Comparison of Machine Learning Models for Hazardous Gas Dispersion Prediction in Field Cases
Dispersion prediction plays a significant role in the management and emergency response to hazardous gas emissions and accidental leaks. Compared with conventional atmospheric dispersion models, machine leaning (ML) models have both high accuracy and efficiency in terms of prediction, especially in...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-07-01
|
Series: | International Journal of Environmental Research and Public Health |
Subjects: | |
Online Access: | http://www.mdpi.com/1660-4601/15/7/1450 |
id |
doaj-5e49a51c1e394e22b335141e163b1aa3 |
---|---|
record_format |
Article |
spelling |
doaj-5e49a51c1e394e22b335141e163b1aa32020-11-24T22:59:11ZengMDPI AGInternational Journal of Environmental Research and Public Health1660-46012018-07-01157145010.3390/ijerph15071450ijerph15071450Comparison of Machine Learning Models for Hazardous Gas Dispersion Prediction in Field CasesRongxiao Wang0Bin Chen1Sihang Qiu2Zhengqiu Zhu3Yiduo Wang4Yiping Wang5Xiaogang Qiu6College of System Engineering, National University of Defense Technology, 109 Deya Road, Changsha 410073, ChinaCollege of System Engineering, National University of Defense Technology, 109 Deya Road, Changsha 410073, ChinaCollege of System Engineering, National University of Defense Technology, 109 Deya Road, Changsha 410073, ChinaCollege of System Engineering, National University of Defense Technology, 109 Deya Road, Changsha 410073, ChinaCollege of System Engineering, National University of Defense Technology, 109 Deya Road, Changsha 410073, ChinaThe Naval 902 Factory, Shanghai 200083, ChinaCollege of System Engineering, National University of Defense Technology, 109 Deya Road, Changsha 410073, ChinaDispersion prediction plays a significant role in the management and emergency response to hazardous gas emissions and accidental leaks. Compared with conventional atmospheric dispersion models, machine leaning (ML) models have both high accuracy and efficiency in terms of prediction, especially in field cases. However, selection of model type and the inputs of the ML model are still essential problems. To address this issue, two ML models (i.e., the back propagation (BP) network and support vector regression (SVR) with different input selections (i.e., original monitoring parameters and integrated Gaussian parameters) are proposed in this paper. To compare the performances of presented ML models in field cases, these models are evaluated using the Prairie Grass and Indianapolis field data sets. The influence of the training set scale on the performances of ML models is analyzed as well. Results demonstrate that the integrated Gaussian parameters indeed improve the prediction accuracy in the Prairie Grass case. However, they do not make much difference in the Indianapolis case due to their inadaptability to the complex terrain conditions. In addition, it can be summarized that the SVR shows better generalization ability with relatively small training sets, but tends to under-fit the training data. In contrast, the BP network has a stronger fitting ability, but sometimes suffers from an over-fitting problem. As a result, the model and input selection presented in this paper will be of great help to environmental and public health protection in real applications.http://www.mdpi.com/1660-4601/15/7/1450hazardous gas dispersion predictionback propagation networksupport vector regressioninput selectionfield case |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rongxiao Wang Bin Chen Sihang Qiu Zhengqiu Zhu Yiduo Wang Yiping Wang Xiaogang Qiu |
spellingShingle |
Rongxiao Wang Bin Chen Sihang Qiu Zhengqiu Zhu Yiduo Wang Yiping Wang Xiaogang Qiu Comparison of Machine Learning Models for Hazardous Gas Dispersion Prediction in Field Cases International Journal of Environmental Research and Public Health hazardous gas dispersion prediction back propagation network support vector regression input selection field case |
author_facet |
Rongxiao Wang Bin Chen Sihang Qiu Zhengqiu Zhu Yiduo Wang Yiping Wang Xiaogang Qiu |
author_sort |
Rongxiao Wang |
title |
Comparison of Machine Learning Models for Hazardous Gas Dispersion Prediction in Field Cases |
title_short |
Comparison of Machine Learning Models for Hazardous Gas Dispersion Prediction in Field Cases |
title_full |
Comparison of Machine Learning Models for Hazardous Gas Dispersion Prediction in Field Cases |
title_fullStr |
Comparison of Machine Learning Models for Hazardous Gas Dispersion Prediction in Field Cases |
title_full_unstemmed |
Comparison of Machine Learning Models for Hazardous Gas Dispersion Prediction in Field Cases |
title_sort |
comparison of machine learning models for hazardous gas dispersion prediction in field cases |
publisher |
MDPI AG |
series |
International Journal of Environmental Research and Public Health |
issn |
1660-4601 |
publishDate |
2018-07-01 |
description |
Dispersion prediction plays a significant role in the management and emergency response to hazardous gas emissions and accidental leaks. Compared with conventional atmospheric dispersion models, machine leaning (ML) models have both high accuracy and efficiency in terms of prediction, especially in field cases. However, selection of model type and the inputs of the ML model are still essential problems. To address this issue, two ML models (i.e., the back propagation (BP) network and support vector regression (SVR) with different input selections (i.e., original monitoring parameters and integrated Gaussian parameters) are proposed in this paper. To compare the performances of presented ML models in field cases, these models are evaluated using the Prairie Grass and Indianapolis field data sets. The influence of the training set scale on the performances of ML models is analyzed as well. Results demonstrate that the integrated Gaussian parameters indeed improve the prediction accuracy in the Prairie Grass case. However, they do not make much difference in the Indianapolis case due to their inadaptability to the complex terrain conditions. In addition, it can be summarized that the SVR shows better generalization ability with relatively small training sets, but tends to under-fit the training data. In contrast, the BP network has a stronger fitting ability, but sometimes suffers from an over-fitting problem. As a result, the model and input selection presented in this paper will be of great help to environmental and public health protection in real applications. |
topic |
hazardous gas dispersion prediction back propagation network support vector regression input selection field case |
url |
http://www.mdpi.com/1660-4601/15/7/1450 |
work_keys_str_mv |
AT rongxiaowang comparisonofmachinelearningmodelsforhazardousgasdispersionpredictioninfieldcases AT binchen comparisonofmachinelearningmodelsforhazardousgasdispersionpredictioninfieldcases AT sihangqiu comparisonofmachinelearningmodelsforhazardousgasdispersionpredictioninfieldcases AT zhengqiuzhu comparisonofmachinelearningmodelsforhazardousgasdispersionpredictioninfieldcases AT yiduowang comparisonofmachinelearningmodelsforhazardousgasdispersionpredictioninfieldcases AT yipingwang comparisonofmachinelearningmodelsforhazardousgasdispersionpredictioninfieldcases AT xiaogangqiu comparisonofmachinelearningmodelsforhazardousgasdispersionpredictioninfieldcases |
_version_ |
1725645419443126272 |