 This study presents a machine learning framework that addresses the challenge of ranking geospatial data by identifying relevant features based on semantics, user behavior, spatial similarity, and metadata attributes, applying a machine learning method to automatically learn a ranking function, and combining existing search-oriented software with a semantic knowledge base, feature extraction, and algorithm. The results show that the machine learning approach outperforms other methods in terms of precision and normalize discounted cumulative gain, setting an example for further research and intelligent geospatial data discovery. This article was offered by Yong Yeo Jiang, Yun Li, Cha Wei Yan, and others.