| Reducing the influence of moisture on soil reflectance using EPO for precise clay prediction |
| Paper ID : 1391-SMPR |
| Authors: |
|
Saham Mirzaei *1, Ali Darvishi Bloorani2, Hossein Ali Bahrami3, Seyed Kazem Alavipanah4, Alijafar Mousivand5 1PhD student, Department of Remote Sensing and GIS, Faculty of Geography, University of Tehran 2Assistant professor, Department of Remote Sensing and GIS, Faculty of Geography, University of Tehran 3Professor, Department of Soil Science, Faculty of Agriculture, Tarbiat Modares University 4Department of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran, Iran 5Department of Remote Sensing & GIS, Faculty of Humanities, Tarbiat Modares University |
| Abstract: |
| Soil moisture hampers the estimation of soil variables such as clay content from remote and proximal sensing data, reducing the strength of the relevant spectral absorption features. In the present study, 21 soil samples which have different texture were rewetted to 5 different moisture levels (air-dry, 10, 20, 30 and 40%) and reflectance measured by spectroradiometer (ASD-Fieldspec 3.). External Parameter Orthogonalization (EPO) used to minimize the influence of soil moisture on clay estimation. Cross Validation (CV) used to determine the optimum number of used components in the EPO matrix. Partial Least Squares Regression (PLSR) model was applied to clay prediction after removing effect of moisture by EPO. The result shows that removing the effects of moisture from the soil reflectance by EPO algorithm lead to improve precision of clay prediction by PLSR model. Therefore, the EPO could be useful method for field level spectrometry for clay estimation without getting affected by moisture |
| Keywords: |
| EPO, PLSR, Cross validation, Spectroradiometer, Soil moisture, Clay |
| Status : Paper Accepted (Poster Presentation) |
