doi: 10.18178/ijesd.2023.14.2.1428
Enhancing Air Quality Prediction Accuracy Using Hybrid Deep Learning
Trang Pham Thi Quynh**
,
Tuyen Nguyen Viet ,
Hang Duong Thi ,
Kha Hoang Manh
- Faculty of Electronics, Hanoi University of Industry
- Manuscript receivedJune 23, 2022
- revisedAugust 15, 2022
- acceptedSeptember 7, 2022
Abstract
PM2.5 (Particulate Matter) and PM10 are themost common pollutants, and the increasing of concentration inthe air will threaten people’s health. The machine learningmethod has recently been of particular interest to manyresearchers due to its effectiveness in air quality predictionmodels. Many solutions employing deep learning-basedtechniques such as Convolutional Neural Networks (CNN),Long Short-Term Memory (LSTM), and hybrid CNN-LSTMmodels to enhance air quality prediction accuracy have beendeveloped. This paper proposes a hybrid Encoder STM modelfor predicting the next day to the next five days’ PM2.5 andPM10 concentrations in Hanoi. Additionally, we proposed fiveextended features to increase the accuracy of prediction. Thenother models, namely the LSTM model and the BidirectionalLSTM model, are also considered for PM2.5 and PM10concentration prediction. Our results show that the proposedapproaches outperform other state-of-the-art deeplearning-based methods on both Mean Absolute Error (MAE)and Root Mean Square Error (RMSE) due to low error and thesmall number of features.
Keywords
- Urban air quality
- PM2.5
- PM10 prediction analysis
- machine learning
- hybrid deep learning
How to Cite
Trang Pham Thi Quynh*, Tuyen Nguyen Viet, Hang Duong Thi, and Kha Hoang Manh, "Enhancing Air Quality Prediction Accuracy Using Hybrid Deep Learning," International Journal of Environmental Science and Development, vol. 14, no. 2, pp. 155-159, 2023. https://doi.org/10.18178/ijesd.2023.14.2.1428
Copyright & License
Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).