BiLSTM-BiGRU: A Fusion Deep Neural Network For Predicting Air Pollutant Concentration

Prasanjit Dey; Soumyabrata Dev; Bianca Schoen Phelan

doi:10.1109/IGARSS52108.2023.10282742

BiLSTM-BiGRU: A Fusion Deep Neural Network For Predicting Air Pollutant Concentration

Prasanjit Dey
, Soumyabrata Dev
, Bianca Schoen Phelan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Predicting air pollutant concentrations is an efficient way to prevent incidents by providing early warnings of harmful air pollutants. A precise prediction of air pollutant concentrations is an important factor in controlling and preventing air pollution. In this paper, we develop a bidirectional long-short-term memory and a bidirectional gated recurrent unit (BiLSTM-BiGRU) to predict PM_2.5 concentrations in a target city for different lead times. The BiLSTM extracts preliminary features, and the BiGRU further extracts deep features from air pollutant and meteorological data. The fully connected (FC) layer receives the output and makes an accurate prediction of the PM_2.5 concentration. The model is then compared with five other deep learning models in terms of root mean square error (RMSE), mean absolute error (MAE) and correlation (R²) over different lead times. The results indicate that the proposed model has at least 2.2 times lower RMSE than the other models.

Original language	English
Title of host publication	IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5166-5169
Number of pages	4
ISBN (Electronic)	9798350320107
DOIs	https://doi.org/10.1109/IGARSS52108.2023.10282742
Publication status	Published - 2023
Event	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States Duration: 16 Jul 2023 → 21 Jul 2023

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2023-July
ISSN (Electronic)	2153-6996

Conference

Conference	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/Territory	United States
City	Pasadena
Period	16/07/23 → 21/07/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Fusion deep neural network
GRU
LSTM
PM concentration prediction

Access to Document

10.1109/IGARSS52108.2023.10282742

Cite this

Dey, P., Dev, S., & Phelan, B. S. (2023). BiLSTM-BiGRU: A Fusion Deep Neural Network For Predicting Air Pollutant Concentration. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 5166-5169). (International Geoscience and Remote Sensing Symposium (IGARSS) ; Vol. 2023-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS52108.2023.10282742

Dey, Prasanjit ; Dev, Soumyabrata ; Phelan, Bianca Schoen. / BiLSTM-BiGRU : A Fusion Deep Neural Network For Predicting Air Pollutant Concentration. IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 5166-5169 (International Geoscience and Remote Sensing Symposium (IGARSS) ).

@inproceedings{91260e6f9ddf46ac9bd7987151e6cf95,

title = "BiLSTM-BiGRU: A Fusion Deep Neural Network For Predicting Air Pollutant Concentration",

abstract = "Predicting air pollutant concentrations is an efficient way to prevent incidents by providing early warnings of harmful air pollutants. A precise prediction of air pollutant concentrations is an important factor in controlling and preventing air pollution. In this paper, we develop a bidirectional long-short-term memory and a bidirectional gated recurrent unit (BiLSTM-BiGRU) to predict PM2.5 concentrations in a target city for different lead times. The BiLSTM extracts preliminary features, and the BiGRU further extracts deep features from air pollutant and meteorological data. The fully connected (FC) layer receives the output and makes an accurate prediction of the PM2.5 concentration. The model is then compared with five other deep learning models in terms of root mean square error (RMSE), mean absolute error (MAE) and correlation (R2) over different lead times. The results indicate that the proposed model has at least 2.2 times lower RMSE than the other models.",

keywords = "Fusion deep neural network, GRU, LSTM, PM concentration prediction",

author = "Prasanjit Dey and Soumyabrata Dev and Phelan, \{Bianca Schoen\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 ; Conference date: 16-07-2023 Through 21-07-2023",

year = "2023",

doi = "10.1109/IGARSS52108.2023.10282742",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS) ",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5166--5169",

booktitle = "IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

address = "United States",

}

Dey, P, Dev, S & Phelan, BS 2023, BiLSTM-BiGRU: A Fusion Deep Neural Network For Predicting Air Pollutant Concentration. in IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS) , vol. 2023-July, Institute of Electrical and Electronics Engineers Inc., pp. 5166-5169, 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023, Pasadena, United States, 16/07/23. https://doi.org/10.1109/IGARSS52108.2023.10282742

BiLSTM-BiGRU: A Fusion Deep Neural Network For Predicting Air Pollutant Concentration. / Dey, Prasanjit; Dev, Soumyabrata; Phelan, Bianca Schoen.
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. p. 5166-5169 (International Geoscience and Remote Sensing Symposium (IGARSS) ; Vol. 2023-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - BiLSTM-BiGRU

T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023

AU - Dey, Prasanjit

AU - Dev, Soumyabrata

AU - Phelan, Bianca Schoen

PY - 2023

Y1 - 2023

N2 - Predicting air pollutant concentrations is an efficient way to prevent incidents by providing early warnings of harmful air pollutants. A precise prediction of air pollutant concentrations is an important factor in controlling and preventing air pollution. In this paper, we develop a bidirectional long-short-term memory and a bidirectional gated recurrent unit (BiLSTM-BiGRU) to predict PM2.5 concentrations in a target city for different lead times. The BiLSTM extracts preliminary features, and the BiGRU further extracts deep features from air pollutant and meteorological data. The fully connected (FC) layer receives the output and makes an accurate prediction of the PM2.5 concentration. The model is then compared with five other deep learning models in terms of root mean square error (RMSE), mean absolute error (MAE) and correlation (R2) over different lead times. The results indicate that the proposed model has at least 2.2 times lower RMSE than the other models.

AB - Predicting air pollutant concentrations is an efficient way to prevent incidents by providing early warnings of harmful air pollutants. A precise prediction of air pollutant concentrations is an important factor in controlling and preventing air pollution. In this paper, we develop a bidirectional long-short-term memory and a bidirectional gated recurrent unit (BiLSTM-BiGRU) to predict PM2.5 concentrations in a target city for different lead times. The BiLSTM extracts preliminary features, and the BiGRU further extracts deep features from air pollutant and meteorological data. The fully connected (FC) layer receives the output and makes an accurate prediction of the PM2.5 concentration. The model is then compared with five other deep learning models in terms of root mean square error (RMSE), mean absolute error (MAE) and correlation (R2) over different lead times. The results indicate that the proposed model has at least 2.2 times lower RMSE than the other models.

KW - Fusion deep neural network

KW - GRU

KW - LSTM

KW - PM concentration prediction

UR - https://www.scopus.com/pages/publications/85178379741

U2 - 10.1109/IGARSS52108.2023.10282742

DO - 10.1109/IGARSS52108.2023.10282742

M3 - Conference contribution

AN - SCOPUS:85178379741

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 5166

EP - 5169

BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 16 July 2023 through 21 July 2023

ER -

Dey P, Dev S, Phelan BS. BiLSTM-BiGRU: A Fusion Deep Neural Network For Predicting Air Pollutant Concentration. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. p. 5166-5169. (International Geoscience and Remote Sensing Symposium (IGARSS) ). doi: 10.1109/IGARSS52108.2023.10282742

BiLSTM-BiGRU: A Fusion Deep Neural Network For Predicting Air Pollutant Concentration

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this