Hydro-morphological processes(HMP,any natural phenomenon contained within the spectrum defined between debris flows and flash floods)are globally occurring natural hazards which pose great threats to our society,leadi...Hydro-morphological processes(HMP,any natural phenomenon contained within the spectrum defined between debris flows and flash floods)are globally occurring natural hazards which pose great threats to our society,leading to fatalities and economical losses.For this reason,understanding the dynamics behind HMPs is needed to aid in hazard and risk assessment.In this work,we take advantage of an explainable deep learning model to extract global and local interpretations of the HMP occurrences across the whole Chinese territory.We use a deep neural network architecture and interpret the model results through the spatial pattern of SHAP values.In doing so,we can understand the model prediction on a hierarchical basis,looking at how the predictor set controls the overall susceptibility as well as doing the same at the level of the single mapping unit.Our model accurately predicts HMP occurrences with AUC values measured in a ten-fold cross-validation ranging between 0.83 and 0.86.This level of predictive performance attests for an excellent prediction skill.The main difference with respect to traditional statistical tools is that the latter usually lead to a clear interpretation at the expense of high performance,which is otherwise reached via machine/deep learning solutions,though at the expense of interpretation.The recent development of explainable Al is the key to combine both strengths.In this work,we explore this combination in the context of HMP susceptibility modeling.Specifically,we demonstrate the extent to which one can enter a new level of data-driven interpretation,supporting the decision-making process behind disaster risk mitigation and prevention actions.展开更多
From 2009 until 2012 the project“Watershed Management of Forest Land in Beijing,Restoration of Small Water Bodies(SWBR)”was implemented,combining Close to Nature Forest Management and Restoration of Small Water Bodi...From 2009 until 2012 the project“Watershed Management of Forest Land in Beijing,Restoration of Small Water Bodies(SWBR)”was implemented,combining Close to Nature Forest Management and Restoration of Small Water Bodies.The targets were to improve flood control,to enhance the ecological conditions by copying nature and to support the recreational value of small water bodies,all in cooperation with people living there.The efficiency of each project was proofed by comparison of biological and hydro-morphological assessment before the projects started and 2-3 years after they were finished.The results confirmed the ecological improvements of the restored river sections and showed the achievements.Guidelines to assess the biological and hydro-morphological status of rivers were developed and there are plans to introduce them as Beijing Standards.Planning and implementation of measures,based on experiences in Central Europe,will be documented in a handbook.&2015 International Research and Training Center on Erosion and Sedimentation and China Water and Power Press.Production and Hosting by Elsevier B.V.This is an open access article under the CC BY-NC-ND license(http://creativecommons.org/licenses/by-nc-nd/4.0/).展开更多
基金supported by the National Natural Science Foundation of China(grant no.42201452)the Fundamental Research Funds for the Central Universities(grant no.2412022QD003)the support from the China Institute of Water Resources and Hydropower Research(IWHR).
文摘Hydro-morphological processes(HMP,any natural phenomenon contained within the spectrum defined between debris flows and flash floods)are globally occurring natural hazards which pose great threats to our society,leading to fatalities and economical losses.For this reason,understanding the dynamics behind HMPs is needed to aid in hazard and risk assessment.In this work,we take advantage of an explainable deep learning model to extract global and local interpretations of the HMP occurrences across the whole Chinese territory.We use a deep neural network architecture and interpret the model results through the spatial pattern of SHAP values.In doing so,we can understand the model prediction on a hierarchical basis,looking at how the predictor set controls the overall susceptibility as well as doing the same at the level of the single mapping unit.Our model accurately predicts HMP occurrences with AUC values measured in a ten-fold cross-validation ranging between 0.83 and 0.86.This level of predictive performance attests for an excellent prediction skill.The main difference with respect to traditional statistical tools is that the latter usually lead to a clear interpretation at the expense of high performance,which is otherwise reached via machine/deep learning solutions,though at the expense of interpretation.The recent development of explainable Al is the key to combine both strengths.In this work,we explore this combination in the context of HMP susceptibility modeling.Specifically,we demonstrate the extent to which one can enter a new level of data-driven interpretation,supporting the decision-making process behind disaster risk mitigation and prevention actions.
文摘From 2009 until 2012 the project“Watershed Management of Forest Land in Beijing,Restoration of Small Water Bodies(SWBR)”was implemented,combining Close to Nature Forest Management and Restoration of Small Water Bodies.The targets were to improve flood control,to enhance the ecological conditions by copying nature and to support the recreational value of small water bodies,all in cooperation with people living there.The efficiency of each project was proofed by comparison of biological and hydro-morphological assessment before the projects started and 2-3 years after they were finished.The results confirmed the ecological improvements of the restored river sections and showed the achievements.Guidelines to assess the biological and hydro-morphological status of rivers were developed and there are plans to introduce them as Beijing Standards.Planning and implementation of measures,based on experiences in Central Europe,will be documented in a handbook.&2015 International Research and Training Center on Erosion and Sedimentation and China Water and Power Press.Production and Hosting by Elsevier B.V.This is an open access article under the CC BY-NC-ND license(http://creativecommons.org/licenses/by-nc-nd/4.0/).
