集成土壤-环境关系与机器学习的干旱区土壤属性数字制图

doi:10.3864/j.issn.0578-1752.2020.03.009

摘要/Abstract

摘要：

【目的】土壤属性的空间分布是影响农业生产力、土地管理和生态安全的重要因素。通过土壤环境耦合关系,在机器学习算法框架下,定量预测出干旱区土壤酸碱度（pH）、土壤盐分含量（Soil Salt Content,SSC)与土壤有机质（Soil Organic Matter, SOM）3种土壤属性的空间分布,为干旱区农业生产和生态安全提供科学依据。【方法】在渭干河—库车河绿洲干旱区于2017年7月设计采集典型表层（0—20 cm）土壤样品82个,依据土壤-环境之间的关系,集成DEM数据和Landsat 8数据提取出32种环境协变量,利用栅格重采样将提取出的32种变量重采样为90 m空间分辨率并转换为Grid格式参与建模。借助梯度提升决策树（Gradient Boosting Decision Tree,GBDT）模型依次对3类土壤属性的32种环境协变量进行重要性排序,并通过均方根误差（Root Mean Square Error,RMSE）界定出协变量重要性阈值点,从而筛选出参与3类土壤属性制图的环境协变量。进而运用随机森林（Random Forest, RF）、Bagging和Cubist 3种非线性模型建模,并引入多元线性回归模型（Multiple Linear Regression,MLR）进行对比分析,选出最优模型并绘制出90 m分辨率新疆渭干河-库车河绿洲干旱区pH、SSC与SOM 3种土壤属性图。【结果】梯度提升决策树能有效筛选出重要协变量,高程（Elevation）、剖面曲率（Profile Curvature）、差值植被指数（Difference Vegetation Index）、扩展增强型植被指数（Extended Normalized Difference Vegetation Index）、调整土壤亮度植被指数（Modified Soil Adjusted Vegetation Index）、盐分指数S1（Salinity Index S1）以及盐分指数S6 （Salinity Index S6） 7类环境变量均参与3类土壤属性建模,其中SSC遴选出参与建模协变量15种,pH和SOM则均为17种,且遥感指标在预测土壤属性图中起到强大的作用。机器学习3种算法的结果均优于MLR。通过3种非线性模型对比发现,随机森林在3种土壤属性中均表现最佳。在随机森林预测的3种土壤属性中,土壤pH验证集效果R ²=0.6779,RMSE =0.2182,ρ_c=0.6084;在SSC预测中,验证集R ²=0.7945,RMSE =3.1803,ρ_c=0.8377;在SOM预测中,验证集R ²=0.7472,RMSE =3.5456,ρ_c=0.7009。【结论】GBDT所筛选出的重要性因子借助机器学习算法可以用于干旱区土壤属性制图,且随机森林模型均对3类土壤属性表现出最佳预测能力。依据所绘制的土壤属性图并结合土壤分类图厘清了3种制图属性的空间分布。

关键词: 土壤属性, 环境协变量, 数字土壤制图, 机器学习, 梯度提升决策树模型, 随机森林模型, Bagging模型, Cubist模型

Abstract:

【Objective】The spatial distribution of soil properties is an important factor affecting agricultural productivity, land management and ecological security. Utilizing the coupling relationship between soil and environment within framework of machine learning algorithm, the spatial distribution of soil pH, soil salt content (SSC) and soil organic matter (SOM) was quantitatively predicted to provide a scientific basis on ecological security and agricultural production in the arid region. 【Method】A total of 82 topsoil (0-20 cm) samples were collected from the Ugan-Kuqa River basin oasis in Xinjiang Uyghur Autonomous Region in July 2017. Furthermore, Digital elevation model (DEM) data and Landsat 8 data were used to extract 32 environmental covariates according to the soil-environment relationship. The 32 extracted variables were resampled to 90 m spatial resolution via raster resampling and were converted to grid format for participate in modeling. According to the importance of environmental covariates, they were ranked respectively using Gradient Boosting Decision Tree (GBDT) algorithm on the three soil attributes. We considered three strategies to estimate soil properties, including random forest, bagging and Cubist algorithm. Compared with non-linear models, we introduced classic linear model (MLR) to conduct optimization. On this foundation, we mapped the soil properties (pH, SSC and SOM) with a resolution of 90 m in the Ugan-Kuqa River basin oasis, respectively.【Result】The results showed that GBDT could screen out important covariates effectively. Elevation and Profile Curvature, Difference Vegetation Index, Extended Normalized Difference Vegetation Index, Modified Soil Adjusted Vegetation Index and Salinity Index S1 and Salinity Index S6 were important factors and involved in modeling of three kinds of soil properties, among which SSC selects 15 covariates to participate in modeling, pH and SOM were both 17. Remote sensing index played a significant role in predicting soil property maps. Non-linear models showed more accuracy than MLR as linear model. Random forest performed best in all three soil properties. Among the three soil properties predicted by random forest, the validation dataset of soil pH, SSC and SOM were R ²=0.6779, RMSE=0.2182, ρ_c=0.6084, R ²=0.7945, RMSE=3.1803, ρ_c=0.8377 and R ²=0.7472, RMSE=3.5456, ρ_c=0.7009, respectively. 【Conclusion】 The importance factors selected by GBDT and machine learning algorithm could be used to mapping soil properties in arid areas. The random forest strategy showed the best predictive ability for soil properties. The spatial distribution of mapping three properties could be determined by combining with soil classification map.

Key words: soil property, environment covariates, digital soil mapping, machine learning, Gradient Boosting Decision Tree, GBDT, Random Forest, RF, Bagging Model, Cubist Model

张振华,丁建丽,王敬哲,葛翔宇,王瑾杰,田美玲,赵启东. 集成土壤-环境关系与机器学习的干旱区土壤属性数字制图[J]. 中国农业科学, 2020, 53(3): 563-573.

ZHANG ZhenHua,DING JianLi,WANG JingZhe,GE XiangYu,WANG JinJie,TIAN MeiLing,ZHAO QiDong. Digital Soil Properties Mapping by Ensembling Soil-Environment Relationship and Machine Learning in Arid Regions[J]. Scientia Agricultura Sinica, 2020, 53(3): 563-573.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2020.03.009

https://www.chinaagrisci.com/CN/Y2020/V53/I3/563

图/表 11

图1

表1

数字土壤制图环境协变量"

编号 Number	数据来源 Data source	协变量定义 Covariable definition	简称 Abbreviation	计算公式 Formula	参考文献 Reference
1	DEM	高程 Elevation	Ele		[23]
2		坡度 Slope	Slo		[23]
3		坡向 Aspect	Asp		[23]
4		曲率 Curvature	Cur		[23]
5		剖面曲率 Profile curvature	PrCu		[23]
6		平面曲率 Plan curvature	PlCu		[23]
7		地形湿度指数 Topographic wetness index	TWI	ln（α/tanβ)	[23]
8	Landsat 8 OLI / TIRS	海岸波段 band 1 coastal	b1
9		蓝波段 Band 2 blue	b2
10		绿波段 Band 3 green	b3
11		红波段 Band 4 Red	b4
12		近红外波段 Band 5 near infrared	b5
13		短波红外1 Band 6 shortwave infrared 1	b6
14		短波红外2 Band 7 shortwave infrared 2	b7
15		增强型植被指数 Enhanced vegetation index	EVI	2.5[(NIR-R)/(NIR+6×R-7.5×R+1)]	[24]
16		差值植被指数 Difference vegetation index	DVI	NIR-R	[9]
17		归一化植被指数 Normalized difference vegetation index	NDVI	(NIR-R)/(NIR+R)	[9]
18		扩展增强型植被指数 Extended normalized difference vegetation index	ENDVI	(NIR+SWIR₂ -R)/(NIR+SWIR₂ +R)	[25]
19		调整土壤亮度植被指数 Modified soil adjusted vegetation index	MSAVI	[2NIR+1-((2NIR+1)²-8(NIR-R))^0.5]/2	[9]
20		强度指数1 Intensity index 1	Int1	(G+R)/2	[26]
21		强度指数2 Intensity index 2	Int2	(G+R+NIR)/2	[26]
22		盐分指数S1 Salinity index S1	S1	B/R	[27]
23		盐分指数S3 Salinity index S3	S3	(G×R)/B	[27]
24		盐分指数S5 Salinity index S5	S5	(B×R)/G	[27]
25		盐分指数S6 Salinity index S6	S6	(R×NIR)/G	[27]
26		盐分指数 Salinity index	SI	(B×R)^0.5	[27]
27		盐分指数1 Salinity index 1	SI1	(G×R)^0.5	[27]
28		盐分指数2 Salinity index 2	SI2	(G² + R² + NIR²)^0.5	[27]
29		盐分指数3 Salinity index 3	SI3	(R² + G²)^0.5	[27]
30		归一化盐分指数 Normalized difference salinity index	NDSI	(R-NIR)/(R+NIR)	[27]
31		综合光谱响应指数 Combined spectral response index	CoSRI	(B+G)/(R+NIR)×NDVI	[28]
32		地表温度 Land surface temperature	LST		[16]

表1

图2

图3

图4

表2

表3

图5

图6

图7

图8

参考文献 40

[1]	MA Y X, MINASNY B, WU C F . Mapping key soil properties to support agricultural production in Eastern China. Geoderma Regional, 2017,10:144-153.
[2]	杨琳, Sherif F, Sheldon H, 朱阿兴, 秦承志, 徐志刚. 基于土壤-环境关系的更新传统土壤图研究. 土壤学报, 2010,47(6):1039-1049.
	YANG L, SHERIF F, SHELDON H, ZHU A X, QIN C Z, XU Z G . Updating conventional soil maps using knowledge on soil- environment relationships extracted from the maps. Acta Pedologica Sinica, 2010,47(6):1039-1049. (in Chinese)
[3]	王幼奇, 白一茹, 赵云鹏 . 宁夏砂田小尺度土壤性质空间变异特征与肥力评价. 中国农业科学, 2016,49(23):4566-4575. DOI: 10.3864/j.issn.0578-1752.2016.23.009.
	WANG Y Q, BAI Y R, ZHAO Y P . Assessment of soil fertility and its spatial variability based on small scale in the gravel mulched field of NingXia. Scientia Agricultura Sinica, 2016,49(23):4566-4575. DOI: 10.3864/j.issn.0578-1752.2016.23.009. (in Chinese)
[4]	LAGACHERIE P, MCBRATNEY A B . Spatial soil information systems and spatial soil inference systems: perspectives for digital soil mapping. Developments in Soil Science, 2006,31:3-22.
[5]	ZHU A X, BAND L, VERTESSY R, DUTTON B . Derivation of soil properties using a soil land inference model (SoLIM). Soil Science Society of America Journal, 1997,61(2):523-533.
[6]	王飞, 杨胜天, 丁建丽, 魏阳, 葛翔宇, 梁静 . 环境敏感变量优选及机器学习算法预测绿洲土壤盐分. 农业工程学报, 2018,34(22):102-110. DOI: 10.11975/j.issn.1002-6819.2018.22.013.
	WANG F, YANG S T, DING J L, WEI Y, GE X Y, LIANG J . Environmental sensitive variable optimization and machine learning algorithm using in soil salt prediction at oasis. Transactions of the Chinese Society of Agricultural Engineering, 2018,34(22):102-110. DOI: 10.11975/j.issn.1002-6819.2018.22.013. (in Chinese)
[7]	ZHANG H, WU P B, YIN A J, YANG X H, ZHANG M, GAO C . Prediction of soil organic carbon in an intensively managed reclamation zone of Eastern China: A comparison of Multiple Linear Regressions and the Random Forest model. Science of the Total Environment, 2017,592:704-713.
[8]	BODAGHABADI B M, MARTÍNEZ-CASASNOVAS J, SALEHI M H, MOHAMMADI J, BORUJENI E I, TOOMANIAN N, GANDOMKAR A. Digital soil mapping using Artificial Neural Networks and terrain-related attributes. Pedosphere, 2015,25(4):580-591.
[9]	MAHMOUDABADI E, KARIMI A, HAGHNIA G H, SEPEHR A . Digital soil mapping using remote sensing indices, terrain attributes, and vegetation features in the rangelands of northeastern Iran. Environmental Monitoring Assessment, 2017,189(10):500.
[10]	鲁如坤 . 土壤农业化学分析方法. 北京: 中国农业科技出版社, 2000.
	LU R K. Methods for Soil Agrochemistry Analysis. Beijing: China Agricultural Science and Technology Press, 2000. ( in Chinese)
[11]	ZHOU Y, HARTEMINK A E, SHI Z, LIANG Z Z, LU Y L . Land use and climate change effects on soil organic carbon in North and Northeast China. Science of the Total Environment, 2019,647:1230-1238.
[12]	ABDEL-KADER F H . Digital soil mapping at pilot sites in the northwest coast of Egypt: A Multinomial Logistic Regression approach. The Egyptian Journal of Remote Sensing and Space Science, 2011,14(1):29-40.
[13]	PENG J, BISWAS A, JIANG Q S, ZHAO R Y, HU J, HU B F, SHI Z . Estimating soil salinity from remote sensing and terrain data in southern Xinjiang Province, China. Geoderma, 2019,337:1309-1319.
[14]	朱阿兴 . 精细数字土壤普查模型与方法. 北京: 科学出版社, 2008: 21-57.
	ZHU A X. Model and Method of Fine Digital Soil Survey. Beijing: Science Press, 2008: 21-57. (in Chinese)
[15]	MEHNATKESH A, AYOUBI S, JALALIAN A, SAHRAWAT K L . Relationships between soil depth and terrain attributes in a semi arid hilly region in western Iran. Journal of Mountain Science, 2013,10(1):163-172.
[16]	QIN Z H, KARNIELI A, BERLINER P . A mono-window algorithm for retrieving land surface temperature from Landsat TM data and its application to the Israel-Egypt border region. International Journal of Remote Sensing, 2001,22(18):3719-3746.
[17]	LIU L F, JI M, BUCHROITHNER M . Combining partial least squares and the gradient-boosting method for soil property retrieval using visible Near-Infrared shortwave infrared spectra. Remote Sensing, 2017,9(12):1299.
[18]	GE X Y, WANG J Z, DING J L, CAO X Y, ZHANG Z P, LIU J, LI X H . Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring. PeerJ, 2019,7:e6926.
[19]	DING J L, YANG A X, WANG J Z, SAGAN V, YU D L . Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy. PeerJ, 2018,6:e5714.
[20]	CORETEAM R . R:A language and environment for statistical computing. Computing, 2015,14:12-21.
[21]	LAWRENCE I, LIN K . A concordance correlation coefficient to evaluate reproducibility. Biometrics, 1989,45(1):255-268.
[22]	WANG J Z, DING J L, ABULIMITI A, CAI L H . Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS-NIR) spectroscopy, Ebinur Lake Wetland, Northwest China. PeerJ, 2018,6:e4703.
[23]	ZERAATPISHEH M, AYOUBI S, JAFARI A, TAJIK S, FINKE P . Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran. Geoderma, 2019,338:445-452.
[24]	LOBELL D, LESCH S, CORWIN D, ULMER M, ANDERSON K, POTTS D, DOOLITTLE J, MATOS M, BALTES M . Regional-scale assessment of soil salinity in the Red River Valley using multi-year MODIS EVI and NDVI. Journal of Environmental Quality, 2010,39(1):35-41.
[25]	陈红艳, 赵庚星, 陈敬春, 王瑞燕, 高明秀 . 基于改进植被指数的黄河口区盐渍土盐分遥感反演. 农业工程学报, 2015,31(5):107-114. DOI: 10.3969/j.issn.1002-6819.2015.05.016.
	CHEN H Y, ZHAO G X, CHEN J C, WANG R Y, GAO M X . Remote sensing inversion of saline soil salinity based on modified vegetation index in estuary area of Yellow River. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(5):107-114. DOI: 10.3969/j.issn.1002-6819.2015.05.016. (in Chinese)
[26]	TRIKI FOURATI H, BOUAZIZ M, BENZINA M, BOUAZIZ S . Modeling of soil salinity within a semi-arid region using spectral analysis. Arabian Journal of Geosciences, 2015,8(12):11175-11182.
[27]	ALLBED A, KUMAR L, ALDAKHEEL Y Y . Assessing soil salinity using soil salinity and vegetation indices derived from IKONOS high-spatial resolution imageries: Applications in a date palm dominated region. Geoderma, 2014,230:1-8.
[28]	MENG L, ZHOU S W, ZHANG H, BI X L . Estimating soil salinity in different landscapes of the Yellow River Delta through Landsat OLI/TIRS and ETM+ Data. Journal of Coastal Conservation, 2016,20(4):271-279.
[29]	GERSHMAN S J, NIV Y . Perceptual estimation obeys Occam's razor. Frontiers in Psychology, 2013,4:623.
[30]	古丽波斯坦·巴图 . 渭—库绿洲不同土地利用方式下土壤理化性质分析[D]. 乌鲁木齐: 新疆大学, 2018.
	GULIBOSITAN-BATU . Analysis of soil physical and chemical properties under different land use/land cover in Weigan and Kuqa rivers delta oasis[D]. Urumqi: Xinjiang University, 2018. ( in Chinese)
[31]	谷海斌 . 灌区尺度土壤特性空间变异性研究[D]. 乌鲁木齐: 新疆农业大学, 2011.
	GU H B . Research on spatial variation of properties in irrigation area scale[D]. Urumqi: Xinjiang Agricultural University, 2011. ( in Chinese)
[32]	王飞, 杨胜天, 魏阳, 杨晓东, 丁建丽 . 基于RF和SGT算法的子区优先建模对绿洲尺度土壤盐度预测精度的影响. 中国农业科学, 2018,51(24):4659-4676. DOI: 10.3864/j. issn.0578-1752.2018.24. 007.
	WANG F, YANG S T, WEI Y, YANG X D, DING J L . Influence of sub-region priority modeling constructed by random forest and stochastic gradient treeboost on the accuracy of soil salinity prediction in oasis scale. Scientia Agricultura Sinica, 2018,51(24):4659-4676. DOI: 10.3864/j.issn.0578-1752.2018.24.007.(in Chinese)
[33]	DING J L, YU D L . Monitoring and evaluating spatial variability of soil salinity in dry and wet seasons in the Werigan-Kuqa Oasis, China, using remote sensing and electromagnetic induction instruments. Geoderma, 2014,235:316-322.
[34]	BRUBAKER S, JONES A, LEWIS D, FRANK K . Soil properties associated with landscape position. Soil Science Society of America Journal, 1993,57(1):235-239.
[35]	FALAHATKAR S, HOSSEINI S M, AYOUBI S, SALMANMAHINY A . Predicting soil organic carbon density using auxiliary environmental variables in Northern Iran. Archives of Agronomy Soil Science, 2016,62(3):375-393.
[36]	葛翔宇, 丁建丽, 王敬哲, 王飞, 蔡亮红, 孙慧兰 . 基于竞争适应重加权采样算法耦合机器学习的土壤含水量估算. 光学学报, 2018,38(10):393-400. DOI: 10.3788/AOS201838.1030001.
	GE X Y, DING J L, WANG J Z, WANG F, CAI L H, SUN H L . Estimation of soil moisture based on CARS algorithm coupled with machine learning. Acta Optica Sinca, 2018,38(10):393-400. DOI: 10.3788/AOS201838.1030001. (in Chinese)
[37]	CHEN S C, LIANG Z Z, WEBSTER R, ZHANG G L, ZHOU Y, TENG H F, HU B F, ARROUAYS D, SHI Z . A high-resolution map of soil pH in China made by hybrid modelling of sparse soil data and environmental covariates and its implications for pollution. Science of the Total Environment, 2019,655:273-283.
[38]	彭杰, 刘焕军, 史舟, 向红英, 迟春明 . 盐渍化土壤光谱特征的区域异质性及盐分反演. 农业工程学报, 2014,30(17):167-174. DOI: 10.3969/j.issn.1002-6819.2014.17.022.
	PENG J, LIU H J, SHI Z, XIANG H Y, CHI C M . Regional heterogeneity of hyperspectral characteristics of salt-affected soil and salinity inversion. Transactions of the Chinese Society of Agricultural Engineering, 2014,30(17):167-174. DOI: 10.3969/j.issn.1002-6819. 2014.17.022. (in Chinese)
[39]	WANG H F, CHEN Y W, ZHANG Z T, CHEN H R, LI X W, WANG M X, CHAI H Y . Quantitatively estimating main soil water-soluble salt ions content based on visible-near infrared wavelength selected using GC, SR and VIP. PeerJ, 2019,7:e6310.
[40]	MOSLEH Z, SALEHI M H, JAFARI A, BORUJENI I E, MEHNATKESH A . The effectiveness of digital soil mapping to predict soil properties over low-relief areas. Environmental Monitoring Assessment, 2016,188(3):195.

土壤属性 Soil Attribute	模型 Model	建模集 Calibration			验证集 Validation
土壤属性 Soil Attribute	模型 Model	R²	ρ_c	RMSE	R²	ρ_c	RMSE
pH	RF	0.7929	0.7786	0.1681	0.6779	0.6084	0.2182
	Cubist	0.5182	0.6356	0.2308	0.4383	0.5805	0.2252
	Bagging	0.6389	0.6409	0.2092	0.5829	0.6159	0.2214
	MLR	0.4154	0.4559	0.2971	0.3004	0.4683	0.2445
SSC	RF	0.9067	0.9219	2.6680	0.7945	0.8377	3.1803
	Cubist	0.8820	0.9237	2.9190	0.7135	0.6194	7.5771
	Bagging	0.7417	0.8331	4.2156	0.6974	0.7791	3.9743
	MLR	0.6478	0.7687	4.0600	0.5050	0.6670	5.7829
SOM	RF	0.8565	0.7872	3.3215	0.7472	0.7009	3.5456
	Cubist	0.5204	0.5774	4.4070	0.4795	0.4305	5.4758
	Bagging	0.7653	0.7551	3.6085	0.6402	0.5494	4.2667
	MLR	0.3835	0.5559	5.0483	0.3250	0.5151	4.8424