جستجوی مقالات مرتبط با کلیدواژه "فیلتر ساویتزی گولای" در نشریات گروه "آب و خاک"

Considering that Khuzestan province has a large area of land susceptible to dust generation, novel approaches such as Hyperspectral images could be used in the determination of soil characteristics. One of the main challenges in using hyperspectral images for evaluation of soil properties in these areas is the presence of some compounds such as gypsum which may lead to some errors in estimating other soil properties. This research has mainly been conducted to determine the soil-gypsum key wavelength in the dust center of Khuzestan province. To achieve this goal, at first the original soil spectrum was preprocessed using FieldSpec3 setup via five methods including 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 Standard Normal Variant (SNV) and the Continuum Removal method (CR). Two Multivariate regression models including Partial Least Squares Regression (PLSR) and Support Vector Machine (SVR) were used and compared in the estimation performance of soil gypsum. The results showed that the SVR model had better performance rather than the PLSR model in estimating soil gypsum. Also, in the SVR model, the continuum removal method (R2cal=0.93, RMSEcal=2.47, RPDcal=3.71) and the main spectra (R2cal=0.76, RMSEcal=6.32, RPDcal=1.59) had the best and weakest performance in estimating soil gypsum, respectively. It is noteworthy that the continuum removal method (R2val=0.88, RMSEval=3.57, RPDval=2.49) and the original spectrum (R2val=0.52, RMSEval=7.81, RPDval=1.12) in the validation group showed the best and the weakest performance, respectively. In the present study, wavelength ranges around 1450, 1550, 1700, 2100, 2200, 2400 nm which had the highest level of correlation with soil-gypsum content, was obtained as the key wavelengths of the soil in sensitive areas to dust production.

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.