Paper Image

Graph neural network for regional air quality estimation

Published on:

2 April 2024

Primary Category:

Machine Learning

Paper Authors:

Xin Zhang,

Ling Chen,

Xing Tang,

Hongyu Shi

Bullets

Key Details

Represents regional data as images for air quality estimation task

Models spatial dependencies of both adjacent and distant grid regions

Introduces dual-view supergrid learning to group correlated regions

Outperforms baselines in experiments by average 19.64% in MAE

AI generated summary

Graph neural network for regional air quality estimation

The paper proposes a dual-view graph neural network called DSGNN to estimate regional air quality. It represents the area's satellite and weather data as images. DSGNN introduces techniques to model spatial dependencies between adjacent and distant grid regions. Experiments demonstrate state-of-the-art air quality estimation, outperforming prior methods.

Answers from this paper

Comments

No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up