Naslov
A Layered Recurrent Neural Network for Imputing Air Pollutants Missing Data and Prediction of NO2, O3 , PM 10, and PM 2.5

Autori
Turabieh, Hamza ; Sheta, Alaa ; Braik, Malik ; Kovač-Andrić, Elvira

Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, ostalo

Knjiga
Forecasting in Mathematics - Recent Advances, New Perspectives and Applications

Urednik/ci
Jaoude, Abdo Abou

Izdavač
IntechOpen

Grad
London : Delhi

Godina
2020

Raspon stranica
1-22

ISBN
978-1-83880-827-3

Ključne riječi
imputing missing data, air pollutants, prediction, layered recurrentneural network

Sažetak
To fulfill the national air quality standards, many countries have created emis-sions monitoring strategies on air quality. Nowadays, policymakers and air qualityexecutives depend on scientific computation and prediction models to monitor thatcause air pollution, especially in industrial cities. Air pollution is considered one ofthe primary problems that could cause many human health problems such asasthma, damage to lungs, and even death. In this study, we present investigateddevelopment forecasting models for air pollutant attributes including ParticulateMatters (PM2.5, PM10), ground-level Ozone (O3), and Nitrogen Oxides (NO2). Thedataset used was collected from Dubrovnik city, which is located in the east ofCroatia. The collected data has missing values. Therefore, we suggested the use of aLayered Recurrent Neural Network (L-RNN) to impute the missing value(s) of airpollutant attributes then build forecasting models. We adopted four regressionmodels to forecast air pollutant attributes, which are: Multiple Linear Regression(MLR), Decision Tree Regression (DTR), Artificial Neural Network (ANN) andL-RNN. The obtained results show that the proposed method enhances the overallperformance of other forecasting models.

Izvorni jezik
Engleski

Znanstvena područja
Kemija

POVEZANOST RADA