<![CDATA[The Urban Heat Island (UHI) phenomenon is characterized by higher temperatures in urban areas compared to surrounding rural areas. This condition poses various environmental risks and adversely impacts public health, particularly in Malang, Indonesia. This study aims to predict land surface temperature (LST) in Malang to better understand and mitigate the effects of UHI's. Support Vector Regression (SVR) is employed using remote sensing data from Landsat-8, Sentinel-2, and SRTM. Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), elevation, and LST are calculated and normalized to ensure accurate data representation. Model testing results indicate that the Radial Basis Function (RBF) kernel performs best with hyperparameter settings of C = 10, Epsilon = 0.1, and gamma = 1. This model achieves an R² of 0.887, an MSE of 1.625, and a MAPE of 2.71%. These findings confirm that SVR with an appropriately tuned RBF kernel can improve prediction accuracy. Consequently, the study provides a robust foundation for developing more effective predictive models to address UHI management in urban areas.]]>
Copyrights © 2024
