Search research articles

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 scoping review of the upstream influences of admissions policies on applicant behaviour: Don't hate the player, hate the game.

Medical teacher·2026

Same author

Sublethal and transgenerational effects of spirodiclofen and cyenopyrafen on the life-history traits and population parameters of Tetranychus urticae Koch (Acari: Tetranychidae).

Pest management science·2025

Same author

CTLA-4-Ig therapy preserves cardiac function following myocardial infarction with reperfusion.

Cardiovascular research·2025

Same author

Visceral adipose tissue demonstrates a stronger association with venous thromboembolism than body mass index.

Journal of thrombosis and haemostasis : JTH·2025

Same author

Shear-dependent platelet aggregation by ChAdOx1 nCoV-19 vaccine: a novel biophysical mechanism for arterial thrombosis.

Blood·2025

Same author

Flood resilience through hybrid deep learning: Advanced forecasting for Taipei's urban drainage system.

Journal of environmental management·2025

Same journal

Microbiota under bloom stress: A review and meta-analysis of bloom-associated cyanopeptides, environmental stressors, and microbial shifts in free-living and host gut microbiomes.

The Science of the total environment·2026

Same journal

Environmental associations in spectral index-based soil salinity detection: A multi-region and multi-sensor assessment.

The Science of the total environment·2026

Same journal

Decoding seasonal urban heat dynamics at neighborhood-scale using explainable deep learning for climate-resilient, digital twin-ready green planning.

The Science of the total environment·2026

Same journal

The effects of microcystin-LR and its location within an environmental pool on rusty crayfish (Faxonius rusticus) behavior and physiology.

The Science of the total environment·2026

Same journal

An advanced hydrological approach for the characterization of the Water Scarcity Footprint at the sub-basin level.

The Science of the total environment·2026

Same journal

Irrigation management and groundwater recharge in Mediterranean intermontane basins: a multi-method evaluation of agricultural controls and interbasin variability.

The Science of the total environment·2026

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 20, 2025

The Visual Colorimetric Detection of Multi-nucleotide Polymorphisms on a Pneumatic Droplet Manipulation Platform

The Visual Colorimetric Detection of Multi-nucleotide Polymorphisms on a Pneumatic Droplet Manipulation Platform

Published on: September 27, 2016

Explore spatio-temporal PM2.5 features in northern Taiwan using machine learning techniques.

Fi-John Chang¹, Li-Chiu Chang², Che-Chia Kang¹

¹Department of Bioenvironmental Systems Engineering, National Taiwan University, Taipei 10617, Taiwan.

The Science of the Total Environment

|June 3, 2020

Summary

This summary is machine-generated.

Accurate prediction of fine particulate matter (PM2.5) is vital for public health. This study uses self-organizing maps and machine learning to visualize and predict PM2.5 concentrations, improving air quality forecasting.

Keywords:

Back propagation neural network (BPNN)Gamma Test Multi-step-ahead prediction PM2.5 Self-organizing map (SOM)Spatio-temporal variation

More Related Videos

Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry

Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry

Published on: March 9, 2018

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Related Experiment Videos

Last Updated: Dec 20, 2025

The Visual Colorimetric Detection of Multi-nucleotide Polymorphisms on a Pneumatic Droplet Manipulation Platform

The Visual Colorimetric Detection of Multi-nucleotide Polymorphisms on a Pneumatic Droplet Manipulation Platform

Published on: September 27, 2016

Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry

Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry

Published on: March 9, 2018

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Area of Science:

Environmental Science
Data Science
Atmospheric Chemistry

Background:

Accurate prediction of fine particulate matter (PM2.5) is challenging due to complex emission sources and regional transport.
Effective air pollution regulatory plans require symbolic representations of spatio-temporal PM2.5 features.
Self-organizing maps (SOM) offer a method for clustering high-dimensional data into meaningful topological maps.

Purpose of the Study:

To implement SOM for extracting and visualizing spatio-temporal features of long-term regional PM2.5 concentrations.
To explore the temporal behavior of PM2.5 at various time scales (yearly, seasonal, hourly).
To establish a machine learning model for predicting PM2.5 concentrations during high pollution events.

Main Methods:

Utilized the Self-Organizing Map (SOM) for clustering spatio-temporal PM2.5 data.
Applied the Kriging method to map spatial distributions across 25 monitoring stations in northern Taiwan.
Developed a machine learning model incorporating key variables identified by the Gamma Test for prediction.

Main Results:

Identified correlations between high PM2.5 concentrations and high population density/traffic load.
Observed significant seasonal variations impacting PM2.5 concentration levels.
Demonstrated that identified key input variables enhance the reliability and accuracy of multi-step-ahead PM2.5 prediction.

Conclusions:

Machine learning techniques, including SOM, can effectively summarize and visualize clustered spatio-temporal PM2.5 features.
The developed model improves the accuracy of air quality prediction, particularly for high pollution events.
Findings support enhanced public notification and air pollution regulatory strategies.