Henry Chen

Noise pollution is a pressing urban challenge with significant implications for public health and quality of life. This research presents a novel approach to predicting noise levels using machine learning and satellite imagery. By analyzing the correlating land cover patterns with noise measurements in London, Ontario, a convolutional neural network (CNN) model was trained to accurately predict noise levels across the city. The study utilizing high-resolution satellite imagery to capture detailed land cover information. The CNN model was built and trained on a dataset of noise measurements collected at various locations throughout London, Ontario, along with corresponding satellite imagery data. The model was evaluated using a validation process to assess its accuracy and generalizability. This research demonstrates the potential of machine learning and satellite imagery for accurate and scalable noise pollution prediction.
Keywords: noise; urban health; machine learning; convolutional neural network; London, Ontario