Traffic Noise Modelling Using Land Use Regression Model Based on Machine Learning, Statistical Regression and GIS

This study estimates the equivalent continuous sound pressure level (Leq) during peak daily periods (‘rush hour’) along New Klang Valley Expressway (NKVE) in Shah Alam, Malaysia, using a land use regression (LUR) model based on machine learning, statistical regression, and geographical information systems (GIS). The research utilises two types of soft computing methods including learning (i.e., decision tree, random frost algorithms) linear support vector to determine best approach create prediction Leq map at NKVE Malaysia. selection algorithm is accomplished by considering correlation, correlation coefficient, mean-absolute-error, mean-square-error, root-mean-square-error, mean absolute percentage error. Traffic noise was monitored three meters (TES 52A), traffic tally done analyse flow. Wind speed gauged wind meter. relied variety predictors speed, digital elevation model, type (specifically, if it residential, industrial, or natural reserve), residential density, road (expressway, primary, secondary) average (Leq). above parameters were fed as inputs into LUR model. Additional influencing factors such lights, intersections, toll gates, gas stations, public transportation infrastructures (bus stop bus line) are also considered this study. models utilised derived from LiDAR (Light Detection Ranging) data, various GIS (Geographical Information Systems) layers extracted produce maps. results highlighted superior performances (random forest) compared regression-based models.