Spatiotemporal Data Mining for Smart Cities: A Case Study of San Jose, California

In the era of rapid urbanization, smart city development necessitates efficient management and analysis of spatial infrastructure data.This research leverages OpenStreetMap (OSM) data to perform spatiotemporal data mining and geo-visual analysis for the city of San Jose.The study outlines a structured preprocessing pipeline to extract and clean relevant urban attributes such as buildings, healthcare, roads, and land use.Using Python and geospatial libraries including Pandas, GeoPandas, and Folium, we conduct exploratory data analysis (EDA) and generate interactive visual maps to uncover spatial patterns.The results highlight infrastructure distribution and potential gaps, contributing to data-driven urban planning.This paper demonstrates how open-source geographic data, when processed and visualized correctly, can provide valuable insights into city planning and smart infrastructure development.