ISODATA Clustering Approach for Mapping and Characterization of Surface Urban Heat Island Intensities Using Time Series of Remotely Sensed Land Surface Temperature and Land-Use/Land-Cover Products

This study evaluated spatial, seasonal, and diurnal variations in surface urban heat island intensities (SUHIIs) across three rapidly developing major cities in Alabama, USA: Huntsville, Birmingham, and Mobile, representing less-studied mid-size cities of the Mid-South USA. We evaluated an integrated clustering approach using ISODATA clustering of Moderate Resolution Imaging Spectroradiometer (MODIS) Land Surface Temperature (LST) time series, followed by supervised cluster merging based on cluster statistics and National Land Cover Database (NLCD) Land-Use/Land-Cover (LULC) products, to map SUHIs and quantify SUHIIs. Our findings show urban expansion across all three study areas, but at varying rates and patterns, with the highest rates in the Huntsville city area. The ISODATA clustering approach using LST time series mapped surface urban heat islands (SUHIs) as distinct clusters of significantly (p = 0.01) warmer surface temperatures than surrounding non-urban areas. The SUHI clusters also resembled spatial distributions of NLCD-developed LULCs, with the highest resemblance between NLCD-developed LULC clusters and SUHI clusters mapped using summer daytime LST time series. Our SUHIIs estimated using the derived SUHI clusters correspond well with the values reported in the SUHI literature. Yearly seasonal-average SUHIIs varied significantly (p = 0.05) among the three study areas and across seasonal and diurnal cycles, while summer daytime SUHIIs were consistently larger across all sites and throughout the study period. Across both seasons (winter and summer) and all sites, the highest SUHIIs were reported over SUHI-3 clusters that resembled high-intensity developed areas. Our findings suggest that our integrated clustering approach, using MODIS LST time series, is a promising approach for local-scale mapping and characterization of SUHIs. However, given the substantial variations in SUHIIs, further verification using field observations and comprehensive analyses across larger geographic regions and time periods is needed to evaluate the approach’s applicability under variable conditions and using different data products.