FAN Yongzhuo,LI Xinguo.Hyperspectral estimation of soil conductivity of different land use types in lakeside oasis of Bosten Lake in Xinjiang[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2023,62(06):31-39.
FAN Yongzhuo,LI Xinguo.Hyperspectral estimation of soil conductivity of different land use types in lakeside oasis of Bosten Lake in Xinjiang[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2023,62(06):31-39. DOI: 10.13471/j.cnki.acta.snus.2023D024.
Hyperspectral estimation of soil conductivity of different land use types in lakeside oasis of Bosten Lake in Xinjiang
To more accurately understand the soil salinity of different land use types in the lakeside oasis of Bosten Lake, Xinjiang, three methods of competitive adaptive reweighted sampling (CARS), successive projection algorithm (SPA), and competitive adaptive reweighted-successive projection algorithm (CARS-SPA) were applied to screen the characteristic bands of soil conductivity hyperspectral data of different land use types, based on the full band and characteristic bands. The estimation models of soil conductivity of the lakeshore oasis were constructed based on the full band and characteristic bands combined with BP neural network to compare the accuracy of estimation models in different ways. The results showed that: (1) the mean values of soil conductivity of cropland, forest land, wasteland, and overall land are 0.84, 5.43, 5.78, and 3.26 mS/cm, respectively; the overall soil conductivity of the lakeshore oasis is 2.42 mS/cm higher than the mean value of cropland, 2.17 and 2.52 mS/cm lower than forest land and wasteland. (2) The CARS-SPA method can reduce the number of bands input to the model and improve the efficiency of the model. The number of characteristic bands for screening the electrical conductivity of cropland, forestland, wasteland, and overall land soil only accounts for 0.71%, 0.59%, 0.06%, and 1.00% of the full bands. (3) Constructing separate estimation models for soil conductivity of cropland, forest land, and wasteland significantly improves the estimation accuracy of soil conductivity in the study area. Among the three models of FDR-CARS-BP, FDR-SPA-BP, and FDR-CARS-SPA-BP, the average
R
2
of soil conductivity modeling for cropland, forest land, and wasteland increased by 0.12, 0.14, and 0.15, respectively, compared with the overall soil modeling, the FDR-CARS-SPA-BP model is the optimal model for hyperspectral estimation of soil conductivity in the study area.
关键词
土壤电导率土地利用类型高光谱数据竞争性自适应重加权-连续投影算法BP神经网络
Keywords
soil conductivityland use typeshyperspectral dataCARS-SPABP neural network
BANNARI A, EL-BATTAY A, BANNARI R,et al,2018.Sentinel-MSI VNIR and SWIR bands sensitivity analysis for soil salinity discrimination in an arid landscape[J].Remote Sens,10(6):855.
CLOUTIS E A,1996.Hyperspectral geological remote sensing: Evaluation of analytical techniques[J].Int J Remote Sens,17(12):2215-2242.
FAN X W, LIU Y B, TAO J,et al,2015.Soil salinity retrieval from advanced multi-spectral sensor with partial least square regression[J]. Remote Sens,7(1):488-511.
FARIFTEH J, van der MEER F, ATZBERGER C,et al,2007.Quantitative analysis of salt-affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN)[J]. Remote Sens Environ,110(1): 59-78.
JIN P B, LI P H, WANG Q, et al,2015.Developing and applying novel spectral feature parameters for classifying soil salt types in arid land[J].Ecol Indic,54:116-123.
HEIL K, SCHMIDHALTER U,2019.Theory and guidelines for the application of the geophysical sensor EM38[J].Sensors,19(19):4293-4293.
SRIVASTAVA R, SETHI M, YADAV R K,et al,2017.Visible-near infrared reflectance spectroscopy for rapid characterization of salt-affected soil in the Indo-Gangetic Plains of Haryana,India[J].J Indian Soc Remote Sens,45(2):307-315.