TY - JOUR ID - 70964 TI - Modeling Soil Salinity in Khuzestan Lands Susceptible for Dust Production Using Visible-Near Infrared Spectroscopic Method JO - Iranian Journal of Soil and Water Research JA - IJSWR LA - en SN - 2008-479X AU - Chatrenor, Mansour AU - Landi, Ahmad AU - Farrokhian Firouzi, Ahmad AU - Noroozi, Aliakbar AU - Bahrami, Hosseinali AD - PhD Student, Department of Soil Science and Engineering, Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Iran AD - Professor, Department of Soil Science and Engineering, Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Iran, Dust research center, Shahid Chamran university of Ahvaz, Ahvaz, Iran AD - Associate Professor, Department of Soil Science and Engineering, Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Iran AD - Associate Professor, Soil Conservation and Watershed Management Research Institute, Tehran, Iran AD - Associate Professor, Department of Soil Science, Faculty of Agriculture, Tarbiat Modares University, Tehran, Iran Y1 - 2019 PY - 2019 VL - 50 IS - 8 SP - 1951 EP - 1962 KW - Partial least squares regression KW - Preprocessing KW - Savitzky-Golay filter KW - Key wavelengths KW - Random forest model DO - 10.22059/ijswr.2019.278116.668150 N2 - A broad area of saline and semi-saline lands of Khuzestan province have changed into centers susceptible to dust production due to eroded wind and lack of surface coating and low soil resistance. The objective of this study was to model the soil salinity of sensitive areas to dust production in Khuzestan Provenience usin spectrometry method of visible and near-infrared wavelengths (2500-350 nm). The least square multivariate regression model, artificial neural network and random forest model were used to estimate soil salinity. The main soil spectrum was determined using the FieldSpect machine. Also, preprocessing methods including Savitzky-Golay filter, the first derivative with the Savitzky-Golay filter (FD-SG), the second derivative with the Savitzky-Golay filter (SD-SG), the standard normalization method (SNV), and the continuum remove method (CR) were used to eliminate the noise and to increase the accuracy of the multivariate model. The results showed that the combined model partial least squares-artificial neural network model with assessment criteria (RPDcal = 3.40-2.65) has high accuracy for salinity estimation. In contrast, the combined model of least squares - random forest showed the lowest accuracy (RPDcal = 0.85-1.98). Preprocess of the main spectrum in two models (neural network and partial least squares regression) increased the relative accuracy of the model; while in the random forest model, preprocess reduced the accuracy of the model compared to the main spectrum. The ranges of 1800, 1900, 2000, 2300 and 1500 nm were recognized as "the key wavelengths" impressed by soil salinity. The key wavelengths can be used in remote sensing studies and mapping of soil salinity in areas sensitive to dust production in Khuzestan province. UR - https://ijswr.ut.ac.ir/article_70964.html L1 - https://ijswr.ut.ac.ir/article_70964_a4f5f5b6d7573be0d1dd34c4c0892f02.pdf ER -