Assessment of urban growth changes in Klang District using Support Vector Machine by different kernel

Abstract The growth of urbanization in Klang District was considered to be fast and has increased the concern policy makers town planners. This paper assess changes urban development using Support Vector Machine (SVM) classification by different kernel for purpose studying built up area within year 2017 2021. At initial stage image processing, Land Use Cover (LULC) been classified based on use SVM (RBF, Polynomial, Linear, Sigmoid) which then reclassify into non after most accurate identified, thus study focused urbanization. As results, highest accuracy is RBF Kernel LULC that were 88% 90% used also analysis growth. It can seen there have every land use, particularly 9.39% (5451.77 Ha). Hence, pattern sprawl would assist planners policymakers planning managing a better city.