干旱区生态环境知识资源中心(Arid): BPNN对不同人为活动区域的盐渍土Na~+ 高光谱估测

Arid

	BPNN对不同人为活动区域的盐渍土Na~+ 高光谱估测
其他题名	Hyperspectral Estimation of Na~+Ion in Saline Soils in Areas With Different Human Activities Using BPNN Model
	田安红; 付承彪; 熊黑钢; 赵俊三
来源期刊	水土保持研究
ISSN	1005-3409
出版年	2020
卷号	27 期号:2 页码:364-369
中文摘要	土壤盐分阳离子Na~+在盐渍土的形成过程中起着重要作用,以新疆无人为活动(A区)和有人为活动(B区)区域的土壤为研究对象,采集野外高光谱和土壤020cm样本,化验Na~+含量,利用BP神经网络(BPNN)、偏最小二乘(PLSR)和逐步多元回归(SMLR)模型对比分析Na~+的高光谱估测,并力图解释Na~+在不同人为活动区域的估算精度机理。结果表明:Na~+在A区和B区的4种阳离子(Ca~(2+),Mg~(2+),K~+,Na~+)中,所占比例最高分别为48.4%和62.3%,均值最大分别为1.590,2.148。对原始(R)和倒数(1/R)两种光谱变换进行一阶与二阶微分预处理,提取出相关系数通过0.05检验的波段为特征波段,3种建模方法在两个研究区域中共有24种模型,且1/R在二阶微分处的BPNN模型均是A区和B区的最佳预测模型,分别迭代19次和9次时精度满足要求。相对分析误差RPD、决定系数R~2和均方根误差RMSE在A区分别为2.461 6,0.860 9,0.350 1,在B区分别为2.169 8,0.800 6,0.803 5。BPNN对Na~+离子的预测能力很好,PLSR的预测能力一般,SMLR的预测能力很差。研究成果可为改良干旱区的盐渍化土壤提供科学依据。
英文摘要	Cation Na~+of soil salinity plays an important role in the formation of saline soil.The soils in no human activity(Zone A)and human activity(Zone B)of Xinjiang were studied.Field hyperspectral data and 020cm soil samples were collected,and Na~+ contents were tested.BP neural network(BPNN),partial least squares(PLSR)and stepwise multiple regression(SMLR)models were used to compare and analyze the hyperspectral estimation of Na~+,and to explain the mechanism of Na~+estimation accuracy in areas with different human activities.The results show that the Na~+ has the highest proportion and the largest mean value among the four cations(Ca~(2+),Mg~(2+),K~+,Na~+),the proportion of Na~+in Zone A and B is 48.429% and 62.274%,respectively,and the mean value is 1.590and 2.148,respectively.First-order and second-order differential processing were been performed on the Original(R)and reciprocal(1/R)spectral transforms, and the band whose correlation coefficient was checked by 0.05was extracted as the characteristic band. There are 24models in Zone A and B for the three modeling methods,and the BPNN models with 1/R at the second-order differential are the best prediction models for Zone A and B,which meet the accuracy requirements when they are iterated by 19times and 9times,respectively.The relative analysis error RPD,the decision coefficient R~2,and the root mean square error RMSE are 2.461 6,0.860 9,and 0.350 1in Zone A, and 2.169 8,0.800 6,and 0.803 5in Zone B,respectively.The prediction ability of BPNN for Na~+ions is very good,the prediction ability of PLSR is general,and the prediction ability of SMLR is very poor.These research results can provide a scientific basis for improving salinized soil in arid regions.
中文关键词	盐渍土 ; Na~+ 离子 ; 微分处理 ; BP神经网络 ; 野外高光谱
英文关键词	saline soil Na~+ differential processing BP neural network field hyperspectral data
类型	Article
语种	中文
收录类别	CSCD
WOS研究方向	Agriculture
CSCD记录号	CSCD:6713084
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/336437
作者单位	田安红, 曲靖师范学院信息工程学院, 曲靖, 云南 655011, 中国.; 付承彪, 曲靖师范学院信息工程学院, 曲靖, 云南 655011, 中国.; 熊黑钢, 北京联合大学应用文理学院, 北京 100083, 中国.; 赵俊三, 昆明理工大学国土资源工程学院, 昆明, 云南 650093, 中国.
推荐引用方式 GB/T 7714	田安红,付承彪,熊黑钢,等. BPNN对不同人为活动区域的盐渍土Na~+ 高光谱估测[J],2020,27(2):364-369.
APA	田安红,付承彪,熊黑钢,&赵俊三.(2020).BPNN对不同人为活动区域的盐渍土Na~+ 高光谱估测.水土保持研究,27(2),364-369.
MLA	田安红,et al."BPNN对不同人为活动区域的盐渍土Na~+ 高光谱估测".水土保持研究 27.2(2020):364-369.