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 soilgypsum 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 (R2 cal=0. 93, RMSEcal=2. 47, RPDcal=3. 71) and the main spectra (R2 cal=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 (R2 val=0. 88, RMSEval=3. 57, RPDval=2. 49) and the original spectrum (R2 val=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...