Landslides significantly threaten human life and infrastructure, requiring accurate and timely identification for effective hazard assessment and management. In this study, we propose a novel approach for landslide identification by integrating Geographic Object-Based Image Analysis (GEOBIA) with advanced techniques and machine learning algorithms. Our methodology includes Simple Non-iterative Clustering (SNIC) segmentation, which divides the image into super-pixels, enabling a detailed analysis at the object level, Gray Level Co-occurrence Matrix (GLCM) feature extraction, which is employed to capture important textural information, Principal Component Analysis (PCA) for dimensionality reduction which helps to reduce the dataset's complexity by transforming the original set of variables into smaller sets of uncorrelated variables recognized as principal components, and the utilization of various machine learning algorithms such as (i) Support vector machine (SVM), (ii) Random Forest (RF), and (iii) Classification and Regression Trees (CART). We utilize the Google Earth Engine (GEE) platform to leverage extensive geospatial data and computational power. The performance of SVM, RF, and CART algorithms is evaluated for landslide detection. SVM demonstrates superior accuracy in detecting landslides, achieving an overall accuracy of 89.01%, surpassing RF (87.82%) and CART (73.31%). The effectiveness of our proposed approach, which involves integrating SNIC segmentation, GLCM feature extraction, PCA analysis, and SVM classification, has been underscored in accurately and efficiently identifying landslides. Combining advanced techniques and machine learning algorithms within the GEOBIA framework with the GEE platform offers promising results for improving landslide identification, monitoring, risk assessment, supporting proactive measures, and mitigating landslide risks.