About Research
Our research focuses on applying AI and geospatial analytics to improve urban livability through station-level analysis. We explore how machine learning can guide compact city planning by modeling real-world access to essential services. The goal is to create data-driven solutions that are both technically robust and socially impactful.
The core objective of our research is to develop a machine learning–powered system that quantifies livability around urban transit nodes, supporting compact and sustainable city development. Our methodology integrates spatial data collection using APIs (e.g., Google Maps, Overpass) with advanced machine learning models, including Artificial Neural Networks, CNNs, Graph Neural Networks, and regression analysis. These models analyze the proximity, diversity, and accessibility of amenities like schools, healthcare, recreation, restaurants, and fitness centers within a 600-meter walking radius. Built using KNIME and Python and deployed to deliver real-time, location-specific insights. The final output is an interactive platform that empowers citizens, urban planners, and companies to explore livability metrics dynamically—supporting informed decisions, public engagement, and data-backed urban development strategies.