Soil salt content estimation in the Yellow River delta with satellite hyperspectral data

被引:10
作者
Weng, Yongling [4 ]
Gong, Peng [1 ,2 ,3 ]
Zhu, Zhiliang [5 ]
机构
[1] Chinese Acad Sci, Inst Remote Sensing Applicat, State Key Lab Remote Sensing Sci, Beijing 100101, Peoples R China
[2] Beijing Normal Univ, Beijing 100101, Peoples R China
[3] Univ Calif Berkeley, Dept Environm Sci Policy & Management, Berkeley, CA 94720 USA
[4] Southeast Univ, Coll Transportat, Dept Surveying & Mapping Engn, Nanjing 210096, Peoples R China
[5] US Geol Survey, EROS Data Ctr, Sioux Falls, SD 57198 USA
关键词
D O I
暂无
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Soil salinization is one of the most common land degradation processes and is a severe environmental hazard. The primary objective of this study is to investigate the potential of predicting salt content in soils with hyperspectral data acquired with EO-1 Hyperion. Both partial least-squares regression (PLSR) and conventional multiple linear regression (MLR), such as stepwise regression (SWR), were tested as the prediction model. PLSR is commonly used to overcome the problem caused by high-dimensional and correlated predictors. Chemical analysis of 95 samples collected from the top layer of soils in the Yellow River delta area shows that salt content was high on average, and the dominant chemicals in the saline soil were NaCl and MgCl2. Multivariate models were established between soil contents and hyperspectral data. Our results indicate that the PLSR technique with laboratory spectral data has a strong prediction capacity. Spectral bands at 1487-1527, 1971-1991, 2032-2092, and 2163-2355 nm possessed large absolute values of regression coefficients, with the largest coefficient at 2203 nm. We obtained a root mean squared error (RMSE) for calibration (with 61 samples) of RMSEC = 0.753 (R-2 = 0.893) and a root mean squared error for validation (with 30 samples) of RMSEV = 0.574. The prediction model was applied on a pixel-by-pixel basis to a Hyperion reflectance image to yield a quantitative surface distribution map of soil salt content. The result was validated successfully from 38 sampling points. We obtained an RMSE estimate of 1.037 (R-2 = 0.784) for the soil salt content map derived by the PLSR model. The salinity map derived from the SWR model shows that the predicted value is higher than the true value. These results demonstrate that the PLSR method is a more suitable technique than stepwise regression for quantitative estimation of soil salt content in a large area.
引用
收藏
页码:259 / 270
页数:12
相关论文
共 38 条
[1]   Mapping of several soil properties using DAIS-7915 hyperspectral scanner data - a case study over clayey soils in Israel [J].
Ben-Dor, E ;
Patkin, K ;
Banin, A ;
Karnieli, A .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2002, 23 (06) :1043-1062
[2]   Global soil characterization with VNIR diffuse reflectance spectroscopy [J].
Brown, David J. ;
Shepherd, Keith D. ;
Walsh, Markus G. ;
Mays, M. Dewayne ;
Reinsch, Thomas G. .
GEODERMA, 2006, 132 (3-4) :273-290
[3]  
*COMO TECHN INC, 2004, UNSCR US MAN
[4]  
DARK NA, 1995, INT J REMOTE SENS, V16, P2555
[5]   Preprocessing EO-1 Hyperion hyperspectral data to support the application of agricultural indexes [J].
Datt, B ;
McVicar, TR ;
Van Niel, TG ;
Jupp, DLB ;
Pearlman, JS .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (06) :1246-1259
[6]   Image-derived spectral endmembers as indicators of salinisation [J].
Dehaan, R ;
Taylor, GR .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2003, 24 (04) :775-794
[7]   Field-derived spectra of salinized soils and vegetation as indicators of irrigation-induced soil salinization [J].
Dehaan, RL ;
Taylor, GR .
REMOTE SENSING OF ENVIRONMENT, 2002, 80 (03) :406-417
[8]   Image transforms as a tool for the study of soil salinity and alkalinity dynamics [J].
Dwivedi, RS ;
Sreenivas, K .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1998, 19 (04) :605-619
[9]   THE SELECTION OF THE BEST POSSIBLE LANDSAT TM BAND COMBINATION FOR DELINEATING SALT-AFFECTED SOILS [J].
DWIVEDI, RS ;
RAO, BRM .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 1992, 13 (11) :2051-2058
[10]  
[刘伟东 Liu Weidong], 2004, [遥感学报, Journal of Remote Sensing], V8, P434