chinilin/spectra

Comparing different data preprocessing methods to predict soil organic carbon content on soil spectra features

Spectra

Spectral preprocessing methods, first and second derivatives (FD & SD), standard normal variate (SNV), multiplicative scatter correction (MSC), and continuum removal (CR) were employed after smoothing with Savitzky-Golay (SG) and moving average filtering (MA) to improve the robustness and performance of the calibration models. According to the criteria of maximal coefficient of determination (R2cv) and minimal root mean square error of prediction in cross-validation (RMSEPcv), the PCR algorithm with FD preprocessing was determined as the best method for predicting soil organic carbon content.

Contact: [email protected]