Landslide susceptibility mapping of mountain roads is frequently confronted by insufficient historical landslide sample data,multicollinearity of existing evaluation index factors,and inconsistency of evaluation facto...Landslide susceptibility mapping of mountain roads is frequently confronted by insufficient historical landslide sample data,multicollinearity of existing evaluation index factors,and inconsistency of evaluation factors due to regional environmental variations.Then,a single machine learning model can easily become overfitting,thus reducing the accuracy and robustness of the evaluation model.This paper proposes a combined machine-learning model to address the issues.The landslide susceptibility in mountain roads were mapped by using factor analysis to normalize and reduce the dimensionality of the initial condition factor and generating six new combination factors as evaluation indexes.The mountain roads in the Youxi County,Fujian Province,China were used for the landslide susceptibility mapping.Three most frequently used machine learning techniques,support vector machine(SVM),random forest(RF),and artificial neural network(ANN)models,were used to model the landslide susceptibility of the study area and validate the accuracy of this evaluation index system.The global minimum variance portfolio was utilized to construct a machine learning combined model.5-fold cross-validation,statistical indexes,and AUC(Area Under Curve)values were implemented to evaluate the predictive accuracy of the landslide susceptibility model.The mean AUC values for the SVM,RF,and ANN models in the training stage were 89.2%,88.5%,and 87.9%,respectively,and 78.0%,73.7%,and 76.7%,respectively,in the validating stage.In the training and validation stages,the mean AUC values of the combined model were 92.4% and 87.1%,respectively.The combined model provides greater prediction accuracy and model robustness than one single model.展开更多
Global climate change is intensifying the impact of slope hazards,particularly rainfall-induced landslide hazards(RILH),on mountain road networks(MRNs).However,effective quantitative models for dynamically assessing M...Global climate change is intensifying the impact of slope hazards,particularly rainfall-induced landslide hazards(RILH),on mountain road networks(MRNs).However,effective quantitative models for dynamically assessing MRNs vulnerability under RILH disturbances are still lacking.To bridge this gap,this study develops a Cascading Failure Model for Rainfall-Induced Landslide Hazard(CFM-RILH).Validation via a case study of the GarzêTibetan Autonomous Prefecture Road Network(GTPRNs)reveals key characteristics of MRNs system vulnerability under RILH disturbances:(1)Under the disturbance effects of RILH,the vulnerability of the MRNs system follows a nonlinear phase transition law that intensifies with increasing disturbance intensity,exhibiting a distinct critical threshold.When the disturbance intensity exceeds this threshold,the system undergoes a global cascading failure phenomenon analogous to an“avalanche.”(2)Under RILH disturbances,the robustness of the MRNs system possesses a distinct safety boundary.Exceeding this boundary not only fails to improve hazard resistance but instead substantially elevates the risk of large-scale cascading failure.(3)Increasing network redundancy may be considered one of the primary engineering measures for enhancing MRNs resilience against such disturbances.Based on these findings,we propose a“Two-Stage Emergency Response and Hierarchical Fortification”strategy specifically to improve the resilience of GTPRNs impacted by RILH.The CFM-RILH model provides an effective tool for assessing road network vulnerability under such hazards.Furthermore,its modeling framework can also inform vulnerability assessment and resilience strategy development for road networks affected by other types of slope hazards.展开更多
SONG Fangrong, the Tu nationality girl who grew up drinking water from mountain springs, walked into the Great Hall of the People in Beijing to accept the highest prize for China’s youth—the "May 4th Youth Priz...SONG Fangrong, the Tu nationality girl who grew up drinking water from mountain springs, walked into the Great Hall of the People in Beijing to accept the highest prize for China’s youth—the "May 4th Youth Prize." Not long before, she had been named one of the National Ten Outstanding Youths. She is the only individual to have won both.展开更多
Despite the complexity and high crash risk associated with driving on mountainous roads,there is a lack of comprehensive understanding of factors influencing driving performance and increasing risk of crashes on mount...Despite the complexity and high crash risk associated with driving on mountainous roads,there is a lack of comprehensive understanding of factors influencing driving performance and increasing risk of crashes on mountainous roads.To address this gap,this study conducts a systematic review by employing the preferred reporting items for systematic reviews and meta-analysis(PRISMA)technique and selected 54 papers for review.The study provides insights into various data collection approaches,including crash history-based studies,naturalistic driving studies,and simulator-based studies,and the performance measures used to analyze driving performance on mountainous roads,including various longitudinal,and lateral measures as well as crash probability.Additionally,the study explores different contributing factors,including drivers,highways,vehicles,and light and weather characteristics,which significantly influence driving performance on mountainous roads.The study reveals a strong correlation between highway characteristics,such as roadway geometry,traffic conditions,road markings,etc.,and driving performance.Moreover,the findings highlight a significant impact of age,gender,and driving experience on driving performance.Most importantly,the study highlights significant gaps in literature,which may serve as guides for future research endeavors in safety assessment of mountainous roads.These gaps include absence of consideration of driver education,distraction,and prevalent highway features like sight distance and transition curve length.Furthermore,vehicle types including SUVs,and heavy vehicles have been overlooked in most studies to determine their impact on driving performance.Additionally,the study emphasized the importance of selecting and combining multiple performance measures for a more comprehensive analysis.展开更多
The settlement of widened highway subgrade in mountainous area is not only affected by the interaction between new and existing subgrade,but also seriously restricted by the external retaining wall.Based on the practi...The settlement of widened highway subgrade in mountainous area is not only affected by the interaction between new and existing subgrade,but also seriously restricted by the external retaining wall.Based on the practical engineering of half-filled and half-cut widened mountainous highway subgrade with external balance weight retaining wall(BWRW),a sophisticated finite element numerical model is established.The evolution law of subgrade settlement is revealed during the whole process of new subgrade filling and BWRW inclination after construction.The settlement component of subgrade is clarified considering whether the existing pavement continues to be used.The results show that the additional settlement caused by the BWRW inclination after construction cannot be ignored in the widening and reconstruction of mountainous highway subgrade.In addition,pursuant to the comprehensive design of subgrade and pavement,the component of subgrade settlement should be determined according to whether the existing pavement continues to be used,while considering the influence of BWRW inclination after construction.When the existing pavement continues to be used,the settlement of the existing subgrade is caused by the new subgrade filling and the BWRW inclination after construction.On the contrary,the settlement is only caused by the BWRW inclination after construction.展开更多
Mountain roads,vital for linking remote areas and boosting regional development in China,suffer from poor conditions,complex environments,frequent accidents and severe consequences.Hence,establishing a predictive mode...Mountain roads,vital for linking remote areas and boosting regional development in China,suffer from poor conditions,complex environments,frequent accidents and severe consequences.Hence,establishing a predictive model for high-risk accident spots tailored to mountainous traffic conditions is crucial for formulating targeted preventive measures.Based on mountainous road accident cases in Guilin City,China from 2016 to 2020,this study employs spatial analysis methods to classify the data into high-risk and low-risk categories,determines key factors through Chi-square analysis and random forest Gini index and constructs an accident high-risk point prediction model using Bayesian networks.The results indicate that 19 variables,including gender,transportation mode and road location,are significantly correlated with accident risk status.Road type and traffic signal mode emerged as key factors directly influencing the overall risk profile,while other factors collectively affect accident risk status through indirect interactions.The highest risk scenario involves a male driver operating a passenger vehicle during the afternoon hours on a straight motorway in a hilly township area.The road is paved with asphalt and in good condition,equipped with basic safety measures such as signs and markings in the absence of signals.However,it suffers from insufficient traffic separation facilities,and there is a history of side-impact collisions causing injuries in this location.The predictive model developed in this study enables the forecasting of risk probabilities and the assessment of injury levels across different accident scenarios,providing a decision-making basis for formulating accident prevention policies for mountainous roads.展开更多
基金the financial support from the National Natural Science Foundation of China(No.U2005205,No.42007235,No.41972268)the Science and Technology Innovation Platform Project of Fuzhou Science and Technology Bureau(No.2021-P-032)。
文摘Landslide susceptibility mapping of mountain roads is frequently confronted by insufficient historical landslide sample data,multicollinearity of existing evaluation index factors,and inconsistency of evaluation factors due to regional environmental variations.Then,a single machine learning model can easily become overfitting,thus reducing the accuracy and robustness of the evaluation model.This paper proposes a combined machine-learning model to address the issues.The landslide susceptibility in mountain roads were mapped by using factor analysis to normalize and reduce the dimensionality of the initial condition factor and generating six new combination factors as evaluation indexes.The mountain roads in the Youxi County,Fujian Province,China were used for the landslide susceptibility mapping.Three most frequently used machine learning techniques,support vector machine(SVM),random forest(RF),and artificial neural network(ANN)models,were used to model the landslide susceptibility of the study area and validate the accuracy of this evaluation index system.The global minimum variance portfolio was utilized to construct a machine learning combined model.5-fold cross-validation,statistical indexes,and AUC(Area Under Curve)values were implemented to evaluate the predictive accuracy of the landslide susceptibility model.The mean AUC values for the SVM,RF,and ANN models in the training stage were 89.2%,88.5%,and 87.9%,respectively,and 78.0%,73.7%,and 76.7%,respectively,in the validating stage.In the training and validation stages,the mean AUC values of the combined model were 92.4% and 87.1%,respectively.The combined model provides greater prediction accuracy and model robustness than one single model.
基金financially supported by the National Key R&D Program of China(2024YFE0111900)The National Natural Science Foundation of China(U2468214,52378370,52278372)+1 种基金The National Ten Thousand Talent Program for Young Top-notch Talents(2022QB04978)The Science and Technology Program of Hebei Province(2023HBQZYCSB004)。
文摘Global climate change is intensifying the impact of slope hazards,particularly rainfall-induced landslide hazards(RILH),on mountain road networks(MRNs).However,effective quantitative models for dynamically assessing MRNs vulnerability under RILH disturbances are still lacking.To bridge this gap,this study develops a Cascading Failure Model for Rainfall-Induced Landslide Hazard(CFM-RILH).Validation via a case study of the GarzêTibetan Autonomous Prefecture Road Network(GTPRNs)reveals key characteristics of MRNs system vulnerability under RILH disturbances:(1)Under the disturbance effects of RILH,the vulnerability of the MRNs system follows a nonlinear phase transition law that intensifies with increasing disturbance intensity,exhibiting a distinct critical threshold.When the disturbance intensity exceeds this threshold,the system undergoes a global cascading failure phenomenon analogous to an“avalanche.”(2)Under RILH disturbances,the robustness of the MRNs system possesses a distinct safety boundary.Exceeding this boundary not only fails to improve hazard resistance but instead substantially elevates the risk of large-scale cascading failure.(3)Increasing network redundancy may be considered one of the primary engineering measures for enhancing MRNs resilience against such disturbances.Based on these findings,we propose a“Two-Stage Emergency Response and Hierarchical Fortification”strategy specifically to improve the resilience of GTPRNs impacted by RILH.The CFM-RILH model provides an effective tool for assessing road network vulnerability under such hazards.Furthermore,its modeling framework can also inform vulnerability assessment and resilience strategy development for road networks affected by other types of slope hazards.
文摘SONG Fangrong, the Tu nationality girl who grew up drinking water from mountain springs, walked into the Great Hall of the People in Beijing to accept the highest prize for China’s youth—the "May 4th Youth Prize." Not long before, she had been named one of the National Ten Outstanding Youths. She is the only individual to have won both.
基金the support received from the Prime Minister’s Research Fellowship(PMRF),Government of India(PMRF Grant number:PM-31-22-788-414).
文摘Despite the complexity and high crash risk associated with driving on mountainous roads,there is a lack of comprehensive understanding of factors influencing driving performance and increasing risk of crashes on mountainous roads.To address this gap,this study conducts a systematic review by employing the preferred reporting items for systematic reviews and meta-analysis(PRISMA)technique and selected 54 papers for review.The study provides insights into various data collection approaches,including crash history-based studies,naturalistic driving studies,and simulator-based studies,and the performance measures used to analyze driving performance on mountainous roads,including various longitudinal,and lateral measures as well as crash probability.Additionally,the study explores different contributing factors,including drivers,highways,vehicles,and light and weather characteristics,which significantly influence driving performance on mountainous roads.The study reveals a strong correlation between highway characteristics,such as roadway geometry,traffic conditions,road markings,etc.,and driving performance.Moreover,the findings highlight a significant impact of age,gender,and driving experience on driving performance.Most importantly,the study highlights significant gaps in literature,which may serve as guides for future research endeavors in safety assessment of mountainous roads.These gaps include absence of consideration of driver education,distraction,and prevalent highway features like sight distance and transition curve length.Furthermore,vehicle types including SUVs,and heavy vehicles have been overlooked in most studies to determine their impact on driving performance.Additionally,the study emphasized the importance of selecting and combining multiple performance measures for a more comprehensive analysis.
基金supported by Sichuan Science and Technology Program(No.2019YFS0492)Key Laboratories Open Engineering Practice Program to Undergraduates of SWJTU(No.ZD2020010010)。
文摘The settlement of widened highway subgrade in mountainous area is not only affected by the interaction between new and existing subgrade,but also seriously restricted by the external retaining wall.Based on the practical engineering of half-filled and half-cut widened mountainous highway subgrade with external balance weight retaining wall(BWRW),a sophisticated finite element numerical model is established.The evolution law of subgrade settlement is revealed during the whole process of new subgrade filling and BWRW inclination after construction.The settlement component of subgrade is clarified considering whether the existing pavement continues to be used.The results show that the additional settlement caused by the BWRW inclination after construction cannot be ignored in the widening and reconstruction of mountainous highway subgrade.In addition,pursuant to the comprehensive design of subgrade and pavement,the component of subgrade settlement should be determined according to whether the existing pavement continues to be used,while considering the influence of BWRW inclination after construction.When the existing pavement continues to be used,the settlement of the existing subgrade is caused by the new subgrade filling and the BWRW inclination after construction.On the contrary,the settlement is only caused by the BWRW inclination after construction.
基金supported by the Natural Science Foundation of Guangxi Zhuang Autonomous Region(Grant No.:2023GXNSFAA026359)the Scientific Research and Technology Development Plan Project of Guilin(Grant No.:20230120-7)+1 种基金Additional support was provided by the National Natural Science Foundation of China(Grant No.:52262047)the Key Research and Development Program of Guangxi(Grant Nos.:AB25069483 and AB25069333).
文摘Mountain roads,vital for linking remote areas and boosting regional development in China,suffer from poor conditions,complex environments,frequent accidents and severe consequences.Hence,establishing a predictive model for high-risk accident spots tailored to mountainous traffic conditions is crucial for formulating targeted preventive measures.Based on mountainous road accident cases in Guilin City,China from 2016 to 2020,this study employs spatial analysis methods to classify the data into high-risk and low-risk categories,determines key factors through Chi-square analysis and random forest Gini index and constructs an accident high-risk point prediction model using Bayesian networks.The results indicate that 19 variables,including gender,transportation mode and road location,are significantly correlated with accident risk status.Road type and traffic signal mode emerged as key factors directly influencing the overall risk profile,while other factors collectively affect accident risk status through indirect interactions.The highest risk scenario involves a male driver operating a passenger vehicle during the afternoon hours on a straight motorway in a hilly township area.The road is paved with asphalt and in good condition,equipped with basic safety measures such as signs and markings in the absence of signals.However,it suffers from insufficient traffic separation facilities,and there is a history of side-impact collisions causing injuries in this location.The predictive model developed in this study enables the forecasting of risk probabilities and the assessment of injury levels across different accident scenarios,providing a decision-making basis for formulating accident prevention policies for mountainous roads.
