When predicting PM2.5 concentrations, it is necessary to consider complex information sources since the concentrations are influenced by various factors within a long period. In this paper, we identify a set of critical domain knowledge for PM2.5 forecasting and develop a novel graph based model, PM2.5-GNN, being capable of capturing long-term dependencies. On a real-world dataset, we validate the effectiveness of the proposed model and examine its abilities of capturing both fine-grained and long-term influences in PM2.5 process. The proposed PM2.5-GNN has also been deployed online to provide free forecasting service.
@article{arxiv.2002.12898,
title = {PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting},
author = {Shuo Wang and Yanran Li and Jiang Zhang and Qingye Meng and Lingwei Meng and Fei Gao},
journal= {arXiv preprint arXiv:2002.12898},
year = {2021}
}
Comments
Pre-print version of a ACM SIGSPATIAL 2020 poster [paper](https://dl.acm.org/doi/10.1145/3397536.3422208). The code is available at [Github](https://github.com/shawnwang-tech/PM2.5-GNN), and the talk is available at [YouTube](https://www.youtube.com/watch?v=VX93vMthkGM)