Google Earth Engine-based mapping of land use and land cover for weather forecast models using Landsat 8 imagery

Abstract

Land Use and Land Cover (LULC) maps are vital prerequisites for weather prediction models. This study proposes a framework to generate LULC maps based on the U.S. Geological Survey (USGS) 24-category scheme using Google Earth Engine. To realize a precise LULC map, a fusion of pixel-based and object-based classification strategies was implemented using various machine learning techniques across different seasons. For this purpose, feature importance analysis was conducted on the top classifiers considering the dynamic (seasonal) behavior of LULC. The results showed that ensemble approaches such as Random Forest and Gradient Tree Boosting outperformed other algorithms. The results also demonstrated that the object-based approach had better performance due to the consideration of contextual features. Finally, the proposed fusion framework produced a LULC map with higher accuracy (overall accuracy = 94.92% and kappa coefficient = 94.19%). Furthermore, the performance of the generated LULC map was assessed by applying it to the Weather Research and Forecasting (WRF) model for downscaling wind speed and 2-m air temperature (T2). The assessment indicated that the generated LULC map effectively reflected real-world conditions, thereby impacting the estimation of wind speed and T2 fields by WRF. Statistical assessments demonstrated enhancements in RMSE by 0.02 °C, MAE by 1 °C, and Bias by 0.03 °C for T2. Additionally, there was an improvement of 0.06 m/s in MAE for wind speed. Consequently, the framework can be implemented to produce accurate and up-to-date high-resolution LULC maps in various geographical areas worldwide. The source codes corresponding to this research paper are available on GitHub via https://github.com/Mganjirad/GEE-LULC-WRF.