Time-Series Modeling of Ozone Concentrations Constrained by Residual Variance in China from 2005 to 2020

Satellite retrievals can capture the spatiotemporal variation of O<sub>3</sub> over a large area near the surface. However, due to the unstable functional relationships between variables across spatiotemporal scales, the outlier predictions will reduce the accuracy of the prediction mode...

Full description

Saved in:
Bibliographic Details
Main Authors: Shoutao Zhu, Bin Zou, Xinyu Huang, Ning Liu, Shenxin Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/9/1534
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Satellite retrievals can capture the spatiotemporal variation of O<sub>3</sub> over a large area near the surface. However, due to the unstable functional relationships between variables across spatiotemporal scales, the outlier predictions will reduce the accuracy of the prediction model. Therefore, a validated residual constrained random forest model (RF-RVC) is proposed to estimate the monthly and annual O<sub>3</sub> concentration datasets of 0.1° in China from 2005 to 2020 using O<sub>3</sub> precursor remote-sensing data and other auxiliary data. The temporal and spatial variations of O<sub>3</sub> concentrations in China and the four urban agglomerations (Beijing–Tianjin–Hebei (BTH), Yangtze River Delta (YRD), Pearl River Delta (PRD) and Sichuan–Chongqing (SC)) were calculated. The results show that the annual <i>R</i><sup>2</sup> and <i>RMSE</i> of the RF-RVC model are 0.72~0.89 and 8.4~13.06 μg/m<sup>3</sup>. Among them, the RF-RVC model with the temporal residuals constraint has the greatest performance improvement, with the annual <i>R</i><sup>2</sup> increasing from 0.59 to 0.8, and the <i>RMSE</i> decreasing from 17.24 μg/m<sup>3</sup> to 10.74 μg/m<sup>3</sup>, which is significantly better than that of the <i>RF</i> model. The North China Plain is the focus of ozone pollution. Summer is the season of a high incidence of ozone pollution in China, YRD, PYD, and SC, while pollution in the PRD is delayed to October due to the monsoon. In addition, the trend of the O<sub>3</sub> and its excess proportion in China and the four urban agglomerations is not satisfactory; targeted measures should be taken to reduce the risk of environmental ozone. The research findings confirm the effectiveness of the residual constraint approach in long-term time-series modeling. In the future, it can be further extended to the modeling of other pollutants, providing more accurate data support for health risk assessments.
ISSN:2072-4292