Identification of strategic location for environmental noise control through the application of land use regression (lur) in a neural network platform

The significant causes of rising noise pollution within urban areas lie in extensive transportation networks, industrial operations, and commercial activities. Addressing this complexity, our study employs Land Use Regression (LUR) modelling to assess the intricate relationship between land-use features and environmental noise in urban landscape. The objective of this study is to provide a framework for predicting environmental noise levels in Delhi, India. For which, Lday, Lnight, LAeq, 24h, and Ldn noise descriptors were modelled at daily resolution data from 31 fixed-site monitors. The prediction at first stage for LUR was found to be R2 = 0.53 which was validated using the n-1 method. The model was later optimized using a NN. Output from the NN is included in the GIS environment to identify the hotspot of the noise. Previously identified engineering interventions applicable to urban contexts that were listed from the literature review were allocated as per hotspots because of the modelled output. The study also explored the avenue of using Delhi-specific transport variables developed from Google travel time data for prediction improvement of the noise level. The research contributes to advancement of noise pollution assessment and management methodologies, particularly in situations with no available validated traffic noise models.