ABSTRACT Sustainable urban development requires translating global sustainability agendas into context‐specific planning priorities, particularly in rapidly urbanizing cities in the Global South. This study integrates community‐defined infrastructure needs with Sustainable Development Goal targets to develop an SDG‐based Urban Infrastructure Sustainability Index for Tirunelveli City, India. Key indicators such as drinking water, sanitation, affordable housing, air quality, public transport, waste collection, and open spaces were identified through stakeholder engagement and mapped to the SDG targets 6.1, 6.2, 11.1, 11.6.2, 11.2, 11.6.1, and 11.7. Machine learning clustering techniques, namely K‐Means and Fuzzy C‐Means, were applied to classify 55 urban wards based on their performance across indicators. The clustering revealed consistent spatial disparities, where northern wards showed relatively higher sustainability performance, while several southern wards consistently appeared in lower‐performing clusters under both algorithms. Weights for the indicators were assigned using the Analytic Hierarchy Process, and a Derived Sustainability Index was constructed for each ward. The overall DSI for Tirunelveli was 0.88, indicating notable progress toward infrastructure‐related SDG targets. However, intra‐city variations highlighted spatial inequality and uneven distribution of infrastructure benefits. Geospatial visualization of the DSI enabled ward‐level comparison and provided evidence for inclusive, data‐driven planning. The study demonstrates how integrating community priorities with spatial analytics and machine learning facilitates more informed decision‐making and the equitable allocation of urban resources.
Venkatesh et al. (Wed,) studied this question.