Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in Beijing

Surface ozone is a pollutant linked to higher risks of cardiopulmonary diseases with long-term exposure. Timely forecasting of ozone levels helps authorities implement preventive measures to protect public health and safety. However, few studies have been able to reliably provide long-term hourly oz...

Full description

Saved in:
Bibliographic Details
Main Authors: Taotao Lv, Yulu Yi, Zhuowen Zheng, Jie Yang, Siwei Li
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/14/2530
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849732961777221632
author Taotao Lv
Yulu Yi
Zhuowen Zheng
Jie Yang
Siwei Li
author_facet Taotao Lv
Yulu Yi
Zhuowen Zheng
Jie Yang
Siwei Li
author_sort Taotao Lv
collection DOAJ
description Surface ozone is a pollutant linked to higher risks of cardiopulmonary diseases with long-term exposure. Timely forecasting of ozone levels helps authorities implement preventive measures to protect public health and safety. However, few studies have been able to reliably provide long-term hourly ozone forecasts due to the complexity of ozone’s diurnal variations. To address this issue, this study constructs a hybrid prediction model integrating improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), bi-directional long short-term memory neural network (BiLSTM), and the persistence model to forecast the hourly ozone concentrations for the next continuous 36 h. The model is trained and tested at the Wanshouxigong site in Beijing. The ICEEMDAN method decomposes the ozone time series data to extract trends and obtain intrinsic mode functions (IMFs) and a residual (Res). Fourier period analysis is employed to elucidate the periodicity of the IMFs, which serves as the basis for selecting the prediction model (BiLSTM or persistence model) for different IMFs. Extensive experiments have shown that a hybrid model of ICEEMDAN, BiLSTM, and persistence model is able to achieve a good performance, with a prediction accuracy of R<sup>2</sup> = 0.86 and RMSE = 18.70 µg/m<sup>3</sup> for the 36th hour, outperforming other models.
format Article
id doaj-art-cff791ffde4f447b8fda111d66fff4db
institution DOAJ
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-cff791ffde4f447b8fda111d66fff4db2025-08-20T03:08:10ZengMDPI AGRemote Sensing2072-42922025-07-011714253010.3390/rs17142530Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in BeijingTaotao Lv0Yulu Yi1Zhuowen Zheng2Jie Yang3Siwei Li4School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSurface ozone is a pollutant linked to higher risks of cardiopulmonary diseases with long-term exposure. Timely forecasting of ozone levels helps authorities implement preventive measures to protect public health and safety. However, few studies have been able to reliably provide long-term hourly ozone forecasts due to the complexity of ozone’s diurnal variations. To address this issue, this study constructs a hybrid prediction model integrating improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), bi-directional long short-term memory neural network (BiLSTM), and the persistence model to forecast the hourly ozone concentrations for the next continuous 36 h. The model is trained and tested at the Wanshouxigong site in Beijing. The ICEEMDAN method decomposes the ozone time series data to extract trends and obtain intrinsic mode functions (IMFs) and a residual (Res). Fourier period analysis is employed to elucidate the periodicity of the IMFs, which serves as the basis for selecting the prediction model (BiLSTM or persistence model) for different IMFs. Extensive experiments have shown that a hybrid model of ICEEMDAN, BiLSTM, and persistence model is able to achieve a good performance, with a prediction accuracy of R<sup>2</sup> = 0.86 and RMSE = 18.70 µg/m<sup>3</sup> for the 36th hour, outperforming other models.https://www.mdpi.com/2072-4292/17/14/2530ozone forecastICEEMDANBiLSTMpersistence model
spellingShingle Taotao Lv
Yulu Yi
Zhuowen Zheng
Jie Yang
Siwei Li
Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in Beijing
Remote Sensing
ozone forecast
ICEEMDAN
BiLSTM
persistence model
title Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in Beijing
title_full Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in Beijing
title_fullStr Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in Beijing
title_full_unstemmed Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in Beijing
title_short Long-Term Hourly Ozone Forecasting via Time–Frequency Analysis of ICEEMDAN-Decomposed Components: A 36-Hour Forecast for a Site in Beijing
title_sort long term hourly ozone forecasting via time frequency analysis of iceemdan decomposed components a 36 hour forecast for a site in beijing
topic ozone forecast
ICEEMDAN
BiLSTM
persistence model
url https://www.mdpi.com/2072-4292/17/14/2530
work_keys_str_mv AT taotaolv longtermhourlyozoneforecastingviatimefrequencyanalysisoficeemdandecomposedcomponentsa36hourforecastforasiteinbeijing
AT yuluyi longtermhourlyozoneforecastingviatimefrequencyanalysisoficeemdandecomposedcomponentsa36hourforecastforasiteinbeijing
AT zhuowenzheng longtermhourlyozoneforecastingviatimefrequencyanalysisoficeemdandecomposedcomponentsa36hourforecastforasiteinbeijing
AT jieyang longtermhourlyozoneforecastingviatimefrequencyanalysisoficeemdandecomposedcomponentsa36hourforecastforasiteinbeijing
AT siweili longtermhourlyozoneforecastingviatimefrequencyanalysisoficeemdandecomposedcomponentsa36hourforecastforasiteinbeijing