田安红^{1, 2,},
付承彪^1,,,
熊黑钢^{3, 4},
赵俊三²
1.曲靖师范学院信息工程学院 曲靖 655011
2.昆明理工大学国土资源工程学院 昆明 650093
3.北京联合大学应用文理学院 北京 100083
4.新疆大学资源与环境科学学院 乌鲁木齐 830046
基金项目: 国家自然科学基金项目41901065
国家自然科学基金项目41671198
国家自然科学基金项目41761081

详细信息

作者简介:田安红, 主要从事干旱区盐渍土的高光谱研究。E-mail:tianfucb@163.com

通讯作者:付承彪, 主要从事遥感与地理信息系统的研究。E-mail:fucb305@163.com

中图分类号:S151.9

计量

文章访问数:412
HTML全文浏览量:6
PDF下载量:198
被引次数:0

出版历程

收稿日期:2019-09-26
录用日期:2019-12-10
刊出日期:2020-02-01

Quantitative analysis of SO₄^2- in saline soil under areas disturbed and undisturbed by human using BP Neural Network

TIAN Anhong^{1, 2,},
FU Chengbiao^1,,,
XIONG Heigang^{3, 4},
ZHAO Junsan²
1. College of Information Engineering, Qujing Normal University, Qujing 655011, China
2. Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650093, China
3. College of Applied Arts and Science, Beijing Union University, Beijing 100083, China
4. College of Resource and Environment Sciences, Xinjiang University, Urumqi 830046, China
Funds: the National Natural Science Foundation of China41901065
the National Natural Science Foundation of China41671198
the National Natural Science Foundation of China41761081

More Information

Corresponding author:FU Chengbiao, E-mail:fucb305@163.com

摘要
HTML全文
图(6)表(3)
参考文献(26)
相关文章
施引文献
资源附件(0)
访问统计

摘要
摘要:SO₄^2-是盐渍土阴离子中的主要离子，但目前针对不同人为干扰区域土壤中SO₄^2-反演研究却鲜有报道。土壤高光谱与土壤某元素间的关系表现为非线性，传统线性偏最小二乘模型（PLSR）对土壤元素的反演精度有限。本文以新疆昌吉回族自治州境内不同人为干扰区域的盐渍化土壤为研究对象，以土壤的野外高光谱和SO₄^2-含量为数据源，对原始（R）和对数（LogR）变换后的高光谱分别进行0阶、一阶和二阶微分预处理，选择通过0.05显著性水平的波段为敏感波段，将敏感波段对应的高光谱反射率作为非线性BP神经网络模型的输入变量，并设定BP的隐藏节点为300，学习速率为0.01，最大迭代次数为1 000，训练函数为trainscg。从SO₄^2-的真实值与预测值的散点图、拟合效果图和BP训练过程3个方面，定量分析无人为干扰（A区）和有人为干扰（B区）土壤SO₄^2-含量，并与PLSR对比预测精度。仿真显示，A区二阶微分后的BP预测精度优于一阶微分，而B区一阶微分后的BP预测精度优于二阶微分。且不论在A区还是B区，LogR光谱变换的反演精度均优于R。最佳BP模型的相对预测性能（RPD）、决定系数（R²）、均方根误差（RMSE）和迭代次数，在A区分别为3.309、0.906、0.253和8次，在B区分别为2.234、0.844、0.786和45次，表明BP对A区SO₄^2-的预测能力非常强（RPD>2.5），对B区SO₄^2-的预测能力较强（RPD为2.0~2.5）。而在A区和B区两种光谱变换的一阶和二阶微分中，PLSR的RPD值均在1.4与1.8之间，其预测性能一般；在B区的0阶微分中，PLSR的RPD值均小于1.0，其不能对SO₄^2-进行预测。因此，BP模型能对不同人为干扰区域的SO₄^2-进行有效的定量分析。
关键词:盐渍土/
人为干扰区域/
SO₄^2-含量/
BP神经网络模型/
光谱变换
Abstract:SO₄^2- is one of the main ions in saline soil, but the inversion of SO₄^2- ion in soils under different levels of human disturbance has rarely been reported. Moreover, the relationship between soil hyperspectral and soil elements is nonlinear, and the traditional linear partial least squares model (PLSR) has limited inversion accuracy for soil elements. In order to quantitatively analyzed soil SO₄^2- content in saline soil, this study selected the saline soils in areas undisturbed and human-disturbed in Changji Hui Autonomous Prefecture of Xinjiang, to predict SO₄^2- contents based on soil hyperspectral by using BP Neural Network. The original (R) and logarithmic transformed (LogR) hyperspectral were subjected as 0-order, first-order and second-order differential preprocessing, respectively. The hyperspectral reflectivity corresponding to the sensitive band was taken as the input variable of the nonlinear BP neural network model, and the hidden node, learning rate and maximum number of iterations of BP were set as 300, 0.01, and 1 000. The training function was trainscg. The SO₄^2- contents of saline soil in undisturbed area (Area A) and human-disturbed area (Area B) were determined by using the scatter plot of measured and predicted SO₄^2- contents, the fitting effect map, and the BP training process. The prediction accuracy was tested by comparison with PLSR results. The simulation showed that the BP prediction accuracy after the second-order differentiation in the Area A was better than the first-order differential, while it was opposite for the Area B. The inversion accuracy of LogR spectral transformation was better than R for both Area A and Area B. The relative prediction performance (RPD), determination coefficient (R²), root mean square error (RMSE) and iteration number of the optimal BP model were 3.309, 0.906, 0.253 and 8 times in the Area A; and 2.234, 0.844, 0.786 and 45 times in the Area B. It indicated that BP predictive ability was strong for SO₄^2- content in Area A and Area B. However, for the first- and second-order differentials of spectral in the Area A and Area B, the RPD values of the PLSR were 1.4-1.8, and the prediction performance was normal; in the 0-order differential of the Area B, the RPD of PLSR were all less than 1.0, which could not predict SO₄^2- content. Therefore, the BP model can perform effectively quantitative analysis of SO₄^2- in different undisturbed or human-disturbed regions.
Key words:Saline soil/
Human-disturbed area/
SO₄^2- content/
BP neural network model/
Spectral transformation

HTML全文


图1无人为干扰区(A)和人为干扰区(B)盐渍土采样点示意图
蓝色方框为水渠位置, 红色圆圈为农场位置, 黄色方框为无人为干扰区(A区), 绿色方框为人为干扰区(B区)。
Figure1.Sampling points of saline soils in the undisturbed area (A) and the human-disturbed area (B)
The blue box is the location of the canal, the red circle is the location of the farm, the yellow box is the undisturbed area (area A), and the green box is the human disturbing area (area B).


下载: 全尺寸图片幻灯片


图2无人为干扰区(A区)和人为干扰区(B区)不同SO₄^2-含量盐渍土壤样本的高光谱曲线图
Figure2.Hyperspectral curves of saline soil samples with different SO₄^2- contents in the undisturbed area (Area A) and the human-disturbed area (Area B)


下载: 全尺寸图片幻灯片


图3无人为干扰区(A区)和人为干扰区(B区)盐渍土高光谱与SO₄^2-含量的相关系数
< |P_0.05|表示显著相关。
Figure3.Correlation coefficients between hyperspectral and SO₄^2- content of saline soil in the undisturbed area (Area A) and the human-disturbed area (Area B)
< |P_0.05| indicates significant correlation.


下载: 全尺寸图片幻灯片


图4无人为干扰区(a)和人为干扰区(b)盐渍土SO₄^2-含量实测值和BP模型预测值的散点图
图中预测数据为高光谱对数二阶微分(LogR)的BP模型预测值。
Figure4.Scatter plots of the measured and BP model-predicted saline soil SO₄^2- contents in the undisturbed (a) and human-disturbed (b) areas
The predicted values are prediction results of BP model with spectral logarithmic transformation.


下载: 全尺寸图片幻灯片


图5无人为干扰区(a)和人为干扰区(b)盐渍土SO₄^2-含量实测值与BP模型预测值的拟合效果
图中预测数据为高光谱对数二阶微分(LogR)的BP模型预测值。
Figure5.Fitting effects between the measured and BP model-predicted saline soil SO₄^2- contents in the undisturbed (a) and human-disturbed (b) areas
The predicted values are prediction results of BP model with spectral Logarithmic transformation.


下载: 全尺寸图片幻灯片


图6无人为干扰区(a)和人为干扰区(b)盐渍土SO₄^2-含量BP模型的训练过程
Figure6.Training processes of the BP model of saline soil SO₄^2- contents in the undisturbed (a) and human-disturbed (b) areas


下载: 全尺寸图片幻灯片

表1无人为干扰区和人为干扰区盐渍土4种阴离子含量描述性统计
Table1.Descriptive statistics of four anions of saline soil in the undisturbed area and the human-disturbed area

阴离子 Anion	无人为干扰区 Undisturbed area						人为干扰区 Human-disturbed area
	最小值 Min. value (g·kg-1)	最大值 Max. value (g·kg-1)	标准差 Standard deviation (g·kg-1)	均值 Mean (g·kg-1)	比例 Proportion (%)		最小值 Min. value (g·kg-1)	最大值 Max. value (g·kg-1)	标准差 Standard deviation (g·kg-1)	均值 Mean (g·kg-1)	比例 Proportion (%)
CO32-	0.000	0.098	0.019	0.013	0.196		0.000	0.114	0.025	0.014	0.190
HCO3-	0.116	0.233	0.026	0.147	2.288		0.033	0.166	0.024	0.139	1.843
Cl-	0.077	9.882	2.157	1.167	18.144		0.077	15.646	4.043	3.081	40.942
SO42-	1.743	5.734	1.016	5.104	79.372		0.169	5.846	1.729	4.291	57.025

下载: 导出CSV
表2无人为干扰区和人为干扰区通过0.05显著性检验的盐渍土高光谱波段数量个数
Table2.Number of spectral bands passed the 0.05 significance test for saline soil in the undisturbed area and the human-disturbed area

光谱变换 Spectral transform	无人为干扰区 Undisturbed area	人为干扰区 Human-disturbed area
R的0阶Zero order of R	0	1 822
R的一阶First order of R	38	264
R的二阶Second order of R	77	121
LogR的0阶Zero order of LogR	0	1 659
LogR的一阶First order of LogR	39	121
LogR的二阶Second order of LogR	74	86
R表示原始高光谱, LogR表示对数变换后的光谱。R is the original hyperspectral, LogR is logarithmic transformation of R.

下载: 导出CSV
表3无人为干扰区和人为干扰区盐渍土SO₄^2-含量高光谱反演模型的精度
Table3.Accuracy of hyperspectral inversion models for saline soil SO₄^2- contents in the undisturbed area and the human-disturbed area

光谱变换 Spectral transform	模型 Model		无人为干扰区 Undisturbed area				人为干扰区 Human-disturbed area
			R2	RMSE	RPD		R2	RMSE	RPD
原始高光谱(R) Original hyperspectral	BP	0阶微分Zero order differential	0.000	0.000	0.000		0.526	1.420	1.135
		一阶微分First order differential	0.823	0.425	2.372		0.819	1.059	1.967
		二阶微分Second order differential	0.945	0.367	2.464		0.729	0.946	1.913
	PLSR	0阶微分Zero order differential	0.000	0.000	0.000		0.132	1.547	0.824
		一阶微分First order differential	0.729	0.475	1.490		0.561	1.281	1.482
		二阶微分Second order differential	0.585	0.765	1.507		0.608	1.079	1.414
对数变换(LogR) Logarithmic transformation	BP	0阶微分Zero order differential	0.000	0.000	0.000		0.560	1.333	1.257
		一阶微分First order differential	0.911	0.380	3.080		0.844	0.786	2.234
		二阶微分Second order differential	0.906	0.253	3.309		0.766	0.853	2.121
	PLSR	0阶微分Zero order differential	0.000	0.000	0.000		0.247	2.325	0.629
		一阶微分First order differential	0.598	0.723	1.443		0.604	1.257	1.567
		二阶微分Second order differential	0.734	0.572	1.682		0.667	1.196	1.546
RPD:相对预测性能。RPD: relative prediction performance.

下载: 导出CSV

参考文献(26)

[1]	段鹏程, 熊黑钢, 李荣荣, 等.不同干扰程度的盐渍土与其光谱反射特征定量分析[J].光谱学与光谱分析, 2017, 37(2):571-576 http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx201702046 DUAN P C, XIONG H G, LI R R, et al. A quantitative analysis of the reflectance of the saline soil under different disturbance extent[J]. Spectroscopy and Spectral Analysis, 2017, 37(2):571-576 http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx201702046
[2]	高会, 陈红艳, 刘慧涛, 等.基于高光谱的鲁西北平原土壤有效磷含量快速检测研究[J].中国生态农业学报, 2013, 21(6):752-757 http://www.ecoagri.ac.cn/zgstny/ch/reader/view_abstract.aspx?file_no=2013615&flag=1 GAO H, CHEN H Y, LIU H T, et al. Spontaneous determination of soil available phosphorus using high spectrum in the northwest plain of Shandong Province[J]. Chinese Journal of Eco-Agriculture, 2013, 21(6):752-757 http://www.ecoagri.ac.cn/zgstny/ch/reader/view_abstract.aspx?file_no=2013615&flag=1
[3]	张娟娟, 余华, 乔红波, 等.基于高光谱特征的土壤有机质含量估测研究[J].中国生态农业学报, 2012, 20(5):566-572 http://www.ecoagri.ac.cn/zgstny/ch/reader/view_abstract.aspx?file_no=2012509&flag=1 ZHANG J J, YU H, QIAO H B, et al. Soil organic matter content estimation based on hyperspectral properties[J]. Chinese Journal of Eco-Agriculture, 2012, 20(5):566-572 http://www.ecoagri.ac.cn/zgstny/ch/reader/view_abstract.aspx?file_no=2012509&flag=1
[4]	蔡亮红, 丁建丽.基于高光谱多尺度分解的土壤含水量反演[J].激光与光电子学进展, 2018, 55(1):400-409 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jgygdzxjz201801052 CAI L H, DING J L. Inversion of soil moisture content based on hyperspectral multi-scale decomposition[J]. Laser & Optoelectronics Progress, 2018, 55(1):400-409 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jgygdzxjz201801052
[5]	MASOUD A A, KOIKE K, ATWIA M G, et al. Mapping soil salinity using spectral mixture analysis of landsat 8 OLI images to identify factors influencing salinization in an arid region[J]. International Journal of Applied Earth Observation and Geoinformation, 2019, 83:101944 doi: 10.1016/j.jag.2019.101944
[6]	LITALIEN A, ZEEB B. Curing the earth:A review of anthropogenic soil salinization and plant-based strategies for sustainable mitigation[J]. Science of the Total Environment, 2020, 698:134235 doi: 10.1016/j.scitotenv.2019.134235
[7]	EL HASINI S, IBEN HALIMA O, EL AZZOUZI M, et al. Organic and inorganic remediation of soils affected by salinity in the Sebkha of Sed El Mesjoune-Marrakech (Morocco)[J]. Soil and Tillage Research, 2019, 193:153-160 doi: 10.1016/j.still.2019.06.003
[8]	LI N, KANG Y H, LI X B, et al. Response of tall fescue to the reclamation of severely saline coastal soil using treated effluent in Bohai Bay[J]. Agricultural Water Management, 2019, 218:203-210 doi: 10.1016/j.agwat.2019.03.025
[9]	SCUDIERO E, SKAGGS T H, CORWIN D L. Comparative regional-scale soil salinity assessment with near-ground apparent electrical conductivity and remote sensing canopy reflectance[J]. Ecological Indicators, 2016, 70:276-284 doi: 10.1016/j.ecolind.2016.06.015
[10]	LI J G, PU L J, HAN M F, et al. Soil salinization research in China:Advances and prospects[J]. Journal of Geographical Sciences, 2014, 24(5):943-960 doi: 10.1007/s11442-014-1130-2
[11]	梁静, 丁建丽, 王敬哲, 等.基于反射光谱与Landsat 8 OLI多光谱数据的艾比湖湿地土壤盐分估算[J].土壤学报, 2019, 56(2):320-330 http://d.old.wanfangdata.com.cn/Periodical/trxb201902007 LIANG J, DING J L, WANG J Z, et al. Quantitative estimation and mapping of soil salinity in the Ebinur lake wetland based on vis-NIR reflectance and landsat 8 OLI data[J]. Acta Pedologica Sinica, 2019, 56(2):320-330 http://d.old.wanfangdata.com.cn/Periodical/trxb201902007
[12]	WANG R S, WAN S Q, SUN J X, et al. Soil salinity, sodicity and cotton yield parameters under different drip irrigation regimes during saline wasteland reclamation[J]. Agricultural Water Management, 2018, 209:20-31 doi: 10.1016/j.agwat.2018.07.004
[13]	PENG J, BISWAS A, JIANG Q S, et al. Estimating soil salinity from remote sensing and terrain data in southern Xinjiang Province, China[J]. Geoderma, 2019, 337:1309-1319 doi: 10.1016/j.geoderma.2018.08.006
[14]	夏芳, 彭杰, 王乾龙, 等.基于省域尺度的农田土壤重金属高光谱预测[J].红外与毫米波学报, 2015, 34(5):593-598 http://d.old.wanfangdata.com.cn/Periodical/hwyhmb201505014 XIA F, PENG J, WANG Q L, et al. Prediction of heavy metal content in soil of cultivated land:Hyperspectral technology at provincial scale[J]. Journal of Infrared and Millimeter Waves, 2015, 34(5):593-598 http://d.old.wanfangdata.com.cn/Periodical/hwyhmb201505014
[15]	王文俊, 王璨, 李志伟, 等.基于高光谱技术的褐土土壤总氮含量的预测[J].山西农业大学学报:自然科学版, 2018, 38(9):71-76 http://d.old.wanfangdata.com.cn/Periodical/sxnydxxb201809013 WANG W J, WANG C, LI Z W, et al. Prediction of total nitrogen content in brown soil based on hyperspectral technology[J]. Journal of Shanxi Agricultural University:Natural Science Edition, 2018, 38(9):71-76 http://d.old.wanfangdata.com.cn/Periodical/sxnydxxb201809013
[16]	LIANG Y J, REN C, WANG H Y, et al. Research on soil moisture inversion method based on GA-BP neural network model[J]. International Journal of Remote Sensing, 2019, 40(5/6):2087-2103 doi: 10.1080/01431161.2018.1484961?journalCode=tres20
[17]	CUI K, QIN X T. Virtual reality research of the dynamic characteristics of soft soil under metro vibration loads based on BP neural networks[J]. Neural Computing and Applications, 2018, 29(5):1233-1242 doi: 10.1007/s00521-017-2853-7
[18]	ZHAO H J, SHI S G, JIANG H Z, et al. Calibration of AOTF-based 3D measurement system using multiplane model based on phase fringe and BP neural network[J]. Optics Express, 2017, 25(9):10413-10433 doi: 10.1364/OE.25.010413
[19]	AO H, LIAO X Y, ZHAO D, et al. Delineation of soil contaminant plumes at a co-contaminated site using BP neural networks and geostatistics[J]. Geoderma, 2019, 354:113878 doi: 10.1016/j.geoderma.2019.07.036
[20]	GOLHANI K, BALASUNDRAM S K, VADAMALAI G, et al. A review of neural networks in plant disease detection using hyperspectral data[J]. Information Processing in Agriculture, 2018, 5(3):354-371 doi: 10.1016/j.inpa.2018.05.002
[21]	刘焕军, 潘越, 窦欣, 等.黑土区田块尺度土壤有机质含量遥感反演模型[J].农业工程学报, 2018, 34(1):127-133 http://d.old.wanfangdata.com.cn/Periodical/nygcxb201801017 LIU H J, PAN Y, DOU X, et al. Soil organic matter content inversion model with remote sensing image in field scale of blacksoil area[J]. Transactions of the CSAE, 2018, 34(1):127-133 http://d.old.wanfangdata.com.cn/Periodical/nygcxb201801017
[22]	乔娟峰, 熊黑钢, 王小平, 等.基于最优模型的荒地土壤有机质含量空间反演[J].江苏农业学报, 2018, 34(1):68-75 doi: 10.3969/j.issn.1000-4440.2018.01.010 QIAO J F, XIONG H G, WANG X P, et al. Spatial inversion of soil organic matter content in wasteland based on optimal model[J]. Jiangsu Journal of Agricultural Sciences, 2018, 34(1):68-75 doi: 10.3969/j.issn.1000-4440.2018.01.010
[23]	BALDOCK J A, HAWKE B, SANDERMAN J, et al. Predicting contents of carbon and its component fractions in Australian soils from diffuse reflectance mid-infrared spectra[J]. Soil Research, 2013, 51(8):577 doi: 10.1071/SR13077
[24]	王海峰, 张智韬, Arnon Karnieli, 等.基于灰度关联-岭回归的荒漠土壤有机质含量高光谱估算[J].农业工程学报, 2018, 34(14):124-131 doi: 10.11975/j.issn.1002-6819.2018.14.016 WANG H F, ZHANG Z T, KARNIELI A, et al. Hyperspectral estimation of desert soil organic matter content based on gray correlation-ridge regression model[J]. Transactions of the CSAE, 2018, 34(14):124-131 doi: 10.11975/j.issn.1002-6819.2018.14.016
[25]	张秋霞, 张合兵, 张会娟, 等.粮食主产区耕地土壤重金属高光谱综合反演模型[J].农业机械学报, 2017, 48(3):148-155 http://d.old.wanfangdata.com.cn/Periodical/nyjxxb201703019 ZHANG Q X, ZHANG H B, ZHANG H J, et al. Hybrid inversion model of heavy metals with hyperspectral reflectance in cultivated soils of main grain producing areas[J]. Transactions of the Chinese Society of Agricultural Machinery, 2017, 48(3):148-155 http://d.old.wanfangdata.com.cn/Periodical/nyjxxb201703019
[26]	田安红, 熊黑钢, 赵俊三, 等.分数阶微分对盐渍土野外光谱预处理精度提升的机理分析[J].光谱学与光谱分析, 2019, 39(8):2495-2500 http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx201908030 TIAN A H, XIONG H G, ZHAO J S, et al. Mechanism improvement for pretreatment accuracy of field spectra of saline soil using fractional differential algorithm[J]. Spectroscopy and Spectral Analysis, 2019, 39(8):2495-2500 http://d.old.wanfangdata.com.cn/Periodical/gpxygpfx201908030