Landslides occurring in sensitive clay often result in widespread destruction,posing a significant risk to human lives and property due to the substantial decrease in undrained shear strength during deformation.Assess...Landslides occurring in sensitive clay often result in widespread destruction,posing a significant risk to human lives and property due to the substantial decrease in undrained shear strength during deformation.Assessing the consequences of these landslides is challenging and necessitates robust numerical methods to comprehensively investigate their failure mechanisms.While studies have extensively explored upward progressive landslides in sensitive clays,understanding downward progressive cases remains limited.In this study,we utilised the nodal integration-based particle finite element method(NPFEM)with a nonlinear strain-softening model to analyse downward progressive landslides in sensitive clay on elongated slopes,induced by surcharge loads near the crest.We focused on elucidating the underlying failure mechanisms and evaluating the effects of different soil parameters and strainsoftening characteristics.The simulation results revealed the typical pattern for downward landslides,which typically start with a localised failure in proximity to the surcharge loads,followed by a combination of different types of failure mechanisms,including single flow slides,translational progressive landslides,progressive flow slides,and spread failures.Additionally,inclined shear bands occur within spread failures,often adopting distinctive ploughing patterns characterised by triangular shapes.The sensitive clay thickness at the base,the clay strength gradient,the sensitivity,and the softening rate significantly influence the failure mechanisms and the extent of diffused displacement.Remarkably,some of these effects mirror those observed in upward progressive landslides,underscoring the interconnectedness of these phenomena.This study contributes valuable insights into the complex dynamics of sensitive clay landslides,shedding light on the intricate interplay of factors governing their behaviour and progression.展开更多
Deep-sea pipelines play a pivotal role in seabed mineral resource development,global energy and resource supply provision,network communication,and environmental protection.However,the placement of these pipelines on ...Deep-sea pipelines play a pivotal role in seabed mineral resource development,global energy and resource supply provision,network communication,and environmental protection.However,the placement of these pipelines on the seabed surface exposes them to potential risks arising from the complex deep-sea hydrodynamic and geological environment,particularly submarine slides.Historical incidents have highlighted the substantial damage to pipelines due to slides.Specifically,deep-sea fluidized slides(in a debris/mud flow or turbidity current physical state),characterized by high speed,pose a significant threat.Accurately assessing the impact forces exerted on pipelines by fluidized submarine slides is crucial for ensuring pipeline safety.This study aimed to provide a comprehensive overview of recent advancements in understanding pipeline impact forces caused by fluidized deep-sea slides,thereby identifying key factors and corresponding mechanisms that influence pipeline impact forces.These factors include the velocity,density,and shear behavior of deep-sea fluidized slides,as well as the geometry,stiffness,self-weight,and mechanical model of pipelines.Additionally,the interface contact conditions and spatial relations were examined within the context of deep-sea slides and their interactions with pipelines.Building upon a thorough review of these achievements,future directions were proposed for assessing and characterizing the key factors affecting slide impact loading on pipelines.A comprehensive understanding of these results is essential for the sustainable development of deep-sea pipeline projects associated with seabed resource development and the implementation of disaster prevention measures.展开更多
In the intelligent medical diagnosis area,Artificial Intelligence(AI)’s trustworthiness,reliability,and interpretability are critical,especially in cancer diagnosis.Traditional neural networks,while excellent at proc...In the intelligent medical diagnosis area,Artificial Intelligence(AI)’s trustworthiness,reliability,and interpretability are critical,especially in cancer diagnosis.Traditional neural networks,while excellent at processing natural images,often lack interpretability and adaptability when processing high-resolution digital pathological images.This limitation is particularly evident in pathological diagnosis,which is the gold standard of cancer diagnosis and relies on a pathologist’s careful examination and analysis of digital pathological slides to identify the features and progression of the disease.Therefore,the integration of interpretable AI into smart medical diagnosis is not only an inevitable technological trend but also a key to improving diagnostic accuracy and reliability.In this paper,we introduce an innovative Multi-Scale Multi-Branch Feature Encoder(MSBE)and present the design of the CrossLinkNet Framework.The MSBE enhances the network’s capability for feature extraction by allowing the adjustment of hyperparameters to configure the number of branches and modules.The CrossLinkNet Framework,serving as a versatile image segmentation network architecture,employs cross-layer encoder-decoder connections for multi-level feature fusion,thereby enhancing feature integration and segmentation accuracy.Comprehensive quantitative and qualitative experiments on two datasets demonstrate that CrossLinkNet,equipped with the MSBE encoder,not only achieves accurate segmentation results but is also adaptable to various tumor segmentation tasks and scenarios by replacing different feature encoders.Crucially,CrossLinkNet emphasizes the interpretability of the AI model,a crucial aspect for medical professionals,providing an in-depth understanding of the model’s decisions and thereby enhancing trust and reliability in AI-assisted diagnostics.展开更多
基金support provided by the UK Engineering and Physical Sciences Research Council(EP/V012169/1).
文摘Landslides occurring in sensitive clay often result in widespread destruction,posing a significant risk to human lives and property due to the substantial decrease in undrained shear strength during deformation.Assessing the consequences of these landslides is challenging and necessitates robust numerical methods to comprehensively investigate their failure mechanisms.While studies have extensively explored upward progressive landslides in sensitive clays,understanding downward progressive cases remains limited.In this study,we utilised the nodal integration-based particle finite element method(NPFEM)with a nonlinear strain-softening model to analyse downward progressive landslides in sensitive clay on elongated slopes,induced by surcharge loads near the crest.We focused on elucidating the underlying failure mechanisms and evaluating the effects of different soil parameters and strainsoftening characteristics.The simulation results revealed the typical pattern for downward landslides,which typically start with a localised failure in proximity to the surcharge loads,followed by a combination of different types of failure mechanisms,including single flow slides,translational progressive landslides,progressive flow slides,and spread failures.Additionally,inclined shear bands occur within spread failures,often adopting distinctive ploughing patterns characterised by triangular shapes.The sensitive clay thickness at the base,the clay strength gradient,the sensitivity,and the softening rate significantly influence the failure mechanisms and the extent of diffused displacement.Remarkably,some of these effects mirror those observed in upward progressive landslides,underscoring the interconnectedness of these phenomena.This study contributes valuable insights into the complex dynamics of sensitive clay landslides,shedding light on the intricate interplay of factors governing their behaviour and progression.
基金supported by the opening fund of State Key Laboratory of Coastal and Offshore Engineering at Dalian University of Technology(No.LP2310)the opening fund of State Key Laboratory of Geohazard Prevention and Geoenvironment Protection at Chengdu University of Technology(No.SKLGP2023K001)+2 种基金the Shandong Provincial Key Laboratory of Ocean Engineering with grant at Ocean University of China(No.kloe200301)the National Natural Science Foundation of China(Nos.42022052,42077272 and 52108337)the Science and Technology Innovation Serve Project of Wenzhou Association for Science and Technology(No.KJFW65).
文摘Deep-sea pipelines play a pivotal role in seabed mineral resource development,global energy and resource supply provision,network communication,and environmental protection.However,the placement of these pipelines on the seabed surface exposes them to potential risks arising from the complex deep-sea hydrodynamic and geological environment,particularly submarine slides.Historical incidents have highlighted the substantial damage to pipelines due to slides.Specifically,deep-sea fluidized slides(in a debris/mud flow or turbidity current physical state),characterized by high speed,pose a significant threat.Accurately assessing the impact forces exerted on pipelines by fluidized submarine slides is crucial for ensuring pipeline safety.This study aimed to provide a comprehensive overview of recent advancements in understanding pipeline impact forces caused by fluidized deep-sea slides,thereby identifying key factors and corresponding mechanisms that influence pipeline impact forces.These factors include the velocity,density,and shear behavior of deep-sea fluidized slides,as well as the geometry,stiffness,self-weight,and mechanical model of pipelines.Additionally,the interface contact conditions and spatial relations were examined within the context of deep-sea slides and their interactions with pipelines.Building upon a thorough review of these achievements,future directions were proposed for assessing and characterizing the key factors affecting slide impact loading on pipelines.A comprehensive understanding of these results is essential for the sustainable development of deep-sea pipeline projects associated with seabed resource development and the implementation of disaster prevention measures.
基金supported by the National Natural Science Foundation of China(Grant Numbers:62372083,62072074,62076054,62027827,62002047)the Sichuan Provincial Science and Technology Innovation Platform and Talent Program(Grant Number:2022JDJQ0039)+1 种基金the Sichuan Provincial Science and Technology Support Program(Grant Numbers:2022YFQ0045,2022YFS0220,2021YFG0131,2023YFS0020,2023YFS0197,2023YFG0148)the CCF-Baidu Open Fund(Grant Number:202312).
文摘In the intelligent medical diagnosis area,Artificial Intelligence(AI)’s trustworthiness,reliability,and interpretability are critical,especially in cancer diagnosis.Traditional neural networks,while excellent at processing natural images,often lack interpretability and adaptability when processing high-resolution digital pathological images.This limitation is particularly evident in pathological diagnosis,which is the gold standard of cancer diagnosis and relies on a pathologist’s careful examination and analysis of digital pathological slides to identify the features and progression of the disease.Therefore,the integration of interpretable AI into smart medical diagnosis is not only an inevitable technological trend but also a key to improving diagnostic accuracy and reliability.In this paper,we introduce an innovative Multi-Scale Multi-Branch Feature Encoder(MSBE)and present the design of the CrossLinkNet Framework.The MSBE enhances the network’s capability for feature extraction by allowing the adjustment of hyperparameters to configure the number of branches and modules.The CrossLinkNet Framework,serving as a versatile image segmentation network architecture,employs cross-layer encoder-decoder connections for multi-level feature fusion,thereby enhancing feature integration and segmentation accuracy.Comprehensive quantitative and qualitative experiments on two datasets demonstrate that CrossLinkNet,equipped with the MSBE encoder,not only achieves accurate segmentation results but is also adaptable to various tumor segmentation tasks and scenarios by replacing different feature encoders.Crucially,CrossLinkNet emphasizes the interpretability of the AI model,a crucial aspect for medical professionals,providing an in-depth understanding of the model’s decisions and thereby enhancing trust and reliability in AI-assisted diagnostics.
