Standard

Atmospheric dispersion prediction and source estimation of hazardous gas using artificial neural network, particle swarm optimization and expectation maximization. / Qiu, Sihang; Chen, Bin; Wang, Rongxiao; Zhu, Zhengqiu; Wang, Yuan; Qiu, Xiaogang.

In: Atmospheric Environment, Vol. 178, 01.04.2018, p. 158-163.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Qiu, Sihang ; Chen, Bin ; Wang, Rongxiao ; Zhu, Zhengqiu ; Wang, Yuan ; Qiu, Xiaogang. / Atmospheric dispersion prediction and source estimation of hazardous gas using artificial neural network, particle swarm optimization and expectation maximization. In: Atmospheric Environment. 2018 ; Vol. 178. pp. 158-163.

BibTeX

@article{79f5f97ce6e14605be1951de7e3ca7d7,
title = "Atmospheric dispersion prediction and source estimation of hazardous gas using artificial neural network, particle swarm optimization and expectation maximization",
abstract = "Hazardous gas leak accident has posed a potential threat to human beings. Predicting atmospheric dispersion and estimating its source become increasingly important in emergency management. Current dispersion prediction and source estimation models cannot satisfy the requirement of emergency management because they are not equipped with high efficiency and accuracy at the same time. In this paper, we develop a fast and accurate dispersion prediction and source estimation method based on artificial neural network (ANN), particle swarm optimization (PSO) and expectation maximization (EM). The novel method uses a large amount of pre-determined scenarios to train the ANN for dispersion prediction, so that the ANN can predict concentration distribution accurately and efficiently. PSO and EM are applied for estimating the source parameters, which can effectively accelerate the process of convergence. The method is verified by the Indianapolis field study with a SF6 release source. The results demonstrate the effectiveness of the method.",
keywords = "Atmospheric dispersion, Expectation maximization (EM), Neural network, Particle swarm optimization (PSO), Source estimation",
author = "Sihang Qiu and Bin Chen and Rongxiao Wang and Zhengqiu Zhu and Yuan Wang and Xiaogang Qiu",
year = "2018",
month = "4",
day = "1",
doi = "10.1016/j.atmosenv.2018.01.056",
language = "English",
volume = "178",
pages = "158--163",
journal = "Atmospheric Environment",
issn = "1352-2310",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Atmospheric dispersion prediction and source estimation of hazardous gas using artificial neural network, particle swarm optimization and expectation maximization

AU - Qiu, Sihang

AU - Chen, Bin

AU - Wang, Rongxiao

AU - Zhu, Zhengqiu

AU - Wang, Yuan

AU - Qiu, Xiaogang

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Hazardous gas leak accident has posed a potential threat to human beings. Predicting atmospheric dispersion and estimating its source become increasingly important in emergency management. Current dispersion prediction and source estimation models cannot satisfy the requirement of emergency management because they are not equipped with high efficiency and accuracy at the same time. In this paper, we develop a fast and accurate dispersion prediction and source estimation method based on artificial neural network (ANN), particle swarm optimization (PSO) and expectation maximization (EM). The novel method uses a large amount of pre-determined scenarios to train the ANN for dispersion prediction, so that the ANN can predict concentration distribution accurately and efficiently. PSO and EM are applied for estimating the source parameters, which can effectively accelerate the process of convergence. The method is verified by the Indianapolis field study with a SF6 release source. The results demonstrate the effectiveness of the method.

AB - Hazardous gas leak accident has posed a potential threat to human beings. Predicting atmospheric dispersion and estimating its source become increasingly important in emergency management. Current dispersion prediction and source estimation models cannot satisfy the requirement of emergency management because they are not equipped with high efficiency and accuracy at the same time. In this paper, we develop a fast and accurate dispersion prediction and source estimation method based on artificial neural network (ANN), particle swarm optimization (PSO) and expectation maximization (EM). The novel method uses a large amount of pre-determined scenarios to train the ANN for dispersion prediction, so that the ANN can predict concentration distribution accurately and efficiently. PSO and EM are applied for estimating the source parameters, which can effectively accelerate the process of convergence. The method is verified by the Indianapolis field study with a SF6 release source. The results demonstrate the effectiveness of the method.

KW - Atmospheric dispersion

KW - Expectation maximization (EM)

KW - Neural network

KW - Particle swarm optimization (PSO)

KW - Source estimation

UR - http://www.scopus.com/inward/record.url?scp=85041462328&partnerID=8YFLogxK

U2 - 10.1016/j.atmosenv.2018.01.056

DO - 10.1016/j.atmosenv.2018.01.056

M3 - Article

VL - 178

SP - 158

EP - 163

JO - Atmospheric Environment

T2 - Atmospheric Environment

JF - Atmospheric Environment

SN - 1352-2310

ER -

ID: 44890945