Influences of Soil Bulk Density and Texture on Estimation of Surface Soil Moisture Using Spectral Feature Parameters and an Artificial Neural Network Algorithm

文献类型： 外文期刊

第一作者： Diao, Wanying

作者： Diao, Wanying;Zhang, Huimin;Diao, Wanying;Liu, Gang;Hu, Kelin;Jin, Xiuliang

作者机构：

关键词： bulk density; spectral characteristics; artificial neural networks; soil water content

期刊名称：AGRICULTURE-BASEL （ 影响因子：2.925； 五年影响因子：3.044 ）

ISSN：

年卷期： 2021 年 11 卷 8 期

页码：

收录情况： SCI

摘要： Effective monitoring of soil moisture (theta) by non-destructive means is important for crop irrigation management. Soil bulk density (rho) is a major factor that affects potential application of theta estimation models using remotely-sensed data. However, few researchers have focused on and quantified the effect of p on spectral reflectance of soil moisture with different soil textures. Therefore, we quantified influences of soil bulk density and texture on theta, and evaluated the performance from combining spectral feature parameters with the artificial neural network (ANN) algorithm to estimate theta. The conclusions are as follows: (1) for sandy soil, the spectral feature parameters most strongly correlated with theta were S-g (sum of reflectance in green edge) and A_Depth(780 -970) (absorption depth at 780-970 nm). (2) The theta had a significant correlation to the R900-970 (maximum reflectance at 900-970 nm) and S900-970 (sum of reflectance at 900-970 nm) for loamy soil. (3) The best spectral feature parameters to estimate theta were R900-970 and S900-970 for clay loam soil, respectively. (4) The R900-970 and S900-970 showed higher accuracy in estimating theta for sandy loam soil. The R900-970 and S900-970 achieved the best estimation accuracy for all four soil textures. Combining spectral feature parameters with ANN produced higher accuracy in estimating theta (R-2 = 0.95 and RMSE = 0.03 m(3) m(-3)) for the four soil textures.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序