Spectral behavior modeling of soil texture over dust center of Khuzestan province using Hyperspectral images and Random Forest model
Author(s):
Article Type:
Research/Original Article (دارای رتبه معتبر)
Abstract:
Soil texture had an essential role in soil resistance of wind erosion. Due to useful Features of Hyperspectral images including low cost and high speed to the evaluation of soil properties, it can be used to determination of soil texture. The aim of this study was to evaluate the spectral behavior of clay, sand and silt content in susceptible soils of Khuzestan province implementing the PLS-RF model. Initially, the main factors were determined, using partial least squares regression (PLSR). Accordingly, the Random Forest model was implemented on main factors. Subsequently, the comparing of performance related to main spectral and five preprocessing methods, i.e. the Savitzky-Golay filter, the first derivative with the Savitzky-Golay filter (FD-SG), the second derivative with the Savitzky-Golay filter (SD-SG), the normalization of standard method (SNV), and the continuum removed method (CR), applied to eliminate the noise and also to increase the accuracy of the PLS-RF model. The Results showed that the best method with high performance was the continuum removal for clay content (, PRDcal=1.93) and silt content, (PRDcal=1.65). Additionally, the second derivative method was the best performance to the evaluation of sand content (PRDcal=1.98). In this study, the key wavelength for clay content was determined in the range of 1200-1210, 1800 and 2200 nm and the results for sand was 1400-1450, 1910-1930, 2200 and 2220 nm, and finally for silt was 1320, 1615, 2200 nm.
Keywords:
Language:
Persian
Published:
Journal of Advanced Applied Geology, Volume:9 Issue: 34, 2020
Pages:
466 to 479
https://www.magiran.com/p2102226
سامانه نویسندگان
اطلاعات نویسنده(گان) توسط ایشان ثبت و تکمیل شدهاست. برای مشاهده مشخصات و فهرست همه مطالب، صفحه رزومه را ببینید.
مقالات دیگری از این نویسنده (گان)
-
Digital Mapping of Soil Penetration Resistance and Shear Strength using Machine Learning Algorithms in the Kilane Watershed, Kurdistan Province
Farzaneh Parsaie, *, Masoud Davari, Ruhollah Taghizadeh-Mehrjardi
Journal of Range and Watershed Management, -
Using Sentinel radar and optical data in the Google Earth Engine platform to determine the extent of land use changes in Alborz Province
Rasoul Kharazmi *, Zahra Mohammadesmail,
Journal of Land Management, -
Spatial Estimation of Soil Erosion and Sediment Yield in GIS Environment Using SEDD and RUSLE Models: A Case Study Roudzard Watershed in Khuzestan Province
Shekoufeh Davoudi, Heidar Ghafari*,
Iranian Journal of Watershed Management Science and Engineering, -
Improving the accuracy of soil heavy metal concentration estimation based on spectral reflectance by minimizing the effect of moisture with the external parameter orthogonalization algorithm
Soheila Alioghli, Mahmoud Shabanpour *, Hosein Ali Bahrami
Journal of Agricultural Engineering, -
Prediction of Temperature Using SDSM Multiple Linear Models (Case Study: Hoor al-Azim and Miangaran Wetlands)
, Nasrin Moradimajd, Bahare Delsouz Khaki, Mirnaser Navidi *, Naser Davatgar
Environmental Sciences, -
Applicability of Proximal Sensing Technology in the study of Silt in the soils of Mazandaran Province
Majid Danesh*, Hosseinali Bahrami, Sayed Mostafa Emadi
Journal of Watershed Management Research,