Urban heat island classification through alternative normalized difference vegetation index

BACKGROUND AND OBJECTIVES: Urban heat island is characterized by higher temperatures in urban areas compared to their surroundings. Vegetation, as measured by the normalized difference vegetation index, is essential for reducing urban heat island effects and impacting land surface temperature. The emergence of machine learning techniques, particularly the random forest approach, has led to improved precision in predicting land surface temperatures. This study explores alternative normalized difference vegetation index adjustments to understand their impact on urban heat island classification in Chiang Mai, Thailand. It investigates how changes to the normalized difference vegetation index can help to be part of practical urban planning measures, such as prioritizing vegetation type and location for cooling strategies in urban areas. Furthermore, the study intends to underscore the significance of vegetation as a viable solution for reducing the detrimental effects of urban heat islands while also promoting greater livability in urban environments. METHODS: Satellite data from Sentinel-2 and Landsat 8 for 2016-2022 were used to develop a 20-meters grid resolution dataset, resulting in approximately 2 million points. Random Forest was employed to predict land surface temperature, followed by systematically adjusting normalized difference vegetation index values from -100 percent to +100 percent in 10 percent increments. Urban heat island was classified based on standard deviation thresholds. Results were examined and visually compared utilizing a geographic information system, which incorporated spatial variations and heat intensity patterns to gain deeper insights into the urban landscape. FINDINGS: Adjusting normalized difference vegetation index values showed a nonlinear relationship with land surface temperature predictions, where certain thresholds caused unexpected decreases in Land Surface Temperature. The identification of urban heat island classifications highlighted various urban regions, each exhibiting unique heat intensity levels. The visual assessment revealed marked differences between the reference case and alternative scenarios, illustrating the responsiveness of land surface temperature to vegetation density. the results also emphasized the role of high normalized difference vegetation index values in cooling urban regions and reducing urban heat island intensity, while extreme reductions in vegetation led to potential misclassification of water bodies, creating anomalies in cooling patterns. The findings of this study highlight significant variables that contribute to the dynamics of urban heat islands, with a particular focus on alterations in vegetation. This information can serve as a valuable resource for future urban planning initiatives. CONCLUSION: The study demonstrates the influence of normalized difference vegetation index on urban heat island classification and its potential in urban planning strategies. By showcasing nonlinear trends, the study further emphasizes the necessity of investigating vegetation dynamics in relation to land surface temperature predictions. The findings contribute to a deeper understanding of urban heat island effects and establish a groundwork for refining machine Learning models and urban planning frameworks. Future studies could expand to other urban areas, incorporate additional variables, and refine predictive algorithms for broader applications. This study will lay the groundwork for the advancement of future real-time monitoring tools that will enable proactive and sustainable solutions to urban heat island problems.