Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Day-Ahead PM2.5 Concentration Forecasting Using WT-VMD Based Decomposition Method and Back Propagation Neural Network

Deyun Wang1,2, Yanling Liu3, Hongyuan Luo4

  • 1School of Economics and Management, China University of Geosciences, Wuhan 430074, China. wang.deyun@hotmail.com.

International Journal of Environmental Research and Public Health
|July 15, 2017
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Fe-Co-Ni Ternary Single-Atom Catalysts for Efficient Electrochemical Nitrate Reduction.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Investigating the Potential Mechanism of Oxymatrine in Alleviating Heat Stress Injury Based on Network Pharmacology, Molecular Docking, and In Vitro Validation.

International journal of molecular sciences·2026
Same author

Serum beta-2 microglobulin as a diagnostic biomarker for pediatric Epstein-Barr virus infections: a retrospective study.

Frontiers in pediatrics·2026
Same author

Spiky mesoporous silica-based nanovaccines enhance mucosal immunity with improved intestinal retention and antigen accessibility.

Materials today. Bio·2026
Same author

Trigeminal motor root anatomy from pons to foramen ovale and its surgical implications: A study using epoxy sheet plastination and three-dimensional reconstruction.

Annals of anatomy = Anatomischer Anzeiger : official organ of the Anatomische Gesellschaft·2026
Same author

REGγ Suppresses Ferroptosis and Induces Drug Resistance by Degrading WDR6 in Chondrosarcoma.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Accurate forecasting of fine particulate matter (PM2.5) concentration is vital. A new hybrid model using wavelet transform, variational mode decomposition, and a differential evolution-optimized neural network significantly improves PM2.5 prediction accuracy.

Area of Science:

  • Environmental Science
  • Atmospheric Chemistry
  • Data Science

Background:

  • Accurate forecasting of fine particulate matter (PM2.5) is essential for public health and environmental protection.
  • The inherent instability and intermittency of PM2.5 concentration data present significant forecasting challenges.

Purpose of the Study:

  • To develop and validate a novel hybrid model for enhanced PM2.5 concentration forecasting.
  • To address the difficulties posed by the complex nature of PM2.5 time series data.

Main Methods:

  • A hybrid approach combining Wavelet Transform (WT) for signal decomposition, Variational Mode Decomposition (VMD) for mode separation, and a Differential Evolution (DE) optimized Back Propagation (BP) neural network for forecasting.
  • WT disassembles the PM2.5 series into frequency subsets, VMD decomposes these into variational modes (VMs), and the DE-BP model forecasts each VM.
Keywords:
PM2.5 concentration forecastingback propagation neural networkdifferential evolutionvariational mode decompositionwavelet transform

Related Experiment Videos

Main Results:

  • The proposed hybrid WT-VMD-DE-BP model demonstrated superior performance in PM2.5 concentration forecasting compared to other evaluated models.
  • Validation using PM2.5 data from Wuhan and Tianjin, China, confirmed the model's effectiveness.

Conclusions:

  • The hybrid WT-VMD-DE-BP model offers a robust and accurate solution for PM2.5 concentration forecasting.
  • This approach effectively handles the complexities of PM2.5 data, leading to improved prediction accuracy for environmental and public health applications.