Physics-Informed Deep Learning to Reduce the Bias in Joint Prediction of Nitrogen Oxides

TL;DR

This paper introduces a physics-informed deep learning framework that integrates chemical transport model principles to improve ground-level NOx prediction accuracy, significantly reducing bias and enhancing spatial extrapolation capabilities.

Contribution

The novel framework combines physical air pollution dynamics with machine learning, achieving substantial bias reduction and better joint NO2 and NOx predictions compared to traditional ML models.

Findings

Bias reduction of 21-42% in NOx predictions

Enhanced spatial extrapolation of air quality levels

Explicit uncertainty estimation in predictions

Abstract

Atmospheric nitrogen oxides (NOx) primarily from fuel combustion have recognized acute and chronic health and environmental effects. Machine learning (ML) methods have significantly enhanced our capacity to predict NOx concentrations at ground-level with high spatiotemporal resolution but may suffer from high estimation bias since they lack physical and chemical knowledge about air pollution dynamics. Chemical transport models (CTMs) leverage this knowledge; however, accurate predictions of ground-level concentrations typically necessitate extensive post-calibration. Here, we present a physics-informed deep learning framework that encodes advection-diffusion mechanisms and fluid dynamics constraints to jointly predict NO2 and NOx and reduce ML model bias by 21-42%. Our approach captures fine-scale transport of NO2 and NOx, generates robust spatial extrapolation, and provides explicit uncertainty estimation. The framework fuses knowledge-driven physicochemical principles of CTMs with the predictive power of ML for air quality exposure, health, and policy applications. Our approach offers significant improvements over purely data-driven ML methods and has unprecedented bias reduction in joint NO2 and NOx prediction.