skip to main content
10.1145/3650215.3650389acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicmlcaConference Proceedingsconference-collections
research-article

Prediction of O3 Concentration Based on CEEMDAN-RCMSE-LSTM Model

Published: 16 April 2024 Publication History

Abstract

In response to the problem that the current ozone forecasting methods fail to consider the characteristic recognition of ozone concentration sequences, a combined forecasting model CEEMDAN-RCMSE-LSTM is proposed. Model extracts the feature distribution of the time series through the frequency-domain processing method and entropy value classification, and predicts daily ozone concentrations at time 0 and time 12 through the LSTM model. The model's performance is validated using the atmospheric ozone concentrations in Beijing's Xicheng district time 0 from January 1, 2020, to August 27, 2022, and the atmospheric ozone concentrations in Beijing at time 12 from January 1, 2020, to August 27, 2022. The results show the combined forecasting model CEEMDAN-RCMSE-LSTM has significantly improved accuracy and can improve the predictive performance of the single LSTM model by 12.3% and 12.6%, respectively. Despite some errors in meteorological forecasts, the proposed still achieves high-precision forecasting results and has good robustness.

References

[1]
BAO F. Analysis of Collaborative Measures for Air Pollution Control in Beijing Tianjin Hebei under the Background of "Dual Carbon" [J]. Cleaning the World. 2023, 39 (02):137-139.
[2]
FAN M Q. Current Situation and Treatment Methods of Air Pollution in China [J]. Green and Environmentally Friendly Building Materials, 2021, (11): 24-25.
[3]
QI L R, MA X, LI X, ZHANG W J, JI D S, WEN W .Current Situation and Suggestions for Air Pollution Prevention and Control in the Beijing Tianjin Hebei Region [C] // Proceedings of the 2021 Science and Technology Annual Meeting of the Chinese Society of Environmental Sciences. Environ-mental Engineering Technology Innovation and Application Branch (II), 2021, 158-163+17.
[4]
VIJAY S, LI M Y, KIM K. Shining New Light on Long-term Ozone Harms [J]. JAMA Internal Medicin, 2020, 180(1):115-116.
[5]
Fu J Yi, BRUSE A M, XUN Z, FEI J. Damages of surface ozone: evidence from agricultural sector in China [J]. Environ-mental Research Letters, 2018, 13(3):19-34.
[6]
MA R M, ZHANG Y Y, BAN J, WANG Q, LI T T. Prediction of near ground ozone station concentrations in the Beijing Tianjin Hebei region based on a random forest model [J]. Journal of Environment and Health, 2019, 36(11): 954-957.
[7]
CHEN Q. Application of Support Vector Machine in Predicting Air Pollutant Concentration [D]. Xi'an University of Science and Technology, 2010.
[8]
ZHENG Y, YI X W, LI M, Forecasting fine-grained air quality based on big data[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2015, 2267-2276.
[9]
UNJIN P, CHUNSONG K, UNSOK R, A hybrid model based on convolutional neural networks and long short-term memory for ozone concentration prediction [J]. Air Quality, Atmosphere & Health, 2018, 11(8): 883-895.
[10]
DONG H Z, WANG L H, TANG W, YANG Q, SHE Y N. Study on PCA-PSO-SVM ozone (O3) prediction method based on spatiotemporal characteristics [J]. Chinese Environmental Sci-ence, 2021, 41(02): 596-60.
[11]
MAO W J, JIAO L M, WANG W L. Long time series ozone prediction in China: A novel dynamic spatiotemporal deep learning approach [J]. Building and Environment, 2022, 218(15): 87-99.
[12]
DAUBECHIES I. Ten lectures on wavelets. Society for industrial and applied mathematics; 1992.
[13]
HUANG N E, SHEN Z, LONG S R, WU M C, et la. The empirical mode decomposition and the Hilbert spectrum for non-linear and non-stationary time series analysis. Proc R Soc Lond Ser A Math Phys Eng Sci, 1998, 454 (1971): 903–915.
[14]
Wu Z, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal, 2009, 1(01): 19–41.
[15]
YEH J R, SHI E J, HHUANG NE. Complementary ensemble empirical mode decomposition: A novel noise enhanced data analysis method. Adv Adapt Data Anal, 2010, 2(02):135–56.
[16]
ZENG Q L, WANG L H, ZHU S Y, GAO Y H, QIU X F,el ta. Long-term PM2.5 concentrations forecasting using CEEMDAN and deep Transformer neural network [J]. Atmospheric Pollution Research, 2023, 23,14(9).
[17]
ZHENG J D, PAN H Y, BAO J H. Fault diagnosis method of rolling bearings based on refined composite multiscale entropy and autoencoder [J]. Noise and Vibration Control, 2019, 39(2):175- 180.
[18]
YE X, HU J, TIAN P, Automatic sleep scoring based on refined composite multi-scale entropy and support vector machine [J]. Journal of Shanghai Jiaotong University, 2019, 53(3):321- 326.
[19]
HOCHREITER S, SCHMIDHUBER J. Long short-term memory. Neural Comput, 1997, 9(8):1735–1780.
[20]
SHAIKH M M, BUTT R A, KHAWAJA A. Forecasting total electron content (TEC) using CEEMDAN -LSTM model [J]. Advances in Space Research, 2023, 71(10).
[21]
YUE Y J, LIU Y H, ZHAO H, Short-term load forecasting based on CEEMDAN-SE and DBN [J]. Electrical Measurement & Instrumentation, 2020, 57(17):59-65.
[22]
KANG W H, XU T Q, WANG Y G, CEEMDAN-refined composite multiscale entropy and Stacking ensemble learning based short-term wind power prediction [J]. Water Resources and Hydropower Engineering, 2022, 53(2): 163-172.
[23]
WU S, WU C, LIN S, Analysis of complex time series using refined composite multiscale entropy. Phys Lett A, 2014, 378(20): 1369-1374.
[24]
LV K Y. Research on PM2.5 concentration prediction method based on CNN-LSTM [D]. Shandong University of Science and Technology, 2019.

Index Terms

  1. Prediction of O3 Concentration Based on CEEMDAN-RCMSE-LSTM Model

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICMLCA '23: Proceedings of the 2023 4th International Conference on Machine Learning and Computer Application
    October 2023
    1065 pages
    ISBN:9798400709449
    DOI:10.1145/3650215
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 16 April 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICMLCA 2023

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 10
      Total Downloads
    • Downloads (Last 12 months)10
    • Downloads (Last 6 weeks)2
    Reflects downloads up to 16 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media