SPECIFIC ALPINE ENVIRONMENT LAND COVER CLASSIFICATION METHODOLOGY: GOOGLE EARTH ENGINE PROCESSING FOR SENTINEL-2 DATA
- 1Politecnico di Torino, DIATI, Department of Environment, Land and Infrastructure Engineering. Corso Duca degli Abruzzi, 24, 10129 Torino, Italy
- 2Politecnico di Torino, DIST, Interuniversity Department of Regional and Urban Studies and Planning. Viale Pier Andrea Mattioli, 39,10125 Torino, Italy
- 3Centrum Badań Kosmicznych PAN, Bartycka 18A, 00-716 Warsaw, Poland
Keywords: Classification, Land Cover, Mountainous areas, Optical imagery, Machine Learning, Sentinel-2, Google Earth Engine, Pixel-based, random forest
Abstract. Land Cover (LC) plays a key role in many disciplines and its classification from optical imagery is one of the prevalent applications of remote sensing. Besides years of researches and innovation on LC, the classification of some areas of the World is still challenging due to environmental and climatic constraints, such as the one of the mountainous chains. In this contribution, we propose a specific methodology for the classification of the Land Cover in mountainous areas using Sentinel 2, 1C-level imagery. The classification considers some specific high-altitude mountainous classes: clustered bare soils that are particularly prone to erosion, glaciers, and solid-rocky areas. It consists of a pixel-based multi-epochs classification using random forest algorithm performed in Google Earth Engine (GEE). The study area is located in the western Alps between Italy and France and the analyzed dataset refers to 2017–2019 imagery captured in the summertime only. The dataset was pre-processed, enriched of derivative features (radiometric, histogram-based and textural). A workflow for the reduction of the computational effort for the classification, which includes correlation and importance analysis of input features, was developed. Each image of the dataset was separately classified using random forest classification algorithm and then aggregated each other by the most frequent pixel value. The results show the high impact of textural features in the separation of the mountainous-specific classes the overall accuracy of the final classification achieves 0.945.