基于多源遥感数据的锡尔河中下游农田土壤水分反演

doi:10.31497/zrzyxb.20191218

自然资源学报 ›› 2019, Vol. 34 ›› Issue (12): 2717-2731.doi: 10.31497/zrzyxb.20191218

基于多源遥感数据的锡尔河中下游农田土壤水分反演

王浩^1,²(), 罗格平^1,^2,³(), 王伟胜¹, PACHIKINKonstantin⁴, 李耀明¹, 郑宏伟^1,², 胡伟杰¹

1. 中国科学院新疆生态与地理研究所荒漠与绿洲国家重点实验室,乌鲁木齐 830011
2. 中国科学院大学,北京 100049
3. 中国科学院中亚生态与环境研究中心,乌鲁木齐 830011
4. 哈萨克斯坦土壤科学与农业化学研究所,哈萨克斯坦阿拉木图 050060

收稿日期:2019-05-25 修回日期:2019-09-09 出版日期:2019-12-28 发布日期:2019-12-28
作者简介:
作者简介：王浩（1992- ）,男,贵州贵阳人,硕士,主要从事遥感与地理信息系统研究。E-mail: wangh_xjb@foxmail.com
基金资助:
国家自然基金项目（41877012）;中国科学院特色研究所项目（TSS-2015-014-FW-1-3）

Inversion of soil moisture content in the farmland in middle and lower reaches of Syr Darya River Basin based on multi-source remotely sensed data

WANG Hao^1,²(), LUO Ge-ping^1,^2,³(), WANG Wei-sheng¹, PACHIKIN Konstantin⁴, LI Yao-ming¹, ZHENG Hong-wei^1,², HU Wei-jie¹

1. State Key Laboratory of Desert and Oasis Ecology, Xinjiang Institute of Ecology and Geography, CAS, Urumqi 830011, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. Central Asian Center for Ecology and Environmental Research, CAS, Urumqi 830011, China
4. The Kazakh Scientific Research Institute of Soil Science and Agriculture Chemistry, Almaty 050060, Kazakhstan

Received:2019-05-25 Revised:2019-09-09 Online:2019-12-28 Published:2019-12-28

摘要/Abstract

摘要：

机器学习结合多源遥感数据反演土壤水分含量（SMC）是目前SMC研究的热点,因较少考虑温度、蒸散等重要SMC影响因子,反演结果存在一定的不确定性。利用Sentinel-1影像、MODIS产品和SRTM数据,提取雷达后向散射系数等32个SMC影响因子,经相关分析选择27个显著的SMC影响因子（P<0.05）作为反演因子,并设计三组因子组合。这三组因子组合分别与随机森林、支持向量回归、BP神经网络三种机器学习方法结合,发现基于随机森林结合所有因子的方案,其SMC反演精度最高,该组合均方根误差RMSE为0.039 m³/m³,将该方案被用于反演2017年生长季锡尔河流域中下游平原区农田SMC。结果表明：从上部至下部SMC总体呈逐渐增加的态势,但存在显著时空差异,春季和秋季SMC较高而夏季较低。SMC差异主要由土壤质地、热量条件和地表植被状况差异引起。春季平原区下部农田SMC要高于上部,SMC的主控因子是土壤质地和地表植被状况;在夏季,土壤水分的主控因子是热量条件,农田灌溉弥补了热量条件差异对土壤水分的影响,导致空间上平原上部和下部土壤SMC空间差异不显著;秋季SMC的主控因子植被状况抵消地表温度和土壤质地差异对SMC的影响,使得秋季SMC空间差异不显著。本文采用的研究方法在一定程度上克服了因考虑SMC影响因子不足而获取更高SMC精度的限制。

关键词: 土壤水分含量, 机器学习, 锡尔河流域中下游, Sentinel-1, MODIS, SRTM

Abstract:

The use of machine learning method to estimate Soil Moisture Content (SMC) from multi-source remotely sensed data is a hot topic in the SMC inversion research. However, taking no account of the important variables of SMC in the ML method makes the SMC results uncertain. The Sentinel-1 and MODIS image products and the STRM data were obtained and used for extracting 32 SMC variables, such as backscattering coefficient, vegetation index, surface temperature and evapotranspiration. A total of 27 significant (P<0.05) SMC variables were selected as input parameters referring to the correlation analysis result, and the input parameters were assigned to 3 groups. Random forest, Support vector regression and Back Propagation Neural Network were tested with 3 groups parameters. The Random forest with the group with all input parameters showed the best estimation accuracy, with the RMSE being 0.039 m³/m³, and it was used for the inversion of SMC in the farmland in the middle and lower reaches of Syr Darya River Basin during the growing season of 2017. The retrieved SMC gradually increased in the middle to the lower reaches during the growing season, but there were significant temporal and spatial differences: SMC in spring and autumn was higher than that in summer. These differences were mainly caused by seasonal or spatial differences in soil texture, heat conditions (temperature) and vegetation cover. In spring, SMC in the lower part of the plain is higher than that in the upper part, and the main SMC controlling factors were soil texture and vegetation cover. In summer, the main SMC controlling factors were heat condition. Irrigation compensated for the influence of heat condition difference, resulting in no significant spatial difference of SMC between upper and lower parts of the plain. The main SMC controlling factors in autumn were soil texture and heat conditions, the influence of surface temperature compensated for the influence of soil texture on SMC, as a result, there was no significant spatial difference of SMC in autumn. With regard to overcoming the limitation of taking no account of the important variables in estimating SMC, the research method adopted in this study improves the retrieved SMC accuracy to a large extent.

Key words: soil moisture content, machine learning, middle and lower reaches of Syr Darya River Basin, Sentinel-1, MODIS, SRTM

王浩, 罗格平, 王伟胜, PACHIKINKonstantin, 李耀明, 郑宏伟, 胡伟杰. 基于多源遥感数据的锡尔河中下游农田土壤水分反演[J]. 自然资源学报, 2019, 34(12): 2717-2731.

WANG Hao, LUO Ge-ping, WANG Wei-sheng, PACHIKIN Konstantin, LI Yao-ming, ZHENG Hong-wei, HU Wei-jie. Inversion of soil moisture content in the farmland in middle and lower reaches of Syr Darya River Basin based on multi-source remotely sensed data[J]. JOURNAL OF NATURAL RESOURCES, 2019, 34(12): 2717-2731.

图/表 13

图1

图2

表1

表2

表3

表4

图3

图4

图5

图6

图7

图8

表5

参考文献 37

[1]	LEGATES D R, MAHMOOD R, LEVIA D F, et al.Soil moisture: A central and unifying theme in physical geography. Progress in Physical Geography, 2011, 35(1): 65-86.
[2]	KANG J, JIN R, LI X, et al.High spatio-temporal resolution mapping of soil moisture by integrating wireless sensor network observations and MODIS apparent thermal inertia in the Babao River Basin, China. Remote Sensing of Environment, 2017, 191(sC): 232-245.
[3]	ZHU W, JIA S, LYU A.A time domain solution of the Modified Temperature Vegetation Dryness Index (MTVDI) for continuous soil moisture monitoring. Remote Sensing of Environment, 2017, 200: 1-17.
[4]	SANTI E, PALOSCIA S, PETTINATO S, et al.Robust assessment of an operational algorithm for the retrieval of soil moisture from AMSR-E data in central Italy. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(6): 2478-2492.
[5]	ZENG J, LI Z, CHEN Q, et al.Evaluation of remotely sensed and reanalysis soil moisture products over the Tibetan Plateau using in-situ observations. Remote Sensing of Environment, 2015, 163: 91-110.
[6]	KIM S, LIU Y Y, JOHNSON F M, et al.A global comparison of alternate AMSR2 soil moisture products: Why do they differ. Remote Sensing of Environment, 2015, 161: 43-62.
[7]	COLLIANDER A, JACKSON T, BINDLISH R, et al.Validation of SMAP surface soil moisture products with core validation sites. Remote Sensing of Environment, 2017, 191: 215-231.
[8]	ZENG J, CHEN K-S, BI H, et al.Radar response of off-specular bistatic scattering to soil moisture and surface roughness at L-band. IEEE Geoscience and Remote Sensing Letters, 2016, 13(12): 1945-1949.
[9]	XING M, QUAN X, LI X, et al.An extended approach for biomass estimation in a mixed vegetation area using ASAR and TM data. Photogrammetric Engineering & Remote Sensing, 2014, 80(5): 429-438.
[10]	KWEON S-K, OH Y.A modified water-cloud model with leaf angle parameters for microwave backscattering from agricultural fields. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(5): 2802-2809.
[11]	MERLIN O, AL BITAR A, WALKER J P, et al.An improved algorithm for disaggregating microwave-derived soil moisture based on red, near-infrared and thermal-infrared data. Remote Sensing of Environment, 2010, 114(10): 2305-2316.
[12]	PENG Z, JIANLI D, FEI W, et al.Retrieval methods of soil water content in vegetation covering areas based on multi-source remote sensing data. Journal of Remote Sensing, 2010, 14(5): 966-981.
[13]	TEMIMI M, LECONTE R, CHAOUCH N, et al.A combination of remote sensing data and topographic attributes for the spatial and temporal monitoring of soil wetness. Journal of Hydrology, 2010, 388(1): 28-40.
[14]	PALOSCIA S, PETTINATO S, SANTI E, et al.Soil moisture mapping using Sentinel-1 images: Algorithm and preliminary validation. Remote Sensing of Environment, 2013, 134: 234-248.
[15]	ALEXAKIS D D, MEXIS F-D K, VOZINAKI A-E K, et al. Soil moisture content estimation based on Sentinel-1 and auxiliary earth observation products. A hydrological approach. Sensors, 2017, 17(6): 1455, Doi: 10.3390/s17061455.
[16]	ÖZERDEM M S, ACAR E, EKINCI R.Soil moisture estimation over vegetated agricultural areas: Tigris Basin, Turkey from Radarsat-2 data by Polarimetric Decomposition Models and a Generalized Regression Neural Network. Remote Sensing, 2017, 9(4): 395, Doi: 10.3390/rs9040395.
[17]	PASOLLI L, NOTARNICOLA C, BERTOLDI G, et al.Soil moisture monitoring in mountain areas by using high-resolution SAR images: Results from a feasibility study. European Journal of Soil Science, 2014, 65(6): 852-864.
[18]	STAMENKOVIC J, FERRAZZOLI P, GUERRIERO L, et al.Crop backscatter modeling and soil moisture estimation with support vector regression. Proceedings of the Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International. Quebec City, QC, Canada. 2014: 3228-3231.
[19]	ZHANG X, CHEN B, FAN H, et al.The potential use of multi-band SAR data for soil moisture retrieval over bare agricultural areas: Hebei, China. Remote Sensing, 2015, 8(1): 7, Doi: 10.3390/rs8010007.
[20]	KE Y, IM J, PARK S, et al.Downscaling of MODIS one kilometer evapotranspiration using Landsat-8 data and machine learning approaches. Remote Sensing, 2016, 8(3): 215, Doi: 10.3390/rs8030215.
[21]	HASSAN-ESFAHANI L, TORRES-RUA A, JENSEN A, et al.Assessment of surface soil moisture using high-resolution multi-spectral imagery and artificial neural networks. Remote Sensing, 2015, 7(3): 2627-2646.
[22]	STAMENKOVIĆ J, FERRAZZOLI P, GUERRIERO L, et al.Joining a discrete radiative transfer Model and a kernel retrieval algorithm for soil Moisture estimation From SAR Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(7): 3463-3475.
[23]	PASOLLI L, NOTARNICOLA C, BRUZZONE L.Multi-objective parameter optimization in support vector regression: General formulation and application to the retrieval of soil moisture from remote sensing data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(5): 1495-1508.
[24]	SANTI E, PALOSCIA S, PETTINATO S, et al.Application of artificial neural networks for the soil moisture retrieval from active and passive microwave spaceborne sensors. International journal of applied earth observation and geoinformation, 2016, 48: 61-73.
[25]	GORELICK N, HANCHER M, DIXON M, et al.Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 2017, 202: 18-27.
[26]	ATTEMA E, ULABY F T.Vegetation modeled as a water cloud. Radio Science, 1978, 13(2): 357-364.
[27]	BREIMAN L.Random forests. Machine Learning, 2001, 45(1): 5-32.
[28]	CORTES C, VAPNIK V.Support-vector networks. Machine Learning, 1995, 20(3): 273-297.
[29]	VOUNDI NKANA J, TONYE J.Assessment of certain soil properties related to different land-use systems in the Kaya watershed of the humid forest zone of Cameroon. Land degradation & Development, 2003, 14(1): 57-67.
[30]	BREIMAN L.Random forests. Machine Learning, 2001, 45(1): 5-32.
[31]	SCHöLKOPF B, SMOLA A J, WILLIAMSON R C, et al. New support vector algorithms. Neural Computation, 2000, 12(5): 1207-1245.
[32]	RUMELHART D E, HINTON G E, WILLIAMS R J.Learning representations by back-propagating errors. Nature, 1986, 323(9): 533-536.
[33]	王修康, 戚兴超, 刘艳丽, 等. 泰山山前平原三种土地利用方式下土壤结构特征及其对土壤持水性的影响. 自然资源学报, 2018, 33(1): 63-74.
	[WANG X K, QI X C, LIU Y L, et al.Soil Structure and its effect on soil water holding property under three land use patterns in piedmont plain of Mountain Tai. Journal of Natural Resources, 2018, 33(1): 63-74.]
[34]	ZHOU H, CHEN Y, LI W.Soil properties and their spatial pattern in an oasis on the lower reaches of the Tarim River, Northwest China. Agricultural water management, 2010, 97(11): 1915-1922.
[35]	王学春, 李军, 王红妮, 等. 黄土高原冬小麦田土壤水分与小麦产量对降水和气温变化响应的模拟研究. 自然资源学报, 2017, 32(8): 1398-410.
	[WANG X C, LI J, WANG X N, et al.Simulation of the response of soil water in winter wheat field and winter wheat yield to rainfall and temperature change on the Loess Plateau. Journal of Natural Resources, 2017, 32(8): 1398-4102.]
[36]	PASOLLI L, NOTARNICOLA C, BRUZZONE L, et al.Polarimetric RADARSAT-2 imagery for soil moisture retrieval in alpine areas. Canadian Journal of Remote Sensing, 2012, 37(5): 535-547.
[37]	ZENG W, XU C, HUANG J, et al.Predicting near-surface moisture content of saline soils from near-infrared reflectance spectra with a modified Gaussian model. Soil Science Society of America Journal, 2016, 80(6): 1496-1506.

数据	空间分辨率/m	时间分辨率/d	来源	用途	时间
Sentinel-1 SAR	5×20	12	ESA(https://scihub.co pernicus.eu)	SMC影响因子的时空数据	2017年4-10月
MOD09GQ地表反射率 MOD11A2 v4地表温度 MOD13Q1v6植被指数 MYD13Q1.v6植被指数 MCD15A3H叶面积指数 MOD16A2 v6蒸散发 MCD43A3地表反照率	250 1000 250 250 500 500 500	1 8 16 16 4 8 1	NASA(https://lpdaac.usgs.gov)		2017年4-10月
SRTM v4高程数据	90		CRIAR(http://srtmcsi.cgiar.org)
SMC实测数据			中国科学院新疆生地所	模型训练与反演结果验证	2017年9月18-20日

SMC影响因子类型	名称	影响因子
微波物理量	后向散射系数（backscattering coefficient,BC）	BC均值/最大值/最小值
植被变量	归一化植被指数（Normalized differential vegetation index,NDVI）	NDVI均值/最大值/最小值
	增强型植被指数（Enhanced Vegetation Index,EVI）	EVI均值/最大值/最小值
	土壤调整植被指（Soil Adjusted Vegetation Index,SAVI）	SAVI均值/最大值/最小值
	叶面积指数（leaf Area Index,LAI）	LAI均值/最大值/最小值
温度变量	地表温度（Surface temperature,LST）	LST均值/最大值/最小值
蒸散发变量	蒸散发（Evapotranspiration,ET）	ET均值/最大值/最小值/累积值
下垫面反射特性变量	可见光范围地表反照率（Albedo in VIS,AIV）	AIV均值/最大值/最小值
下垫面反射特性变量	近红外范围地表反照率（Albedo in NIR,AIN）	AIN均值/最大值/最小值
地形变量	高程（Elevation）坡度（Slope）坡向（Aspect）地面粗糙度（Roughness）	高程/坡度/坡向/地面粗糙度

植被变量			温度或水分变量和微波物理量			地形变量和下垫面反射特性变量
	r²	P		r²	P		r²	P
NDVI平均值	0.615	0.006	LST平均值	-0.385	0.034	AIV平均值	0.673	0.002
NDVI最大值	0.584	0.009	LST最大值	-0.757	0.000	AIV最大值	0.723	0.001
NDVI最小值	0.584	0.009	LST最小值	-0.492	0.026	AIV最小值	0.701	0.001
SAVI平均值	0.358	0.042	ET平均值	0.100	0.356	AIN平均值	0.698	0.001
SAVI最大值	0.354	0.047	ET累积值	-0.328	0.050	AIN最大值	0.726	0.001
SAVI最小值	0.373	0.039	ET最小值	-0.334	0.048	AIN最小值	0.752	0.000
LAI平均值	0.183	0.197	ET最大值	0.394	0.031	Elevation高程	-0.682	0.002
LAI最大值	0.165	0.270	BS平均值	0.437	0.031	Aspect坡向	0.556	0.013
LAI最小值	0.737	0.001	BS最大值	0.379	0.037	Slope坡度	-0.238	0.188
EVI平均值	0.380	0.032	BS最小值	0.366	0.040	Rough地面粗糙度	-0.242	0.184
EVI最大值	0.526	0.018
EVI最小值	0.526	0.018

机器学习模型	试验组合方案	基于训练样本的精度统计				基于验证样本的精度统计
机器学习模型	试验组合方案	R²	RMSE/(m³/m³)	MAPE/%		R²	RMSE/(m³/m³)	MAPE/%
RF	VV	0.69	0.041	11.2		0.52	0.065	17.5
	NDVI+VV	0.78	0.038	10.6		0.59	0.054	13.5
	所有因子	0.80	0.035	10.3		0.68	0.039	10.5
SVR	VV	0.71	0.042	11.5		0.53	0.056	13.8
	NDVI+VV	0.75	0.037	11.3		0.55		0.059	13.7
	所有因子	0.78	0.037	10.7	0.64		0.043	10.9
BPNN	VV	0.69	0.042	11.4	0.49	0.086	18.4
	NDVI+VV	0.73	0.039	10.9	0.54		0.059	14.1
	所有因子	0.74	0.038	11.0	0.59		0.052	11.9

研究	数据源	建模因子	方法	RMSE	研究区
Pasolli等^[36]	RADARSAT-2	HH或VV单个因子	SVR	0.0485 m³/m³	意大利
Pasolli等^[17]	RADARSAT-2	HH或VV单个因子	SVR	5.38%~6.85%	意大利
Santi等^[24]	AMSR2、Envisat等	VV+NDVI或HH+NDVI双因子	ANN	0.023~0.052 m³/m³	巴西
Paloscia等^[14]	Sentinel-1、MODIS等	VV+NDVI或者HH+NDVI双因子	ANN	2.32%~5.47%	意大利等 (部分农田)
Alexakis等^[15]	Sentinel-1、Landsat8	NDVI、HV等4个因子	ANN	0.022~0.058 m³/m³	希腊
Zeng等^[37]	土样光谱信息	热红外波段相关的3~4个因子	ANN	0.017~0.032 m³/m³	中国内蒙(农田)
Hassan等^[21]	AggieAir 无人机高光谱影像	NDVI等10个因子	ANN	2%	美国犹他州 (农田)
ÖZerdem等^[16]	RADARSAT-2	VV等10个因子	ANN	2.84%~9.76%	土耳其(农田)
本文	Sentinel-1、MODIS等	NDVI均值等27个因子	RF	0.039 m³/m³	锡尔河中下游绿洲农田

基于多源遥感数据的锡尔河中下游农田土壤水分反演

Inversion of soil moisture content in the farmland in middle and lower reaches of Syr Darya River Basin based on multi-source remotely sensed data

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 37

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	崔喆, 沈丽珍, 刘子慎, 汪侠. 基于公司行业结构的哈尔滨跨区域联系网络分析[J]. 自然资源学报, 2020, 35(7): 1672-1685.
[2]	刘文斌, 陶建斌, 徐猛, 陈瑞卿, 郭洋. 基于人工神经网络多源数据融合的子像元冬油菜提取——以两湖平原为例[J]. 自然资源学报, 2019, 34(5): 1079-1092.
[3]	贺敏, 宋立生, 王展鹏, 辜清, 王大菊, 郭博. 基于多源数据的干旱监测指数对比研究——以西南地区为例[J]. 自然资源学报, 2018, 33(7): 1257-1269.
[4]	吕鑫, 王卷乐, 康海军, 韩雪华. 基于遥感估产的2006—2015年青海果洛与玉树地区草畜平衡分析[J]. 自然资源学报, 2018, 33(10): 1821-1832.
[5]	王凤杰, 冯文兰, 扎西央宗, 牛晓俊, 刘志红, 王永前. 基于FY-3A/VIRR和TERRA/MODIS数据藏北干旱监测对比[J]. 自然资源学报, 2017, 32(7): 1229-1239.
[6]	姜艳阳, 王文, 周正昊. MODIS MOD16蒸散发产品在中国流域的质量评估[J]. 自然资源学报, 2017, 32(3): 517-528.
[7]	朱林富, 谢世友, 杨华, 马明国. 基于MODIS EVI的重庆植被覆盖变化的地形效应[J]. 自然资源学报, 2017, 32(12): 2023-2033.
[8]	向海燕, 罗红霞, 刘光鹏, 杨任飞, 雷茜, 程玉丝, 陈婧祎. 基于Sentinel-1A极化SAR数据与面向对象方法的山区地表覆被分类[J]. 自然资源学报, 2017, 32(12): 2136-2148.
[9]	吕鑫, 王卷乐, 康海军, 赵强, 韩雪华, 王玉洁. 基于MODIS NPP的2006—2015年三江源区产草量时空变化研究[J]. 自然资源学报, 2017, 32(11): 1857-1868.
[10]	郭昱杉, 刘庆生, 刘高焕, 黄翀. 基于MODIS时序NDVI主要农作物种植信息提取研究[J]. 自然资源学报, 2017, 32(10): 1808-1818.
[11]	徐春海, 李忠勤, 王飞腾, 王林. 基于LiDAR、SRTM DEM的祁连山黑河流域十一冰川2000—2012年物质平衡估算[J]. 自然资源学报, 2017, 32(1): 88-100.
[12]	张静怡, 卢晓宁, 洪佳, 孟成真. 2000—2014年四川省气溶胶时空格局及其驱动因子定量研究[J]. 自然资源学报, 2016, 31(9): 1514-1525.
[13]	杨存建, 周其林, 任小兰, 程武学, 王琴. 基于多时相MODIS数据的四川省森林植被类型信息提取[J]. 自然资源学报, 2014, 29(3): 507-515.
[14]	陈燕丽, 罗永明, 莫伟华, 莫建飞, 黄永璘, 丁美花. MODIS NDVI与MODIS EVI对气候因子响应差异[J]. 自然资源学报, 2014, 29(10): 1802-1812.
[15]	李海亮, 罗微, 李世池, 戴声佩, 刘海清. 基于遥感信息和净初级生产力的天然橡胶估产模型[J]. 自然资源学报, 2012, 27(9): 1610-1621.