Image-Based Air Quality Forecasting Through Multi-Level Attention
Lists
Only you see this
Abstract
The problem of air quality forecasting is important but also challenging because air quality is affected by a diverse set of complex factors. This paper describes the first image-based air quality forecasting model. It fuses a history of PM <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> measurements with colocated images. We construct a multi-level attention-based recurrent network that uses images and PM <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> data to represent variation over space and time. Experiments on Shanghai data show that our model improves PM <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> RMSE prediction accuracy by 15.8% and MAE by 10.9% compared to previous forecasting methods. In addition, we evaluate the impact of each model component via ablation studies.
BibTeX
@inproceedings{zhang2022image,
author = {Tony Zhang and Robert P. Dick},
title = {{Image-Based Air Quality Forecasting Through Multi-Level Attention}},
booktitle = {ICIP},
year = {2022},
url = {https://openreview.net/forum?id=JHF97KeLo1J},
}Loading related content...