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!
_version_ 1850135969183825920
author Shoutao Zhu
Bin Zou
Xinyu Huang
Ning Liu
Shenxin Li
author_facet Shoutao Zhu
Bin Zou
Xinyu Huang
Ning Liu
Shenxin Li
author_sort Shoutao Zhu
collection DOAJ
description 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.
format Article
id doaj-art-0ebe59237db643f988b91ef994474c56
institution OA Journals
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-0ebe59237db643f988b91ef994474c562025-08-20T02:31:16ZengMDPI AGRemote Sensing2072-42922025-04-01179153410.3390/rs17091534Time-Series Modeling of Ozone Concentrations Constrained by Residual Variance in China from 2005 to 2020Shoutao Zhu0Bin Zou1Xinyu Huang2Ning Liu3Shenxin Li4School of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaSchool of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaSatellite 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.https://www.mdpi.com/2072-4292/17/9/1534O<sub>3</sub>residualsoutlier samplessatellite mapping
spellingShingle Shoutao Zhu
Bin Zou
Xinyu Huang
Ning Liu
Shenxin Li
Time-Series Modeling of Ozone Concentrations Constrained by Residual Variance in China from 2005 to 2020
Remote Sensing
O<sub>3</sub>
residuals
outlier samples
satellite mapping
title Time-Series Modeling of Ozone Concentrations Constrained by Residual Variance in China from 2005 to 2020
title_full Time-Series Modeling of Ozone Concentrations Constrained by Residual Variance in China from 2005 to 2020
title_fullStr Time-Series Modeling of Ozone Concentrations Constrained by Residual Variance in China from 2005 to 2020
title_full_unstemmed Time-Series Modeling of Ozone Concentrations Constrained by Residual Variance in China from 2005 to 2020
title_short Time-Series Modeling of Ozone Concentrations Constrained by Residual Variance in China from 2005 to 2020
title_sort time series modeling of ozone concentrations constrained by residual variance in china from 2005 to 2020
topic O<sub>3</sub>
residuals
outlier samples
satellite mapping
url https://www.mdpi.com/2072-4292/17/9/1534
work_keys_str_mv AT shoutaozhu timeseriesmodelingofozoneconcentrationsconstrainedbyresidualvarianceinchinafrom2005to2020
AT binzou timeseriesmodelingofozoneconcentrationsconstrainedbyresidualvarianceinchinafrom2005to2020
AT xinyuhuang timeseriesmodelingofozoneconcentrationsconstrainedbyresidualvarianceinchinafrom2005to2020
AT ningliu timeseriesmodelingofozoneconcentrationsconstrainedbyresidualvarianceinchinafrom2005to2020
AT shenxinli timeseriesmodelingofozoneconcentrationsconstrainedbyresidualvarianceinchinafrom2005to2020