Machine learning based combinatorial analysis for land use and land cover assessment in Kyiv City (Ukraine)

Abstract

The main goal of this study is to evaluate different models for further improvement of the accuracy of land use and land cover (LULC) classification on Google Earth Engine using random forest (RF) and support vector machine (SVM) learning algorithms. Ten indices, namely normalized difference vegetation index, normalized difference soil index, index-based built-up index, biophysical composition index, built-up area extraction index (BAEI), urban index, new built-up index, band ratio for built-up area, bare soil index, and normalized built up area index, were used as input parameters for the machine learning algorithms to improve classification accuracy. The combinatorial analysis of the Sentinel-2 bands and the aforementioned indices allowed us to create four combinations based on surface reflectance characteristics. The study includes data from April 2020 to September 2021 and April 2022 to June 2022. The multitemporal Sentinel-2 data with spatial resolutions of 10 m were used to determine the LULC classification. The major land use classes such as water, forest, grassland, urban areas, and other lands were obtained. Generally, the RF algorithm showed higher accuracy than the SVM. The overall accuracy for RF and SVM was 86.56% and 84.48%, respectively, and the mean Kappa was 0.82 and 0.79, respectively. Using the combination 2 with the RF algorithm and combination 4 with the SVM algorithm for LULC classification was more accurate. The additional use of vegetation indices allowed to increase in the accuracy of LULC classification and separate classes with similar reflection spectra