干旱区生态环境知识资源中心(Arid): 基于机器学习的绿洲土壤盐渍化尺度效应研究

Arid

	基于机器学习的绿洲土壤盐渍化尺度效应研究
其他题名	Scale Effect on Soil Salinization Simulation in Arid Oasis Based on Machine Learning Methods
	陈香月; 丁建丽; 葛翔宇; 王飞; 王敬哲
来源期刊	农业机械学报
ISSN	1000-1298
出版年	2021
卷号	52 期号:9 页码:312-320
中文摘要	针对干旱区绿洲土壤盐渍化的生态环境问题,以新疆维吾尔自治区奇台绿洲为研究区,基于58个表层土壤盐度数据及与之对应的Landsat TM多光谱遥感影像数据,分别选取栅格重采样(空间分辨率为30~990 m)和邻域滤波(窗口尺度为33、55、...、31*31)两种尺度转换方法获取不同尺度下Landsat TM派生数据,并据此计算相应的环境变量(总数为720);随后利用梯度提升决策树(GBDT)模型在不同尺度下依托环境变量对土壤盐度进行模拟,并分析其定量关系。结果表明:单一尺度下,基于30 m空间分辨率的邻域滤波方法对土壤盐度的解析力总体优于栅格重采样模式,其最大解析力分别为78.55%、75.31%。混合多种尺度下,对土壤盐度的解析效果较单一尺度得到明显提升,解析力最高可达90.66%,有效实现了信息互补。栅格重采样模式相对于邻域滤波而言,其调整R~2波动范围更为宽泛,说明栅格重采样尺度变换方法相较于邻域滤波对土壤盐度-环境变量关系的表征更具灵敏性。
英文摘要	Soil salinity is one of the crucial factors which affects eco-environmental quality in the oasis of arid regions.Consequently,there is a great need to monitor soil salinity for prevention and mitigation of land degradation and further promote regional sustainable development.The variation in soil salinity is affected by environmental factors that occur at different scales with varying intensities.It is critical to adequately consider environmental variables under scale effects for digital soil mapping which has been minimally discussed in previous studies.Totally 58 soil samples were collected from the Qitai Oasis,Xinjiang Uygur Autonomous Region of China.In the laboratory,the soil samples were prepared for analysis of electrical conductivity(EC)when prepared into suspensions 1∶5 in soil and distilled water ratio.In addition,the corresponding Landsat-5 TM data was collected and preprocessed for up-scale transformation by raster resampling(spatial resolution were 30~990 m)and neighborhood filtering(window size were 33,55,...,31*31),and the environmental variables(vegetation index(VI),normalized difference infrared index(NDII),principal component analysis(PCA),and tasseled cap transformation(TC))were further generated.Then,the gradient boosting decision tree(GBDT)model was employed for the estimation of surface soil salinity based on these 720 environmental variables at various spatial scales.The results showed that for individual scale mode,the neighborhood filtering method based on 30 m pretreated data was generally better than those of the raster resampling modes,and the maximum analytical power reached 78.55% and 75.31%,respectively.In terms of mixed scale,the analytical effect of soil salinity was significantly improved compared with the mode of individual scale,and the analytical power could reach up to 90.66%,which suggested the effective information complementarity.Compared with the neighborhood filtering,the range of adjusts R~2 of the resampling mode was broader,which indicated that the scale transformation of grid resampling was more sensitive to the characterization of the relationship between soil salinity and environmental variables.The research result was helpful for understanding specific scale-dependent relationships and had the potential to reveal the scale control of soil salinity variation in arid regions.
中文关键词	土壤盐渍化 ; 遥感 ; 尺度效应 ; 环境变量 ; 邻域滤波
英文关键词	soil salinization remote sensing scale effect environment variables neighborhood filtering
类型	Article
语种	中文
收录类别	CSCD
WOS类目	Geography
CSCD记录号	CSCD:7048675
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/377801
作者单位	陈香月, 新疆大学;;新疆大学, 智慧城市与环境建模自治区普通高校重点实验室;;绿洲生态教育部重点实验室, 乌鲁木齐;;乌鲁木齐, ;; 830046;;830046.; 丁建丽, 新疆大学;;新疆大学, 智慧城市与环境建模自治区普通高校重点实验室;;绿洲生态教育部重点实验室, 乌鲁木齐;;乌鲁木齐, ;; 830046;;830046.; 葛翔宇, 新疆大学;;新疆大学, 智慧城市与环境建模自治区普通高校重点实验室;;绿洲生态教育部重点实验室, 乌鲁木齐;;乌鲁木齐, ;; 830046;;830046.; 王飞, 新疆大学;;新疆大学, 智慧城市与环境建模自治区普通高校重点实验室;;绿洲生态教育部重点实验室, 乌鲁木齐;;乌鲁木齐, ;; 830046;;830046.; 王敬哲, 深圳大学, 自然资源部大湾区地理环境监测重点实验室, 深圳, 广东 518060, 中国.
推荐引用方式 GB/T 7714	陈香月,丁建丽,葛翔宇,等. 基于机器学习的绿洲土壤盐渍化尺度效应研究[J],2021,52(9):312-320.
APA	陈香月,丁建丽,葛翔宇,王飞,&王敬哲.(2021).基于机器学习的绿洲土壤盐渍化尺度效应研究.农业机械学报,52(9),312-320.
MLA	陈香月,et al."基于机器学习的绿洲土壤盐渍化尺度效应研究".农业机械学报 52.9(2021):312-320.