A Gaussian Process Method with Uncertainty Quantification for Air Quality Monitoring

Atmosphere

Hui Fang¹  Chengxi Jiang²  Lyudmila Mihaylova³  Said Munir⁴  Martin Mayfield⁴  Rohit Chakraborty⁴  Peng Wang⁵  Khan Alam⁶  Muhammad Fahim Khokhar⁷  Zhengkai Zheng⁸ 

[1] College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China;College of Electrical and Electronic Engineering, Wenzhou University, Wenzhou 325035, China;Department of Automatic Control and Systems Engineering, The University of Sheffield, Sheffield S10 2TN, UK;Department of Civil and Structural Engineering, The University of Sheffield, Sheffield S10 2TN, UK;Department of Computing and Mathematics, Manchester Metropolitan University, Manchester M15 6BH, UK;Department of Physics, University of Peshawar, KPK, Peshawar 25120, Pakistan;Institute of Environmental Sciences and Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan;Yueqing Xinshou Agricultural Development Co., Ltd., Yueqing 325604, China;

关键词: Gaussian process;    uncertainty quantification;    air quality forecasting;    low-cost sensors;    sustainable development;   

DOI  :  10.3390/atmos12101344

来源: DOAJ

【 摘 要 】

The monitoring and forecasting of particulate matter (e.g., ${\mathrm{PM}}_{2.5}$) and gaseous pollutants (e.g., NO, ${\mathrm{NO}}_2$, and ${\mathrm{SO}}_2$) is of significant importance, as they have adverse impacts on human health. However, model performance can easily degrade due to data noises, environmental and other factors. This paper proposes a general solution to analyse how the noise level of measurements and hyperparameters of a Gaussian process model affect the prediction accuracy and uncertainty, with a comparative case study of atmospheric pollutant concentrations prediction in Sheffield, UK, and Peshawar, Pakistan. The Neumann series is exploited to approximate the matrix inverse involved in the Gaussian process approach. This enables us to derive a theoretical relationship between any independent variable (e.g., measurement noise level, hyperparameters of Gaussian process methods), and the uncertainty and accuracy prediction. In addition, it helps us to discover insights on how these independent variables affect the algorithm evidence lower bound. The theoretical results are verified by applying a Gaussian processes approach and its sparse variants to air quality data forecasting.

【 授权许可】

Unknown