A Review of Google Earth Engine for Land Use and Land Cover Change Analysis: Trends, Applications, and Challenges

Google Earth Engine (GEE) has emerged as a powerful tool for analyzing Land Use and Land Cover (LULC) changes in a wide range of research. While some GEE-related reviews exist, they primarily cover publications before 2020. This review examines the latest trends, applications, and challenges in using GEE for LULC change detection up to February 2025. In this study, 72 studies were selected from Google Scholar, Scopus, and Web of Science databases. Results reveal that GEE experienced exponential growth in the research field from 2011 to 2025. The journal “Remote Sensing” plays a significant role in the field, accounting for 25% of total publications. China leads in GEE-LULC-based studies with 27%, followed by India (13%). Landsat data appears in 65% of studies, making it the most utilized, followed by Sentinel data at 23%. Random Forest (RF) is the most used classification method (36%), surpassing Support Vector Machine (SVM) and Classification and Regression Tree (CART). Most studies validate classification results with overall accuracy rates from 80% to 98.68%, with the highest achieved using the combination of RF, CART, and SVM. GEE’s users noted challenges such as memory limits, slow processing, cloud cover issues, and limited support for advanced machine learning (ML) models. Unlike previous reviews focusing solely on GEE or LULC, this study integrates both, providing a dedicated analysis of their intersection and filling a clear gap in the literature. This study aims to provide a comprehensive review of how GEE is applied to LULC change detection, identifying current trends, methodological preferences, and practical challenges, and to guide future research on leveraging GEE in LULC change studies.