Vol.:(0123456789) Environmental Earth Sciences (2025) 84:92 https://doi.org/10.1007/s12665-024-12045-8 ORIGINAL ARTICLE Geographic object‑based image analysis for landslide identification using machine learning on google earth engine Diwakar Khadka 1  · Jie Zhang 2  · Atma Sharma 2 Received: 13 June 2024 / Accepted: 18 December 2024 / Published online: 28 January 2025 © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025 Abstract Landslides significantly threaten human life and infrastructure, requiring accurate and timely identification for effective hazard assessment and management. This study proposes a new approach combining Geographic Object-Based Image Analysis (GEOBIA) and machine learning on the Google Earth Engine (GEE) platform, utilizing high-resolution Sentinel-2 imagery and NASADEM data. Our methodology begins with Simple Non-iterative Clustering (SNIC) segmentation, which divides the images into homogeneous super-pixels. This step is crucial for reducing 'salt and pepper' noise and enhances the differentiation of spectrally similar objects through advanced texture, shape, and contextual analysis. Following segmentation, Gray Level Co-occurrence Matrix (GLCM) feature extraction is employed to gather critical textural information, which is pivotal in discerning surface roughness, heterogeneity, and composition—key factors in identifying landslide-prone areas. To manage the high dimensionality of the data, Principal Component Analysis (PCA) is utilized for dimensionality reduction, transforming original variables into a set of uncorrelated principal components that facilitate more efficient subsequent analysis. Various machine learning algorithms are utilized, including Support Vector Machine (SVM), Random Forest (RF), and Classification and Regression Trees (CART). We use the GEE platform to leverage extensive geospatial data and computational power. The performance of SVM, RF, and CART algorithms is evaluated for landslide detection. RF demonstrates superior accuracy in detecting landslides, achieving an overall accuracy of 87.41%, surpassing SVM (85.47%) and CART (68.45%). Integrating SNIC segmentation, GLCM feature extraction, PCA analysis, and RF algorithm within the GEOBIA framework using the GEE platform shows promising results for improving landslide identification, monitoring, and risk assessment. Keywords Landslide identification · Geographic Object-Based Image Analysis · Machine Learning · Google Earth Engine Introduction Landslides are natural disasters that occurs around the globe, causing damage to several infrastructures and loss of human lives (Adriano et al. 2020). Landslides can be triggered by natural environmental changes and human activities, includ- ing quarrying, and road construction (Jones et al. 2021). Identifying landslides and measuring their relevant features are not just research priority; however, it is an important task that faces numerous technological challenges (Hibert et al. 2018). These complications increase because of the fact that one needs to take into consideration not only the likelihood of landslide occurrences but also the potential consequences, which demands probabilistic approaches if uncertainties are to be dealt with sufficiently (Zhang et al. 2013). To address these challenges, several researchers have attempted various approaches in the past (Chen et al. 2016; Devara et al. 2021; * Diwakar Khadka diwakar@tongji.edu.cn Jie Zhang cezhangjie@tongji.edu.cn Atma Sharma atmasharma@tongji.edu.cn 1 Department of Geotechnical Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China 2 Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education, Department of Geotechnical Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China