Ai Based Air Quality Pm2.5 Forecasting Models for Developing Countries: A Case Study of Ho Chi Minh City, Vietnam

28 Pages Posted: 16 May 2022

See all articles by Rajnish Rakholia

Rajnish Rakholia

affiliation not provided to SSRN

Quan Le

affiliation not provided to SSRN

Bang Quoc Ho

affiliation not provided to SSRN

Khue Vu

affiliation not provided to SSRN

Ricardo Simon Carbajo

University College Dublin (UCD)

Abstract

Outdoor air pollution damages the climate and causes many diseases. In particular, Particulate Matter (PM2.5)  is considered a hazardous air pollutant to human health. Accurate hourly forecasting of the PM2.5 concentration is thus of significant importance for public health, helping the citizens to plan the measures to alleviate the harmful effect.This study analyses and discusses the temporal characteristics of PM2.5 at different locations in Ho Chi Minh City (HCMC), Vietnam - an economic centre and a megacity in a developing country with a population of 8.99 million people. We developed several AI-based one-shot multi-step PM2.5 forecasting models, with both an hourly forecast granularity and a 24-hour rolling mean. These Machine Learning algorithms include Stochastic Gradient Descent Regressor, hybrid 1D CNN-LSTM, eXtreme Gradient Boosting Regressor, and Prophet. We collected the data from six monitoring stations installed by the HealthyAir project in HCMC, including traffic, residential and industrial areas. In addition, we developed a suitable model training protocol using data from a short period to address the non-stationarity of the PM 2.5 time series. Our proposed PM 2.5 forecasting models achieve state-of-the-art accuracy and will be deployed in our HealthyAir mobile app to warn HCMC citizens of air pollution issues.

Keywords: Urban air quality, PM2.5 Forecasting, Spatiotemporal analysis, Machine learning, Ho Chi Minh City, Vietnam

Suggested Citation

Rakholia, Rajnish and Le, Quan and Ho, Bang Quoc and Vu, Khue and Carbajo, Ricardo Simon, Ai Based Air Quality Pm2.5 Forecasting Models for Developing Countries: A Case Study of Ho Chi Minh City, Vietnam. Available at SSRN: https://ssrn.com/abstract=4111434 or http://dx.doi.org/10.2139/ssrn.4111434

Rajnish Rakholia

affiliation not provided to SSRN ( email )

No Address Available

Quan Le

affiliation not provided to SSRN ( email )

No Address Available

Bang Quoc Ho (Contact Author)

affiliation not provided to SSRN ( email )

No Address Available

Khue Vu

affiliation not provided to SSRN ( email )

No Address Available

Ricardo Simon Carbajo

University College Dublin (UCD) ( email )

Dublin

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
76
Abstract Views
597
Rank
589,776
PlumX Metrics