Flood disasters pose serious threats to human life and property worldwide.Exploring the spatial drivers of flood disasters on a macroscopic scale is of great significance for mitigating their impacts.This study propos...Flood disasters pose serious threats to human life and property worldwide.Exploring the spatial drivers of flood disasters on a macroscopic scale is of great significance for mitigating their impacts.This study proposes a comprehensive framework for integrating driving-factor optimization and interpretability,while considering spatial heterogeneity.In this framework,the Optimal Parameter-based Geographic Detector(OPGD),Recursive Feature Estimation(RFE),and Light Gradient Boosting Machine(LGBM)models were utilized to construct the OPGD–RFE–LGBM coupled model to identify the essential driving factors and simulate the spatial distribution of flood disasters.The SHapley Additive ExPlanation(SHAP)interpreter was employed to quantitatively explain the driving mechanisms behind the spatial distribution of flood disasters.Yunnan Province,a typical mountainous and plateau area in Southwest China,was selected to implement the proposed framework and conduct a case study.For this purpose,a flood disaster inventory of 7332 historical events was prepared,and 22 potential driving factors related to precipitation,surface environment,and human activity were initially selected.Results revealed that flood disasters in Yunnan Province exhibit high spatial heterogeneity,with geomorphic zoning accounting for 66.1%of the spatial variation in historical flood disasters.The OPGD–RFE–LGBM coupled model offers clear advantages over a single LGBM in identifying essential driving factors and quantitatively analyzing their impacts.Moreover,the simulation performance shows a slight improvement(a 6%average decrease in RMSE and an average increase of 1%in R2)even with reduced factor data.Factor explanatory analysis indicated that the combination of the essential driving factor sets varied across different subregions;nevertheless,precipitation-related factors,such as precipitation intensity index(SDII),wet days(R10MM),and 5-day maximum precipitation(RX5day),were the main driving factors controlling flood disasters.This study provides a quantitative analytical framework for the spatial drivers of flood disasters at large scales with significant heterogeneity,offering a reference for disaster management authorities in developing macro-strategies for disaster prevention.展开更多
The present study aims to develop two hybrid models to optimize the factors and enhance the predictive ability of the landslide susceptibility models.For this,a landslide inventory map was created with 406 historical ...The present study aims to develop two hybrid models to optimize the factors and enhance the predictive ability of the landslide susceptibility models.For this,a landslide inventory map was created with 406 historical landslides and 2030 non-landslide points,which was randomly divided into two datasets for model training(70%)and model testing(30%).22 factors were initially selected to establish a landslide factor database.We applied the GeoDetector and recursive feature elimination method(RFE)to address factor optimization to reduce information redundancy and collinearity in the data.Thereafter,the frequency ratio method,multicollinearity test,and interactive detector were used to analyze and evaluate the optimized factors.Subsequently,the random forest(RF)model was used to create a landslide susceptibility map with original and optimized factors.The resultant hybrid models GeoDetector-RF and RFE-RF were evaluated and compared by the area under the receiver operating characteristic curve(AUC)and accuracy.The accuracy of the two hybrid models(0.868 for GeoDetector-RF and 0.869 for RFE-RF)were higher than that of the RF model(0.860),indicating that the hybrid models with factor optimization have high reliability and predictability.Both RFE-RF GeoDetector-RF had higher AUC values,respectively 0.863 and 0.860,than RF(0.853).These results confirm the ability of factor optimization methods to improve the performance of landslide susceptibility models.展开更多
[目的]揭示黄土高原农牧交错带草地净初级生产力(NPP)时空演变规律,明确自然因素与人类活动作用及其交互驱动机制,为该区域或类似草地生态系统的科学管理与可持续利用提供理论依据。[方法]应用CASA模型模拟1990—2020年草地NPP,结合趋...[目的]揭示黄土高原农牧交错带草地净初级生产力(NPP)时空演变规律,明确自然因素与人类活动作用及其交互驱动机制,为该区域或类似草地生态系统的科学管理与可持续利用提供理论依据。[方法]应用CASA模型模拟1990—2020年草地NPP,结合趋势分析及最优参数地理探测器识别草地NPP时空变化特征的驱动因素。[结果](1) 1990—2020年黄土高原农牧交错带草地NPP整体呈增加趋势,年平均增长率4.93 g C/(m^(2)·a)。NPP的阶段性特征比较明显,1990—1999年草地NPP呈不显著下降趋势;2000年后,草地NPP开始增加,2011—2020年这一阶段增加显著。(2) 1990—2020年草地NPP呈显著增加的面积达82.15%;减少的地区仅占3.14%,零星分布于内蒙古自治区。(3)草地NPP呈东南高、西北低的分异格局,降水和坡度是主要驱动因素,并且总体呈正向作用;人类活动的影响在因子间非线性交互作用下显著增强,其中放牧、耕地及建设用地扩张整体呈负向效应。但随着人均GDP的增加,生态保护与技术投入降低了人类活动的负面影响。[结论]黄土高原农牧交错带草地整体恢复较好,未来草地管理中考虑自然作用的影响与差异化的适度放牧政策,增加农牧民收入,同时平衡草地生态系统的直接受益者(草地生产力使用)和间接受益者(草地调节服务)之间的权衡。展开更多
土壤风蚀是评估干旱半干旱区生态环境的关键。针对现有研究在干旱区大区域尺度上的不足,利用GIS技术和修正风蚀方程模型模拟了中国干旱半干旱区1990—2020年五个时期的土壤风蚀时空特征,利用最优参数地理探测器研究了其驱动因素,结果表...土壤风蚀是评估干旱半干旱区生态环境的关键。针对现有研究在干旱区大区域尺度上的不足,利用GIS技术和修正风蚀方程模型模拟了中国干旱半干旱区1990—2020年五个时期的土壤风蚀时空特征,利用最优参数地理探测器研究了其驱动因素,结果表明:(1)中国干旱半干旱区年均风蚀量达31.66亿t,土壤风蚀量平均值为0.566 kg m^(-2)a^(-1),风蚀高值区集中于华北平原、内蒙古高原、准噶尔盆地、柴达木盆地及青藏高原大部。风蚀强度以微度和轻度为主,剧烈侵蚀仅占0.37%。(2)土壤风蚀量总体呈现波动下降趋势,下降速率为0.027 kg m^(-2)a^(-1),且大部分区域风蚀减轻。(3)不同土地利用类型年均单位面积风蚀量排序:裸地>建设用地>农田>沙地>草地>灌丛>林地。(4)识别出风速、降水、大风日数、植被覆盖度和坡度为主导驱动因子,其中风速与大风日数的交互作用对风蚀解释力最强。研究为干旱半干旱区风蚀防治与生态修复提供科学依据,服务于区域可持续发展和环境治理政策。展开更多
Understanding the influencing factors of ecosystem services(ESs)and their relationships is essential for sustainable ecosystem management in degraded alpine ecosystems.There is a lack of integrated multi-model approac...Understanding the influencing factors of ecosystem services(ESs)and their relationships is essential for sustainable ecosystem management in degraded alpine ecosystems.There is a lack of integrated multi-model approaches to explore the multidimensional influences on ESs and their relationships in alpine ecosystems.Taking the Daxing'anling forest area,Inner Mongolia(DFAIM)as a case study,this study used the integrated valuation of ecosystem services and trade-offs(InVEST)model to quantify four ESs—soil conservation(SC),water yield(WY),carbon storage(CS),and habitat quality(HQ)—from 2013 to 2018.We adopted root mean square deviation(RMSD)and coupling coordination degree models(CCDM)to analyze their relationships,and integrated three complementary approaches—optimal parameter-based geographical detector model(OPGDM),gradient boosting regression tree model(GBRTM),and quantile regression model(QRM)—to reveal multidimensional influencing factors.Key findings include the following:(1)From 2013 to 2018,WY,SC,and HQ declined while CS increased.WY was primarily influenced by mean annual precipitation(MAP),forest ratio(RF),and soil bulk density(SBD);CS and HQ by RF and population density(PD);and SC by slope(S),RF,and MAP.Mean annual temperature(MAT),gross domestic product(GDP),and road network density(RND)showed increasing negative impacts.(2)Low trade-off intensity(TI<0.15)dominated all ES pairs,with RF,MAP,PD,and normalized difference vegetation index(NDVI)being the dominant factors.The factor interactions primarily showed two-factor enhancement patterns.(3)The average coupling coordination degree(CCD)of the four ESs was low and declined over time,with low-CCD areas becoming increasingly prevalent.RF,S,SBD,and NDVI positively influenced CCD,while PD,MAT,GDP,and RND had increasing negative impacts,with over 62%of the factor interactions exceeding the individual factor effects.In summary,ES supply generally decreased.Local relationships showed moderate coordination,while overall relationships indicated primary dysfunction.Land use and natural factors primarily shaped these ES and their relationships,while climate and socioeconomic changes diminished ES supply and intensified competition.We recommend enhancing the resilience of natural systems rather than replacing them,establishing climate adaptation monitoring systems,and promoting conservation tillage and cross-departmental coordination mechanisms for collaborative ES optimization.These results provide valuable insights into the sustainable management of alpine ecosystems.展开更多
基金the National Key Research and Development Program of China(Grant No.2022YFF1302405)the Yunnan Province Key Research and Development Program(Grant No.202203AC100005)+1 种基金the National Natural Science Foundation of China(Grant No.42061005,42067033)Applied Basic Research Programs of Yunnan Province(Grant No.202101AT070110,202001BB050073).
文摘Flood disasters pose serious threats to human life and property worldwide.Exploring the spatial drivers of flood disasters on a macroscopic scale is of great significance for mitigating their impacts.This study proposes a comprehensive framework for integrating driving-factor optimization and interpretability,while considering spatial heterogeneity.In this framework,the Optimal Parameter-based Geographic Detector(OPGD),Recursive Feature Estimation(RFE),and Light Gradient Boosting Machine(LGBM)models were utilized to construct the OPGD–RFE–LGBM coupled model to identify the essential driving factors and simulate the spatial distribution of flood disasters.The SHapley Additive ExPlanation(SHAP)interpreter was employed to quantitatively explain the driving mechanisms behind the spatial distribution of flood disasters.Yunnan Province,a typical mountainous and plateau area in Southwest China,was selected to implement the proposed framework and conduct a case study.For this purpose,a flood disaster inventory of 7332 historical events was prepared,and 22 potential driving factors related to precipitation,surface environment,and human activity were initially selected.Results revealed that flood disasters in Yunnan Province exhibit high spatial heterogeneity,with geomorphic zoning accounting for 66.1%of the spatial variation in historical flood disasters.The OPGD–RFE–LGBM coupled model offers clear advantages over a single LGBM in identifying essential driving factors and quantitatively analyzing their impacts.Moreover,the simulation performance shows a slight improvement(a 6%average decrease in RMSE and an average increase of 1%in R2)even with reduced factor data.Factor explanatory analysis indicated that the combination of the essential driving factor sets varied across different subregions;nevertheless,precipitation-related factors,such as precipitation intensity index(SDII),wet days(R10MM),and 5-day maximum precipitation(RX5day),were the main driving factors controlling flood disasters.This study provides a quantitative analytical framework for the spatial drivers of flood disasters at large scales with significant heterogeneity,offering a reference for disaster management authorities in developing macro-strategies for disaster prevention.
文摘The present study aims to develop two hybrid models to optimize the factors and enhance the predictive ability of the landslide susceptibility models.For this,a landslide inventory map was created with 406 historical landslides and 2030 non-landslide points,which was randomly divided into two datasets for model training(70%)and model testing(30%).22 factors were initially selected to establish a landslide factor database.We applied the GeoDetector and recursive feature elimination method(RFE)to address factor optimization to reduce information redundancy and collinearity in the data.Thereafter,the frequency ratio method,multicollinearity test,and interactive detector were used to analyze and evaluate the optimized factors.Subsequently,the random forest(RF)model was used to create a landslide susceptibility map with original and optimized factors.The resultant hybrid models GeoDetector-RF and RFE-RF were evaluated and compared by the area under the receiver operating characteristic curve(AUC)and accuracy.The accuracy of the two hybrid models(0.868 for GeoDetector-RF and 0.869 for RFE-RF)were higher than that of the RF model(0.860),indicating that the hybrid models with factor optimization have high reliability and predictability.Both RFE-RF GeoDetector-RF had higher AUC values,respectively 0.863 and 0.860,than RF(0.853).These results confirm the ability of factor optimization methods to improve the performance of landslide susceptibility models.
文摘[目的]揭示黄土高原农牧交错带草地净初级生产力(NPP)时空演变规律,明确自然因素与人类活动作用及其交互驱动机制,为该区域或类似草地生态系统的科学管理与可持续利用提供理论依据。[方法]应用CASA模型模拟1990—2020年草地NPP,结合趋势分析及最优参数地理探测器识别草地NPP时空变化特征的驱动因素。[结果](1) 1990—2020年黄土高原农牧交错带草地NPP整体呈增加趋势,年平均增长率4.93 g C/(m^(2)·a)。NPP的阶段性特征比较明显,1990—1999年草地NPP呈不显著下降趋势;2000年后,草地NPP开始增加,2011—2020年这一阶段增加显著。(2) 1990—2020年草地NPP呈显著增加的面积达82.15%;减少的地区仅占3.14%,零星分布于内蒙古自治区。(3)草地NPP呈东南高、西北低的分异格局,降水和坡度是主要驱动因素,并且总体呈正向作用;人类活动的影响在因子间非线性交互作用下显著增强,其中放牧、耕地及建设用地扩张整体呈负向效应。但随着人均GDP的增加,生态保护与技术投入降低了人类活动的负面影响。[结论]黄土高原农牧交错带草地整体恢复较好,未来草地管理中考虑自然作用的影响与差异化的适度放牧政策,增加农牧民收入,同时平衡草地生态系统的直接受益者(草地生产力使用)和间接受益者(草地调节服务)之间的权衡。
文摘土壤风蚀是评估干旱半干旱区生态环境的关键。针对现有研究在干旱区大区域尺度上的不足,利用GIS技术和修正风蚀方程模型模拟了中国干旱半干旱区1990—2020年五个时期的土壤风蚀时空特征,利用最优参数地理探测器研究了其驱动因素,结果表明:(1)中国干旱半干旱区年均风蚀量达31.66亿t,土壤风蚀量平均值为0.566 kg m^(-2)a^(-1),风蚀高值区集中于华北平原、内蒙古高原、准噶尔盆地、柴达木盆地及青藏高原大部。风蚀强度以微度和轻度为主,剧烈侵蚀仅占0.37%。(2)土壤风蚀量总体呈现波动下降趋势,下降速率为0.027 kg m^(-2)a^(-1),且大部分区域风蚀减轻。(3)不同土地利用类型年均单位面积风蚀量排序:裸地>建设用地>农田>沙地>草地>灌丛>林地。(4)识别出风速、降水、大风日数、植被覆盖度和坡度为主导驱动因子,其中风速与大风日数的交互作用对风蚀解释力最强。研究为干旱半干旱区风蚀防治与生态修复提供科学依据,服务于区域可持续发展和环境治理政策。
基金funded primarily by the Central Public Welfare Research Institutes Basic Research Business Funds to Support the Administration’s Central Work Project(Grant No.CAFYBB2023ZA003-4)the National Natural Science Foundation of China(Grant Nos.31170593 and 31570633)National Forestry and Grassland Administration Forestry Under the Project“Forestry Major Issues Research”(Grant Nos.500102-1776 and 500102-5110).
文摘Understanding the influencing factors of ecosystem services(ESs)and their relationships is essential for sustainable ecosystem management in degraded alpine ecosystems.There is a lack of integrated multi-model approaches to explore the multidimensional influences on ESs and their relationships in alpine ecosystems.Taking the Daxing'anling forest area,Inner Mongolia(DFAIM)as a case study,this study used the integrated valuation of ecosystem services and trade-offs(InVEST)model to quantify four ESs—soil conservation(SC),water yield(WY),carbon storage(CS),and habitat quality(HQ)—from 2013 to 2018.We adopted root mean square deviation(RMSD)and coupling coordination degree models(CCDM)to analyze their relationships,and integrated three complementary approaches—optimal parameter-based geographical detector model(OPGDM),gradient boosting regression tree model(GBRTM),and quantile regression model(QRM)—to reveal multidimensional influencing factors.Key findings include the following:(1)From 2013 to 2018,WY,SC,and HQ declined while CS increased.WY was primarily influenced by mean annual precipitation(MAP),forest ratio(RF),and soil bulk density(SBD);CS and HQ by RF and population density(PD);and SC by slope(S),RF,and MAP.Mean annual temperature(MAT),gross domestic product(GDP),and road network density(RND)showed increasing negative impacts.(2)Low trade-off intensity(TI<0.15)dominated all ES pairs,with RF,MAP,PD,and normalized difference vegetation index(NDVI)being the dominant factors.The factor interactions primarily showed two-factor enhancement patterns.(3)The average coupling coordination degree(CCD)of the four ESs was low and declined over time,with low-CCD areas becoming increasingly prevalent.RF,S,SBD,and NDVI positively influenced CCD,while PD,MAT,GDP,and RND had increasing negative impacts,with over 62%of the factor interactions exceeding the individual factor effects.In summary,ES supply generally decreased.Local relationships showed moderate coordination,while overall relationships indicated primary dysfunction.Land use and natural factors primarily shaped these ES and their relationships,while climate and socioeconomic changes diminished ES supply and intensified competition.We recommend enhancing the resilience of natural systems rather than replacing them,establishing climate adaptation monitoring systems,and promoting conservation tillage and cross-departmental coordination mechanisms for collaborative ES optimization.These results provide valuable insights into the sustainable management of alpine ecosystems.
