自然资源学报 ›› 2019, Vol. 34 ›› Issue (12): 2717-2731.doi: 10.31497/zrzyxb.20191218
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
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:
WANG Hao1,2(), LUO Ge-ping1,2,3(
), WANG Wei-sheng1, PACHIKIN Konstantin4, LI Yao-ming1, ZHENG Hong-wei1,2, HU Wei-jie1
Received:
2019-05-25
Revised:
2019-09-09
Online:
2019-12-28
Published:
2019-12-28
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。
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.
表1
锡尔河中下游农田2017年生长季SMC研究所需数据"
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 |
表2
锡尔河流域中下游SMC影响因子"
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 |
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 |
表3
锡尔河流域中下游SMC与影响因子相关性分析"
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 |
表4
不同反演组合的SMC反演精度统计"
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 | |||||
---|---|---|---|---|---|---|---|---|
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 |
表5
机器学习结合遥感数据的SMC反演对比"
研究 | 数据源 | 建模因子 | 方法 | RMSE | 研究区 |
---|---|---|---|---|---|
Pasolli等[ | RADARSAT-2 | HH或VV单个因子 | SVR | 0.0485 m3/m3 | 意大利 |
Pasolli等[ | RADARSAT-2 | HH或VV单个因子 | SVR | 5.38%~6.85% | 意大利 |
Santi等[ | AMSR2、Envisat等 | VV+NDVI或HH+NDVI双因子 | ANN | 0.023~0.052 m3/m3 | 巴西 |
Paloscia等[ | 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[ | Sentinel-1、Landsat8 | NDVI、HV等4个因子 | ANN | 0.022~0.058 m3/m3 | 希腊 |
Zeng等[ | 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[ | 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[ | 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 |
[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. |
[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. |
|