Nathvani, R;
D., V;
Clark, SN;
Alli, AS;
Muller, E;
Coste, H;
Bennett, JE;
... Ezzati, M; + view all
(2023)
Beyond here and now: Evaluating pollution estimation across space and time from street view images with deep learning.
Science of the Total Environment
, 903
, Article 166168. 10.1016/j.scitotenv.2023.166168.
(In press).
Preview |
Text
1-s2.0-S0048969723047939-main.pdf - Published Version Download (4MB) | Preview |
Abstract
Advances in computer vision, driven by deep learning, allows for the inference of environmental pollution and its potential sources from images. The spatial and temporal generalisability of image-based pollution models is crucial in their real-world application, but is currently understudied, particularly in low-income countries where infrastructure for measuring the complex patterns of pollution is limited and modelling may therefore provide the most utility. We employed convolutional neural networks (CNNs) for two complementary classification models, in both an end-to-end approach and as an interpretable feature extractor (object detection), to estimate spatially and temporally resolved fine particulate matter (PM2.5) and noise levels in Accra, Ghana. Data used for training the models were from a unique dataset of over 1.6 million images collected over 15 months at 145 representative locations across the city, paired with air and noise measurements. Both end-to-end CNN and object-based approaches surpassed null model benchmarks for predicting PM2.5 and noise at single locations, but performance deteriorated when applied to other locations. Model accuracy diminished when tested on images from locations unseen during training, but improved by sampling a greater number of locations during model training, even if the total quantity of data was reduced. The end-to-end models used characteristics of images associated with atmospheric visibility for predicting PM2.5, and specific objects such as vehicles and people for noise. The results demonstrate the potential and challenges of image-based, spatiotemporal air pollution and noise estimation, and that robust, environmental modelling with images requires integration with traditional sensor networks.
| Type: | Article |
|---|---|
| Title: | Beyond here and now: Evaluating pollution estimation across space and time from street view images with deep learning |
| Location: | Netherlands |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.scitotenv.2023.166168 |
| Publisher version: | https://doi.org/10.1016/j.scitotenv.2023.166168 |
| Language: | English |
| Additional information: | © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
| Keywords: | Air pollution, Computer vision, Deep learning, Environmental modelling, Noise pollution, Street-view images |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Centre for Advanced Spatial Analysis |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10178814 |
Archive Staff Only
 |
View Item |
