Spatio-Temporal Field Neural Networks for Air Quality Inference

2024/03/02 by Yutong Feng, Feng, Yutong, Qiongyan Wang +9 · 6 citations
Environmental Science · #Air Quality Monitoring and Forecasting #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2403.02354

openalex publication_date 2024/03/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The air quality inference problem aims to utilize historical data from a limited number of observation sites to infer the air quality index at an unknown location. Considering the sparsity of data due to the high maintenance cost of the stations, good inference algorithms can effectively save the cost and refine the data granularity. While spatio-temporal graph neural networks have made excellent progress on this problem, their non-Euclidean and discrete data structure modeling of reality limits its potential. In this work, we make the first attempt to combine two different spatio-temporal perspectives, fields and graphs, by proposing a new model, Spatio-Temporal Field Neural Network, and its corresponding new framework, Pyramidal Inference. Extensive experiments validate that our model achieves state-of-the-art performance in nationwide air quality inference in the Chinese Mainland, demonstrating the superiority of our proposed model and framework.

Cited by

• FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation
• OmniField: Conditioned Neural Fields for Robust Multimodal Spatiotemporal Learning
• From Deterministic to Generative Deep Learning for Urban Air Quality Reconstruction from Sparse Observations
• RainSeer: Fine-Grained Rainfall Reconstruction via Physics-Guided Modeling
• Scale-Disentangled spatiotemporal Modeling for Long-term Traffic Emission Forecasting
• MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data (Extended Version)

Related

• Deep Spatio-Temporal Neural Network for Air Quality Reanalysis
• Deep Inferential Spatial-Temporal Network for Forecasting Air Pollution Concentrations
• AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks
• HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method
• Fine-gained air quality inference based on low-quality sensing data using self-supervised learning