Improving the methodology for monitoring vegetation cover based on type segmentation

Abstract

Monitoring is an important element for defining sustainable land cover management strategies. The monitoring technique proposed and developed in this work with integrated processing of remote sensing data has the potential to scale and optimize the interpretation of vegetation classes, making the analysis of the territory more detailed. This approach based on multiclass classification of composite images with data preprocessing based on Google Earth Engine (GEE) cloud platform. The article describes the characteristics and benefits of the uses cloud platform. Three regions, different in their characteristics and climatic features, were chosen as the study area: Voronezh Oblast, Republic of Tatarstan and Perm Krai. The objects of the study were the classes of forest vegetation, arable land and meadow vegetation. The article presents a step-by-step methodology for obtaining and processing Sentinel-2 satellite imagery data. The main steps of the methodology include obtaining a time series of satellite data and processing them, applying a vegetation index to satellite images, selecting reference data for validation, classifying objects using the random forests algorithm. An overview of WorldCover cartographic product from European Space Agency (ESA) and its advantages for use in working with geoinformation data is presented. The classification of target classes of vegetation in GEE cloud platform was carried out. The results of the study contain an analysis of a combination of normalized difference vegetation index (NDVI) for each studied class of vegetation. Implementation of the methodology is important for retrospective analysis and operational monitoring of vegetation cover classes. The method of multi-class segmentation of objects based on time series analysis will significantly improve the accuracy and speed of providing analytics to update information on land use.