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 Video

Updated: Nov 27, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K

An improved deep learning model for predicting daily PM2.5 concentration.

Fei Xiao1, Mei Yang2, Hong Fan2

  • 1School of Public Health, Southern Medical University, Guangzhou, 510515, Guangdong, China.

Scientific Reports
|December 3, 2020
PubMed
Summary
This summary is machine-generated.

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

A SARS-CoV-2 antibody curbs viral nucleocapsid protein-induced complement hyperactivation.

Nature communications·2021
Same author

Cooperation of ATF4 and CTCF promotes adipogenesis through transcriptional regulation.

Cell biology and toxicology·2021
Same author

Joint line plate fixation for tibial plateau fractures caused by hyperextension varus.

Experimental and therapeutic medicine·2021
Same author

Effective Generation of Glucosylpiericidins with Selective Cytotoxicities and Insights into Their Biosynthesis.

Applied and environmental microbiology·2021
Same author

A signature of estimate-stromal-immune score-based genes associated with the prognosis of lung adenocarcinoma.

Translational lung cancer research·2021
Same author

Cholangiojejunostomy for multiple biliary ducts in living donor liver transplantation: A case report.

World journal of clinical cases·2021
Same journal

Therapeutic potential of crude protein extracts from two Egyptian freshwater snails Lanistes carinatus and Bellamya unicolor.

Scientific reports·2026
Same journal

Microbial contamination of donor corneas and post-keratoplasty endophthalmitis: a comparison between Japanese and U.S. eye banks using cold storage.

Scientific reports·2026
Same journal

Prevalence and contributing factors of virological non-suppression among adult patients on first-line antiretroviral therapy in tertiary hospitals in Ethiopia.

Scientific reports·2026
Same journal

An in vitro comparison of color stability between alkasite and different restorative materials in various staining solutions.

Scientific reports·2026
Same journal

Toward accessible mRNA LNP formulation: systematic evaluation of mixing strategies and key parameters.

Scientific reports·2026
Same journal

A network analysis of personality traits, mentalizing, and psychological health in Chinese college students.

Scientific reports·2026
See all related articles

This study introduces a weighted long short-term memory neural network extended model (WLSTME) for accurate PM2.5 prediction. The WLSTME model effectively considers site density and wind conditions, outperforming existing methods in accuracy.

Area of Science:

  • Environmental Science
  • Data Science
  • Atmospheric Science

Background:

  • Air pollution, particularly fine particulate matter (PM2.5), poses significant public health risks.
  • Accurate PM2.5 concentration prediction is vital for environmental management and health protection.
  • Existing models often overlook the varying spatiotemporal correlations influenced by uneven monitoring site distribution and local conditions.

Purpose of the Study:

  • To develop an advanced model for precise PM2.5 forecasting.
  • To address the limitations of previous methods by incorporating the impact of monitoring site density and wind conditions on spatiotemporal correlations.
  • To improve the accuracy of PM2.5 predictions by accounting for complex environmental factors.

Main Methods:

  • Proposed a weighted long short-term memory neural network extended model (WLSTME).

More Related Videos

Visualizing Field Data Collection Procedures of Exposure and Biomarker Assessments for the Household Air Pollution Intervention Network Trial in India
09:33

Visualizing Field Data Collection Procedures of Exposure and Biomarker Assessments for the Household Air Pollution Intervention Network Trial in India

Published on: December 23, 2022

2.5K

Related Experiment Videos

Last Updated: Nov 27, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K
Visualizing Field Data Collection Procedures of Exposure and Biomarker Assessments for the Household Air Pollution Intervention Network Trial in India
09:33

Visualizing Field Data Collection Procedures of Exposure and Biomarker Assessments for the Household Air Pollution Intervention Network Trial in India

Published on: December 23, 2022

2.5K
  • Utilized multilayer perception (MLP) to generate weighted historical PM2.5 data based on neighbor site proximity, pollution levels, and wind conditions.
  • Integrated weighted neighbor data with central site historical data into a long short-term memory (LSTM) network to capture spatiotemporal dependencies.
  • Incorporated meteorological data with extracted spatiotemporal features using another MLP for final PM2.5 forecasting.

    • Main Results:

    • The WLSTME model demonstrated superior performance compared to three existing methods.
    • Achieved the lowest Root Mean Square Error (RMSE) of 40.67 and Mean Absolute Error (MAE) of 26.10.
    • Obtained the highest correlation coefficient (p) of 0.59, indicating strong predictive power.
    • Consistently outperformed other models across all seasons and regions in Beijing-Tianjin-Hebei.

    Conclusions:

    • The proposed WLSTME model significantly enhances PM2.5 prediction accuracy.
    • WLSTME effectively accounts for the influence of monitoring site density and wind conditions on spatiotemporal air pollution dynamics.
    • The model offers a robust solution for improving air quality forecasting and public health strategies.