READ ME File For 'Dateset for Urban Noise Prediction'

Dataset DOI: 10.5258/SOTON/D3762

ReadMe Author: Feiyu Zhu, University of Southampton, 0009-0001-5496-349X

This dataset supports the thesis entitled 'Assessing the feasibility of applying machine learning tools to predict environmental stressors from digital urban fingerprints'
AWARDED BY: University of Southampton
DATE OF AWARD: 2025


Information about geographic location of data collection: United Kingdom

Licence: CC-BY


--------------------
DATA & FILE OVERVIEW
--------------------

This dataset contains:

Code and models for multispectral and GNN-based urban noise prediction across UK cities

This repository contains the full implementation of the methods described in Feiyu Zhu's PhD dissertation, which explores scalable and transferable models for predicting urban noise levels using high-resolution multispectral satellite imagery and graph-based machine learning.


Project Structure

- `chapter4_efficientnet/` - Remote sensing-based CNN model (EfficientNet) for noise prediction in Southampton.
- `chapter5_gnn_southampton/` - Graph neural network model integrating spatial structure and urban context (Southampton only).
- `chapter6_crosscity_generalization/` - Generalizable noise prediction across five UK cities using domain adaptation and pseudo-labelling.



Date that the file was created: Nov, 2025