Visible and Near-Infrared Reflectance Spectroscopy for Assessment of Soil Properties in the Caucasus Mountains,Azerbaijan |
| |
Authors: | Elton Mammadov Michael Denk Frank Riedel Karolina Lewinska Cezary Ka?mierowski Cornelia Glaesser |
| |
Institution: | 1. Institute of Soil Science and Agrochemistry of Azerbaijan National Academy of Sciences , Baku, Azerbaijan elton.eldaroglu@gmail.comhttps://orcid.org/0000-0002-3446-9507;3. Department of Remote Sensing and Cartography, Martin Luther University Halle-Wittenberg , Halle (Saale), Germany https://orcid.org/0000-0003-1806-1242;4. Department of Remote Sensing and Cartography, Martin Luther University Halle-Wittenberg , Halle (Saale), Germany;5. Department of Soil Science and Remote Sensing of Soils, Adam Mickiewicz University in Poznan , Poznan, Poland https://orcid.org/0000-0002-9630-4855;6. Department of Soil Science and Remote Sensing of Soils, Adam Mickiewicz University in Poznan , Poznan, Poland https://orcid.org/0000-0002-8964-3920;7. Department of Remote Sensing and Cartography, Martin Luther University Halle-Wittenberg , Halle (Saale), Germany https://orcid.org/0000-0002-1176-6613 |
| |
Abstract: | ABSTRACT This study aimed to predict soil properties using visible–near infrared (VIS-NIR) spectroscopy combined with partial least square regression (PLSR) modeling. Special emphasis was given to evaluating effect of pre-processing methods on prediction accuracy and important wavelengths. A total of 114 samples were collected and involved in chemical and spectral analyzes. PLSR model of each soil property was calibrated for all pre-processing methods using all samples, and leave-one-out cross-validation was used to make comparisons between them. Then, PLSR model of each best pre-processing method was calibrated using a 75% of all samples and correspondingly validated with the remaining a 25%. Model accuracy was evaluated based on coef?cient of determination (R2), root mean-squared errors (RMSE), and residual prediction deviations (RPD). The high correlation coefficients were found between the tested soil properties and reflectance spectra. The pre-processing methods considerably improved prediction accuracy and filtering methods outperformed linearization methods, and the latter outperformed normalization methods. The performance of cross-validation, calibration and independent validation was similar. An excellent prediction (RPD>2.5) model was obtained for soil organic carbon (SOC) and calcium-carbonate (CaCO3), good quantitative (2.0< RPD<2.5) prediction for sand, silt, and clay, fair prediction (1.4< RPD<1.8) for pH, and poor prediction (1.0< RPD<1.4) for hygroscopic water content (WC). Important wavelengths varied depending on soil property, but some wavelengths were common. This study can be a precursor to building a pioneering soil spectral database, calibrating satellite data, and hyperspectral image mapping of soils as well as digital soil mapping, environmental, and erosion modeling in the Caucasus Mountains. |
| |
Keywords: | Soil properties VIS-NIR spectroscopy partial least squares regression the Caucasus Mountains |
|
|