Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study pres...Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT) model and the K-means cluster algorithm to produce a regional landslide susceptibility map. Yanchang County, a typical landslide-prone area located in northwestern China, was taken as the area of interest to introduce the proposed application procedure. A landslide inventory containing 82 landslides was prepared and subsequently randomly partitioned into two subsets: training data(70% landslide pixels) and validation data(30% landslide pixels). Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means cluster algorithm. The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC) curve) of the proposed model was the highest, reaching 0.88,compared with traditional models(support vector machine(SVM) = 0.85, Bayesian network(BN) = 0.81,frequency ratio(FR) = 0.75, weight of evidence(WOE) = 0.76). The landslide frequency ratio and frequency density of the high susceptibility zones were 6.76/km^(2) and 0.88/km^(2), respectively, which were much higher than those of the low susceptibility zones. The top 20% interval of landslide occurrence probability contained 89% of the historical landslides but only accounted for 10.3% of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without containing more " stable" pixels. Therefore, the obtained susceptibility map is suitable for application to landslide risk management practices.展开更多
Overbuilding, i.e. capping or decking, of roads assigned for the transportation of dangerous goods in major cities is being considered more often in many countries including Sweden. This type of facility introduces a ...Overbuilding, i.e. capping or decking, of roads assigned for the transportation of dangerous goods in major cities is being considered more often in many countries including Sweden. This type of facility introduces a number of risks and challenges related to rare events, such as dangerous goods accidents in tunnels, with a potential to cause substantial damage, e.g. collapse of buildings on the over site development. Many argue that the major problem associated with risk evaluation of such risks is the lack of commonly agreed acceptance criteria and regulations. Approaching the problem from a scientific perspective suggests that the root cause of this problem has not been adequately identified. However, there are strong indications that it is because the nature of the risk is not adequately addressed in risk analysis. In this study, we have structured the problem and propose ways of making progress in the evaluation of risk exposure and risk control. It is concluded that several challenges are inherent in the risk management of decking over routes for the transport of dangerous goods, and that these must be addressed in order to be able to control the risk. One of the complicating factors is that it is practically and economically impossible to construct the overbuilding so that it can withstand the maximum permissible explosion load. The main conclusions of this study are that overbuilding of dangerous goods routes has the potential to lead to catastrophic events, that the transport of dangerous goods in the future is associated with considerable intrinsic uncertainties, and that the possibility of supervising and controlling the transport of goods is limited once the route is in use.展开更多
A relatively perfect coalmine fire risk-evaluating and order-arranging model that includes sixteen influential factors was established according to the statistical information of the fully mechanized coalface ground o...A relatively perfect coalmine fire risk-evaluating and order-arranging model that includes sixteen influential factors was established according to the statistical information of the fully mechanized coalface ground on the uncertainty measure theory. Then the single-index measure function of sixteen influential factors and the calculation method of computing the index weight ground on entropy theory were respectively established. The value assignment of sixteen influential factors was carried out by the qualitative analysis and observational data, respectively, in succession. The sequence of fire danger class of four experimental coalfaces could be obtained by the computational aids of Matlab according to the confidence level criterion. Some conclusions that the fire danger class of the No.l, No.2 and No.3 coalface belongs to high criticality can be obtained. But the fire danger class of the No.4 coalface belongs to higher criticality. The fire danger class of the No.4 coalface is more than that of the No.2 coalface. The fire danger class of the No.2 coalface is more than that of the No.1 coalface. Finally, the fire danger class of the No.1 coalface is more than that of the No.3 coalface.展开更多
基金This research is funded by the National Natural Science Foundation of China(Grant Nos.41807285 and 51679117)Key Project of the State Key Laboratory of Geohazard Prevention and Geoenvironment Protection(SKLGP2019Z002)+3 种基金the National Science Foundation of Jiangxi Province,China(20192BAB216034)the China Postdoctoral Science Foundation(2019M652287 and 2020T130274)the Jiangxi Provincial Postdoctoral Science Foundation(2019KY08)Fundamental Research Funds for National Universities,China University of Geosciences(Wuhan)。
文摘Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT) model and the K-means cluster algorithm to produce a regional landslide susceptibility map. Yanchang County, a typical landslide-prone area located in northwestern China, was taken as the area of interest to introduce the proposed application procedure. A landslide inventory containing 82 landslides was prepared and subsequently randomly partitioned into two subsets: training data(70% landslide pixels) and validation data(30% landslide pixels). Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means cluster algorithm. The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC) curve) of the proposed model was the highest, reaching 0.88,compared with traditional models(support vector machine(SVM) = 0.85, Bayesian network(BN) = 0.81,frequency ratio(FR) = 0.75, weight of evidence(WOE) = 0.76). The landslide frequency ratio and frequency density of the high susceptibility zones were 6.76/km^(2) and 0.88/km^(2), respectively, which were much higher than those of the low susceptibility zones. The top 20% interval of landslide occurrence probability contained 89% of the historical landslides but only accounted for 10.3% of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without containing more " stable" pixels. Therefore, the obtained susceptibility map is suitable for application to landslide risk management practices.
文摘Overbuilding, i.e. capping or decking, of roads assigned for the transportation of dangerous goods in major cities is being considered more often in many countries including Sweden. This type of facility introduces a number of risks and challenges related to rare events, such as dangerous goods accidents in tunnels, with a potential to cause substantial damage, e.g. collapse of buildings on the over site development. Many argue that the major problem associated with risk evaluation of such risks is the lack of commonly agreed acceptance criteria and regulations. Approaching the problem from a scientific perspective suggests that the root cause of this problem has not been adequately identified. However, there are strong indications that it is because the nature of the risk is not adequately addressed in risk analysis. In this study, we have structured the problem and propose ways of making progress in the evaluation of risk exposure and risk control. It is concluded that several challenges are inherent in the risk management of decking over routes for the transport of dangerous goods, and that these must be addressed in order to be able to control the risk. One of the complicating factors is that it is practically and economically impossible to construct the overbuilding so that it can withstand the maximum permissible explosion load. The main conclusions of this study are that overbuilding of dangerous goods routes has the potential to lead to catastrophic events, that the transport of dangerous goods in the future is associated with considerable intrinsic uncertainties, and that the possibility of supervising and controlling the transport of goods is limited once the route is in use.
基金Supported by the National Foundation of China(50974055)the Program for Changjiang Scholars and Innovative Research Team in University(IRT0618)Henan Province Basic and Leading-edge Technology Research Program(082300463205)
文摘A relatively perfect coalmine fire risk-evaluating and order-arranging model that includes sixteen influential factors was established according to the statistical information of the fully mechanized coalface ground on the uncertainty measure theory. Then the single-index measure function of sixteen influential factors and the calculation method of computing the index weight ground on entropy theory were respectively established. The value assignment of sixteen influential factors was carried out by the qualitative analysis and observational data, respectively, in succession. The sequence of fire danger class of four experimental coalfaces could be obtained by the computational aids of Matlab according to the confidence level criterion. Some conclusions that the fire danger class of the No.l, No.2 and No.3 coalface belongs to high criticality can be obtained. But the fire danger class of the No.4 coalface belongs to higher criticality. The fire danger class of the No.4 coalface is more than that of the No.2 coalface. The fire danger class of the No.2 coalface is more than that of the No.1 coalface. Finally, the fire danger class of the No.1 coalface is more than that of the No.3 coalface.
