Identification of a Set of Variables for the Classification of Páramo Soils Using a Nonparametric Model, Remote Sensing, and Organic Carbon

Abstract

Páramo ecosystems harbor important biodiversity and provide essential environmental services such as water regulation and carbon sequestration. Unfortunately, the scarcity of information on their land uses makes it difficult to generate sustainable strategies for their conservation. The purpose of this study is to develop a methodology to easily monitor and document the conservation status, degradation rates, and land use changes in the páramo. We analyzed the performance of two nonparametric models (the CART decision tree, CDT, and multivariate adaptive regression curves, MARS) in the páramos of the Chambo sub-basin (Ecuador). We used three types of attributes: digital elevation model (DEM), land use cover (Sentinel 2), and organic carbon content (Global Soil Organic Carbon Map data, GSOC) and a categorical variable, land use. We obtained a set of selected variables which perform well with both models, and which let us monitor the land uses of the páramos. Comparing our results with the last report of the Ecuadorian Ministry of Environment (2012), we found that 9% of the páramo has been lost in the last 8 years.