Fine-gained air quality inference based on low-quality sensing data using self-supervised learning

TL;DR

This paper introduces a multi-task spatio-temporal network that leverages self-supervised learning and seasonal decomposition to improve fine-grained air quality mapping using low-quality micro-station data, achieving high accuracy in a real-world Chinese city.

Contribution

The paper proposes a novel multi-task spatio-temporal network with self-supervised learning and seasonal decomposition to enhance air quality inference from low-quality sensing data.

Findings

MTSTN outperforms benchmark models in accuracy.

Utilizing low-quality micro-station data significantly improves AQ inference.

Model robustness and interpretability are validated through ablation tests.

Abstract

Fine-grained air quality (AQ) mapping is made possible by the proliferation of cheap AQ micro-stations (MSs). However, their measurements are often inaccurate and sensitive to local disturbances, in contrast to standardized stations (SSs) that provide accurate readings but fall short in number. To simultaneously address the issues of low data quality (MSs) and high label sparsity (SSs), a multi-task spatio-temporal network (MTSTN) is proposed, which employs self-supervised learning to utilize massive unlabeled data, aided by seasonal and trend decomposition of MS data offering reliable information as features. The MTSTN is applied to infer NO$_2$, O$_3$ and PM$_{2.5}$ concentrations in a 250 km$^2$ area in Chengdu, China, at a resolution of 500m$\times$500m$\times$1hr. Data from 55 SSs and 323 MSs were used, along with meteorological, traffic, geographic and timestamp data as features. The MTSTN excels in accuracy compared to several benchmarks, and its performance is greatly enhanced by utilizing low-quality MS data. A series of ablation and pressure tests demonstrate the results' robustness and interpretability, showcasing the MTSTN's practical value for accurate and affordable AQ inference.