AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction

TL;DR

AirPhyNet is a physics-guided neural network that improves air quality prediction accuracy by integrating physical principles of particle movement, outperforming existing models especially with sparse data and long-term forecasts.

Contribution

This paper introduces AirPhyNet, a novel neural network architecture that incorporates physics principles into air quality prediction, enhancing accuracy and interpretability over traditional data-driven models.

Findings

Outperforms state-of-the-art models in various scenarios

Reduces prediction errors by up to 10%

Effectively captures physical processes of particle movement

Abstract

Air quality prediction and modelling plays a pivotal role in public health and environment management, for individuals and authorities to make informed decisions. Although traditional data-driven models have shown promise in this domain, their long-term prediction accuracy can be limited, especially in scenarios with sparse or incomplete data and they often rely on black-box deep learning structures that lack solid physical foundation leading to reduced transparency and interpretability in predictions. To address these limitations, this paper presents a novel approach named Physics guided Neural Network for Air Quality Prediction (AirPhyNet). Specifically, we leverage two well-established physics principles of air particle movement (diffusion and advection) by representing them as differential equation networks. Then, we utilize a graph structure to integrate physics knowledge into a neural network architecture and exploit latent representations to capture spatio-temporal relationships within the air quality data. Experiments on two real-world benchmark datasets demonstrate that AirPhyNet outperforms state-of-the-art models for different testing scenarios including different lead time (24h, 48h, 72h), sparse data and sudden change prediction, achieving reduction in prediction errors up to 10%. Moreover, a case study further validates that our model captures underlying physical processes of particle movement and generates accurate predictions with real physical meaning.