Search research articles

Search research articles

Related Experiment Videos

Multi-Horizon Air Pollution Forecasting with Deep Neural Networks.

Mirche Arsov¹, Eftim Zdravevski¹, Petre Lameski¹

¹Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, 1000 Skopje, North Macedonia.

Sensors (Basel, Switzerland)

|February 13, 2021

Summary

Related Concept Videos

Neural Control of Respiration

Neural Control of Respiration

The neural regulation of respiration is a meticulously coordinated process primarily controlled by the respiratory centers located within the brainstem. These centers, composed of specialized neurons, transmit nerve impulses that control the contraction and relaxation of our respiratory muscles.
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...

You might also read

Related Articles

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

Sort by

Same author

Development and Implementation of a Defect Detection Model for Microstructures Using Image Processing Methods.

Materials (Basel, Switzerland)·2025

Same author

AI Act Compliance Within the MyHealth@EU Framework: Tutorial.

Journal of medical Internet research·2025

Same author

Innovative artificial intelligence for practice management in medical healthcare.

European heart journal·2025

Same author

Forecasting air pollution with deep learning with a focus on impact of urban traffic on PM10 and noise pollution.

PloS one·2024

Same author

mHealth Apps Targeting Obesity and Overweight in Young People: App Review and Analysis.

JMIR mHealth and uHealth·2023

Same author

Correction: Ambient Assisted Living: Scoping Review of Artificial Intelligence Models, Domains, Technology, and Concerns.

Journal of medical Internet research·2022

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

This study uses Recurrent Neural Network (RNN) models to predict PM10 air pollution levels in Skopje. The advanced models accurately forecast pollution, outperforming traditional methods for better environmental management.

Area of Science:

Environmental Science
Computer Science
Data Science

Background:

Air pollution is a critical global issue, particularly severe in urban centers like Skopje, North Macedonia.
Skopke frequently ranks among the world's most polluted cities, especially during winter, due to high population density and diverse emission sources.
Effective air quality management requires accurate, short-term pollution forecasting.

Purpose of the Study:

To develop and evaluate advanced deep learning models for predicting PM10 particle concentrations.
To assess the efficacy of Recurrent Neural Network (RNN) models with long short-term memory (LSTM) units for air quality forecasting.
To compare the performance of these novel models against traditional statistical methods like ARIMA.

Main Methods:

Keywords:

LSTM RNN air pollution convolutional networks deep learning

Related Experiment Videos

Utilized historical air quality data from sensors across Skopje.

Incorporated meteorological data, including temperature and humidity, as input features.

Implemented and compared various deep learning architectures, focusing on RNN-LSTM, against an Auto-regressive Integrated Moving Average (ARIMA) baseline model.

Predicted PM10 levels at 6, 12, and 24-hour future intervals.

Main Results:

The proposed deep learning models, particularly RNN-LSTM, demonstrated superior performance in predicting PM10 levels compared to the ARIMA model.
The models consistently achieved higher accuracy in forecasting air pollution.
The predictive capabilities were validated across multiple future time horizons (6, 12, and 24 hours).

Conclusions:

Recurrent Neural Network models with LSTM units are effective tools for accurate PM10 air pollution prediction in urban environments.
These advanced models offer a significant improvement over traditional methods for air quality forecasting.
The findings support the use of these predictive models to aid decision-makers in implementing proactive air pollution management strategies.