Xinjiang Uygur Autonomous Region,the largest agricultural high-efficiency water-saving arid area in China,was adopted to explore the coupling relationship between agricultural water consumption and economic benefits,w...Xinjiang Uygur Autonomous Region,the largest agricultural high-efficiency water-saving arid area in China,was adopted to explore the coupling relationship between agricultural water consumption and economic benefits,which is of great significance to guiding the efficient utilization and sustainable development of agricultural water resources.This study utilizes an indicator,termed the Agricultural Water Footprint Intensity(short as AWFI,which means the amount of water resource consumed per unit of agricultural GDP),to study the economic benefits of agricultural water in Xinjiang from 1991-2018.In addition,the Theil index,a measure of the imbalance between individuals or regions,was used to study the evolution in the spatial differences in water efficiency,and the Logarithmic Mean Divisia Index(LMDI)method was applied to quantify the factors driving the AWFI.The results showed that AWFI in Xinjiang has experienced three stages:obvious decline,stable and slow decline,which decreased from 16114 m^(3)/10^(4) CNY to 2100 m^(3)/10^(4) CNY,decreasing by 86.97%.The Theil index indicated that the spatial evolution of 14 prefectures(cities)resembled an inverted N-shaped Kuznets curve over time.Among the influencing factors,the contributions of water-saving technology and planting structure to the change in the AWFI in Xinjiang,China from 1991 to 2018 were 154.03%and−37.98%,respectively.The total contribution to AWFI of the total population,urbanization rate,and production scale was−16.06%.This study concluded that further improvements in the economic benefits of agricultural water consumption can be obtained by continuing to promote more efficient or“water-conservation”irrigation technologies(engineering aspects),adjusting the planting structure(policy guidance aspects),and intensive management of cultivated land(management aspects).展开更多
Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning(ML) models have proven to be effective tools for assessin...Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning(ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following:(1) The stacking ensemble learning, using RF-XGBCB-LR model, significantly enhances flood susceptibility simulation.(2) In addition to rainfall,key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland.(3) In the northeast of the study area,heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management.展开更多
基金This work was financially supported by the Third Xinjiang Scientific Expedition(Grant No.2022xjkk0103,2021xjkk0406)the National Natural Science Foundation of China(Grant No.52179028)+1 种基金the Water Conservancy Science and Technology Project of Hunan Province(Grant No.XSKJ2019081-02)the Xinjiang Water Conservancy Science and technology project(Grant No.XSKJ-2021-01).
文摘Xinjiang Uygur Autonomous Region,the largest agricultural high-efficiency water-saving arid area in China,was adopted to explore the coupling relationship between agricultural water consumption and economic benefits,which is of great significance to guiding the efficient utilization and sustainable development of agricultural water resources.This study utilizes an indicator,termed the Agricultural Water Footprint Intensity(short as AWFI,which means the amount of water resource consumed per unit of agricultural GDP),to study the economic benefits of agricultural water in Xinjiang from 1991-2018.In addition,the Theil index,a measure of the imbalance between individuals or regions,was used to study the evolution in the spatial differences in water efficiency,and the Logarithmic Mean Divisia Index(LMDI)method was applied to quantify the factors driving the AWFI.The results showed that AWFI in Xinjiang has experienced three stages:obvious decline,stable and slow decline,which decreased from 16114 m^(3)/10^(4) CNY to 2100 m^(3)/10^(4) CNY,decreasing by 86.97%.The Theil index indicated that the spatial evolution of 14 prefectures(cities)resembled an inverted N-shaped Kuznets curve over time.Among the influencing factors,the contributions of water-saving technology and planting structure to the change in the AWFI in Xinjiang,China from 1991 to 2018 were 154.03%and−37.98%,respectively.The total contribution to AWFI of the total population,urbanization rate,and production scale was−16.06%.This study concluded that further improvements in the economic benefits of agricultural water consumption can be obtained by continuing to promote more efficient or“water-conservation”irrigation technologies(engineering aspects),adjusting the planting structure(policy guidance aspects),and intensive management of cultivated land(management aspects).
基金National Natural Science Foundation of China,No.42271037Key Research and Development Program Project of Anhui Province,No.2022m07020011+1 种基金The University Synergy Innovation Program of Anhui Province,No.GXXT-2021-048Science Foundation for Excellent Young Scholars of Anhui,No.2108085Y13。
文摘Flood susceptibility modeling is crucial for rapid flood forecasting, disaster reduction strategies, evacuation planning, and decision-making. Machine learning(ML) models have proven to be effective tools for assessing flood susceptibility. However, most previous studies have focused on individual models or comparative performance, underscoring the unique strengths and weaknesses of each model. In this study, we propose a stacking ensemble learning algorithm that harnesses the strengths of a diverse range of machine learning models. The findings reveal the following:(1) The stacking ensemble learning, using RF-XGBCB-LR model, significantly enhances flood susceptibility simulation.(2) In addition to rainfall,key flood drivers in the study area include NDVI, and impervious surfaces. Over 40% of the study area, primarily in the northeast and southeast, exhibits high flood susceptibility, with higher risks for populations compared to cropland.(3) In the northeast of the study area,heavy precipitation, low terrain, and NDVI values are key indicators contributing to high flood susceptibility, while long-duration precipitation, mountainous topography, and upper reach vegetation are the main drivers in the southeast. This study underscores the effectiveness of ML, particularly ensemble learning, in flood modeling. It identifies vulnerable areas and contributes to improved flood risk management.
