Historically,landslides have been the primary type of geological disaster worldwide.Generally,the stability of reservoir banks is primarily affected by rainfall and reservoir water level fluctuations.Moreover,the stab...Historically,landslides have been the primary type of geological disaster worldwide.Generally,the stability of reservoir banks is primarily affected by rainfall and reservoir water level fluctuations.Moreover,the stability of reservoir banks changes with the long-term dynamics of external disastercausing factors.Thus,assessing the time-varying reliability of reservoir landslides remains a challenge.In this paper,a machine learning(ML)based approach is proposed to analyze the long-term reliability of reservoir bank landslides in spatially variable soils through time series prediction.This study systematically investigated the prediction performances of three ML algorithms,i.e.multilayer perceptron(MLP),convolutional neural network(CNN),and long short-term memory(LSTM).Additionally,the effects of the data quantity and data ratio on the predictive power of deep learning models are considered.The results show that all three ML models can accurately depict the changes in the time-varying failure probability of reservoir landslides.The CNN model outperforms both the MLP and LSTM models in predicting the failure probability.Furthermore,selecting the right data ratio can improve the prediction accuracy of the failure probability obtained by ML models.展开更多
Landslide susceptibility mapping is an integral part of geological hazard analysis.Recently,the emphasis of many studies has been on data-driven models,notably those derived from machine learning,owing to their aptitu...Landslide susceptibility mapping is an integral part of geological hazard analysis.Recently,the emphasis of many studies has been on data-driven models,notably those derived from machine learning,owing to their aptitude for tackling complex non-linear problems.However,the prevailing models often disregard qualitative research,leading to limited interpretability and mistakes in extracting negative samples,i.e.inaccurate non-landslide samples.In this study,Scoops 3D(a three-dimensional slope stability analysis tool)was utilized to conduct a qualitative assessment of slope stability in the Yunyang section of the Three Gorges Reservoir area.The depth of the bedrock was predicted utilizing a Convolutional Neural Network(CNN),incorporating local boreholes and building on the insights from prior research.The Random Forest(RF)algorithm was subsequently used to execute a data-driven landslide susceptibility analysis.The proposed methodology demonstrated a notable increase of 29.25%in the evaluation metric,the area under the receiver operating characteristic curve(ROC-AUC),outperforming the prevailing benchmark model.Furthermore,the landslide susceptibility map generated by the proposed model demonstrated superior interpretability.This result not only validates the effectiveness of amalgamating mathematical and mechanistic insights for such analyses,but it also carries substantial academic and practical implications.展开更多
With the construction of the Three Gorges Reservoir dam,frequent reservoir landslide events have been recorded.In recent years,multi-row stabilizing piles(MRSPs)have been used to stabilize massive reservoir landslides...With the construction of the Three Gorges Reservoir dam,frequent reservoir landslide events have been recorded.In recent years,multi-row stabilizing piles(MRSPs)have been used to stabilize massive reservoir landslides in China.In this study,two centrifuge model tests were carried out to study the unreinforced and MRSP-reinforced slopes subjected to reservoir water level(RWL)operation,using the Taping landslide as a prototype.The results indicate that the RWL rising can provide lateral support within the submerged zone and then produce the inward seepage force,eventually strengthening the slope stability.However,a rapid RWL drawdown may induce outward seepage forces and a sudden debuttressing effect,consequently reducing the effective soil normal stress and triggering partial pre-failure within the RWL fluctuation zone.Furthermore,partial deformation and subsequent soil structure damage generate excess pore water pressures,ultimately leading to the overall failure of the reservoir landslide.This study also reveals that a rapid increase in the downslope driving force due to RWL drawdown significantly intensifies the lateral earth pressures exerted on the MRSPs.Conversely,the MRSPs possess a considerable reinforcement effect on the reservoir landslide,transforming the overall failure into a partial deformation and failure situated above and in front of the MRSPs.The mechanical transfer behavior observed in the MRSPs demonstrates a progressive alteration in relation to RWL fluctuations.As the RWL rises,the mechanical states among MRSPs exhibit a growing imbalance.The shear force transfer factor(i.e.the ratio of shear forces on pile of the n th row to that of the first row)increases significantly with the RWL drawdown.This indicates that the mechanical states among MRSPs tend toward an enhanced equilibrium.The insights gained from this study contribute to a more comprehensive understanding of the failure mechanisms of reservoir landslides and the mechanical behavior of MRSPs in reservoir banks.展开更多
Landslide susceptibility mapping is a crucial tool for analyzing geohazards in a region.Recent publications have popularized data-driven models,particularly machine learning-based methods,owing to their strong capabil...Landslide susceptibility mapping is a crucial tool for analyzing geohazards in a region.Recent publications have popularized data-driven models,particularly machine learning-based methods,owing to their strong capability in dealing with complex nonlinear problems.However,a significant proportion of these models have neglected qualitative aspects during analysis,resulting in a lack of interpretability throughout the process and causing inaccuracies in the negative sample extraction.In this study,Scoops 3D was employed as a physics-informed tool to qualitatively assess slope stability in the study area(the Hubei Province section of the Three Gorges Reservoir Area).The non-landslide samples were extracted based on the calculated factor of safety(FS).Subsequently,the random forest algorithm was employed for data-driven landslide susceptibility analysis,with the area under the receiver operating characteristic curve(AUC)serving as the model evaluation index.Compared to the benchmark model(i.e.,the standard method of utilizing the pure random forest algorithm),the proposed method’s AUC value improved by 20.1%,validating the effectiveness of the dual-driven method(physics-informed data-driven).展开更多
The rational construction of electrocatalysts with desired features is significant but challenging for superior water splitting at high current density. Herein, amorphous Co Ni S nanosheets are synthesized on nickel f...The rational construction of electrocatalysts with desired features is significant but challenging for superior water splitting at high current density. Herein, amorphous Co Ni S nanosheets are synthesized on nickel foam(NF) through a facile structure evolution strategy and present advanced performance at high current densities in water splitting. The high catalytic activity can be attributed to the sufficient active sites exposed by the flexible amorphous configuration. Moreover, the hydrophilicity and aerophobicity of a-CoNiS/NF promote surface wettability of the self-supporting electrode and avoid the aggregation of bubbles, which expedites the diffusion of electrolyte and facilitates the mass transfer. As a result, the optimized electrode demonstrates low overpotentials of 289 and 434 m V at 500 m A/cm^(2) under alkaline conditions for hydrogen evolution reaction(HER) and oxygen evolution reaction(OER), respectively. Impressively, an electrolytic water splitting cell assembled by bifunctional a-Co Ni S/NF operates with a low cell voltage of 1.46 V@10 mA/cm^(2) and reaches 1.79 V at 500 mA/cm^(2). The strategy sheds light on a competitive platform for the reasonable design of non-precious-metal electrocatalysts under high current density.展开更多
It’s often the case that the supplier will provide the retailer with a permissible delay period in payments, during which the supplier charges the retailer no interest and the retailer accumulates interest earned fro...It’s often the case that the supplier will provide the retailer with a permissible delay period in payments, during which the supplier charges the retailer no interest and the retailer accumulates interest earned from investment return. As a type of price reduction and an alternative to price discount,trade credit helps the supplier encourage the retailer’s ordering. This paper develops an inventory replenishment model for a deteriorating item with time-varying demand and shortages, taking account of trade credit and time value of money under inflation over a finite time horizon. This model is an extension and development of the existing studies related to the inventory system considering trade credit and time value of money and offers a more general model with more flexibility and resilience to handle the situation where demand of the end market is non-decreasing with regard to time.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.52308340)the Innovative Projects of Universities in Guangdong(Grant No.2022KTSCX208)Sichuan Transportation Science and Technology Project(Grant No.2018-ZL-01).
文摘Historically,landslides have been the primary type of geological disaster worldwide.Generally,the stability of reservoir banks is primarily affected by rainfall and reservoir water level fluctuations.Moreover,the stability of reservoir banks changes with the long-term dynamics of external disastercausing factors.Thus,assessing the time-varying reliability of reservoir landslides remains a challenge.In this paper,a machine learning(ML)based approach is proposed to analyze the long-term reliability of reservoir bank landslides in spatially variable soils through time series prediction.This study systematically investigated the prediction performances of three ML algorithms,i.e.multilayer perceptron(MLP),convolutional neural network(CNN),and long short-term memory(LSTM).Additionally,the effects of the data quantity and data ratio on the predictive power of deep learning models are considered.The results show that all three ML models can accurately depict the changes in the time-varying failure probability of reservoir landslides.The CNN model outperforms both the MLP and LSTM models in predicting the failure probability.Furthermore,selecting the right data ratio can improve the prediction accuracy of the failure probability obtained by ML models.
基金funded by the Sichuan Transportation Science and Technology Project(Grant No.2018-ZL-01)High-end Foreign Expert Introduction program(Grant No.G2022165004L)Science and Technology Research Program of Chongqing Municipal Education Commission(Grant No.HZ2021001).
文摘Landslide susceptibility mapping is an integral part of geological hazard analysis.Recently,the emphasis of many studies has been on data-driven models,notably those derived from machine learning,owing to their aptitude for tackling complex non-linear problems.However,the prevailing models often disregard qualitative research,leading to limited interpretability and mistakes in extracting negative samples,i.e.inaccurate non-landslide samples.In this study,Scoops 3D(a three-dimensional slope stability analysis tool)was utilized to conduct a qualitative assessment of slope stability in the Yunyang section of the Three Gorges Reservoir area.The depth of the bedrock was predicted utilizing a Convolutional Neural Network(CNN),incorporating local boreholes and building on the insights from prior research.The Random Forest(RF)algorithm was subsequently used to execute a data-driven landslide susceptibility analysis.The proposed methodology demonstrated a notable increase of 29.25%in the evaluation metric,the area under the receiver operating characteristic curve(ROC-AUC),outperforming the prevailing benchmark model.Furthermore,the landslide susceptibility map generated by the proposed model demonstrated superior interpretability.This result not only validates the effectiveness of amalgamating mathematical and mechanistic insights for such analyses,but it also carries substantial academic and practical implications.
基金funded by Chongqing Natural Science Key Program of China(Grant No.cstc2020jcyj-zdxmX0019)China Geological Survey Program(Grant No.DD20190637/DD20221748).
文摘With the construction of the Three Gorges Reservoir dam,frequent reservoir landslide events have been recorded.In recent years,multi-row stabilizing piles(MRSPs)have been used to stabilize massive reservoir landslides in China.In this study,two centrifuge model tests were carried out to study the unreinforced and MRSP-reinforced slopes subjected to reservoir water level(RWL)operation,using the Taping landslide as a prototype.The results indicate that the RWL rising can provide lateral support within the submerged zone and then produce the inward seepage force,eventually strengthening the slope stability.However,a rapid RWL drawdown may induce outward seepage forces and a sudden debuttressing effect,consequently reducing the effective soil normal stress and triggering partial pre-failure within the RWL fluctuation zone.Furthermore,partial deformation and subsequent soil structure damage generate excess pore water pressures,ultimately leading to the overall failure of the reservoir landslide.This study also reveals that a rapid increase in the downslope driving force due to RWL drawdown significantly intensifies the lateral earth pressures exerted on the MRSPs.Conversely,the MRSPs possess a considerable reinforcement effect on the reservoir landslide,transforming the overall failure into a partial deformation and failure situated above and in front of the MRSPs.The mechanical transfer behavior observed in the MRSPs demonstrates a progressive alteration in relation to RWL fluctuations.As the RWL rises,the mechanical states among MRSPs exhibit a growing imbalance.The shear force transfer factor(i.e.the ratio of shear forces on pile of the n th row to that of the first row)increases significantly with the RWL drawdown.This indicates that the mechanical states among MRSPs tend toward an enhanced equilibrium.The insights gained from this study contribute to a more comprehensive understanding of the failure mechanisms of reservoir landslides and the mechanical behavior of MRSPs in reservoir banks.
基金funded by the National Key R&D Program of China(Project No.2019YFC1509605)High-end Foreign Expert Introduction program(No.G20200022005 and DL2021165001L)Science and Technology Research Program of Chongqing Municipal Education Commission(Grant No.HZ2021001)。
文摘Landslide susceptibility mapping is a crucial tool for analyzing geohazards in a region.Recent publications have popularized data-driven models,particularly machine learning-based methods,owing to their strong capability in dealing with complex nonlinear problems.However,a significant proportion of these models have neglected qualitative aspects during analysis,resulting in a lack of interpretability throughout the process and causing inaccuracies in the negative sample extraction.In this study,Scoops 3D was employed as a physics-informed tool to qualitatively assess slope stability in the study area(the Hubei Province section of the Three Gorges Reservoir Area).The non-landslide samples were extracted based on the calculated factor of safety(FS).Subsequently,the random forest algorithm was employed for data-driven landslide susceptibility analysis,with the area under the receiver operating characteristic curve(AUC)serving as the model evaluation index.Compared to the benchmark model(i.e.,the standard method of utilizing the pure random forest algorithm),the proposed method’s AUC value improved by 20.1%,validating the effectiveness of the dual-driven method(physics-informed data-driven).
基金supported by the National Natural Science Foundation of China (Nos. 51871119, 22101132, and 22075141)Scientific and Technological Innovation Special Fund for Carbon Peak and Carbon Neutrality of Jiangsu Province (No. BK20220039)+4 种基金Jiangsu Provincial Founds for Natural Science Foundation (No. BK20210311)China Postdoctoral Science Foundation (Nos. 2018M640481 and 2019T120426)the Natural Science Foundation of Jiangsu Province (No. BK20210311)Jiangsu Postdoctoral Research Fund (No. 2019K003)the Postgraduate Research & Practice Innovation Program of NUAA (No. xcxjh20210607)。
文摘The rational construction of electrocatalysts with desired features is significant but challenging for superior water splitting at high current density. Herein, amorphous Co Ni S nanosheets are synthesized on nickel foam(NF) through a facile structure evolution strategy and present advanced performance at high current densities in water splitting. The high catalytic activity can be attributed to the sufficient active sites exposed by the flexible amorphous configuration. Moreover, the hydrophilicity and aerophobicity of a-CoNiS/NF promote surface wettability of the self-supporting electrode and avoid the aggregation of bubbles, which expedites the diffusion of electrolyte and facilitates the mass transfer. As a result, the optimized electrode demonstrates low overpotentials of 289 and 434 m V at 500 m A/cm^(2) under alkaline conditions for hydrogen evolution reaction(HER) and oxygen evolution reaction(OER), respectively. Impressively, an electrolytic water splitting cell assembled by bifunctional a-Co Ni S/NF operates with a low cell voltage of 1.46 V@10 mA/cm^(2) and reaches 1.79 V at 500 mA/cm^(2). The strategy sheds light on a competitive platform for the reasonable design of non-precious-metal electrocatalysts under high current density.
文摘It’s often the case that the supplier will provide the retailer with a permissible delay period in payments, during which the supplier charges the retailer no interest and the retailer accumulates interest earned from investment return. As a type of price reduction and an alternative to price discount,trade credit helps the supplier encourage the retailer’s ordering. This paper develops an inventory replenishment model for a deteriorating item with time-varying demand and shortages, taking account of trade credit and time value of money under inflation over a finite time horizon. This model is an extension and development of the existing studies related to the inventory system considering trade credit and time value of money and offers a more general model with more flexibility and resilience to handle the situation where demand of the end market is non-decreasing with regard to time.
