-Series Evaluation
Maps of Land Use and Cover (LULC)
Time-Series Showing the Impact of ENSO Target Groups
Scientists, lecturers and students in the field of geology and ecology
Geoscientists and Ecologists with a focus on remote sensing About the AuthorChristian Bödinger holds a M.Sc. in Physical Geography from the University of Tübingen, Germany. His focus in research lies on remote sensing and image analysis for environmental applications. He is currently working for a company focusing on aquatic remote sensing.

Auteur

Christian Bödinger holds a M.Sc. in Physical Geography from the University of Tübingen, Germany. His focus in research lies on remote sensing and image analysis for environmental applications. He is currently working for a company focusing on aquatic remote sensing.

Contenu
TanDEM-X DEM, Sentinel Optical and Radar Data, Landsat Surface Reflectance.- Machine Learning Using SVMs and Random Forest.- Statistical Time-Series Evaluation.- Maps of Land Use and Cover (LULC).- Time-Series Showing the Impact of ENSO.