Search

The advent of lab diffuse reflectance spectroscopy (LDRS) that exploits the fundamental vibration, overtones and combination of functional groups of soil components makes the soil study easier. The present research intends to predict sand content utilizing the proximal soil sensing (PSS) tech. Thus, in accord with the supplementary data layers and stratified randomized sampling (SRS) method, eventually, 128 samples were gathered from 20 cm of soil surface of Mazandaran Province, Iran. First of all, the sample set was subdivided into two subsets: calibration (96) and validation (32). Using the multivariate regression analysis-partial least squares regression (PLSR) algorithm with leave-one-out cross-validation (LOOCV) technique and some pre-processing algorithms, such as spectral averaging, smoothing and 1st derivative (1st-D), the definitive calibration model with two & four latent vectors (LVs/LFs) and correlation coefficient (RP), determination coefficient (R2P), root mean square error (RMSEP), ratio of performance to deviation (RPDP) and ratio of performance to interquartile distance (RPIQP) respectively: 0.83&0.82, 0.68&0.67,8.68&8.83%,1.78&1.75,2.45&2.41, were validated and spotted as the most appropriate predictive model for the sand content prediction in the study region. Last, the potentiality of the visible-near infrared diffuse reflectance spectroscopy (VNIR-DRS) for sand content estimation in Mazandaran soils was proved. Also, it is feasible to upscale the sand prediction process utilizing the principal resulted model and the key spectral domains via airborne/satellite hyperspectral data, which emphatically shows the LDRS importance as a commencement point for characterizing the informative optical wavelengths. Likewise, that will be the infrastructure for spaceborne data modeling and upscaling process. [ABSTRACT FROM AUTHOR]

Understanding the physical and especially mechanical properties of forest soils is very important in forest engineering operations including road construction and exploitation. Unconfined compressive strength (UCS) is one of the most important mechanical properties for evaluating the strength of adhesive soils in many engineering projects including forest roads. Measuring the USC of soil in the laboratory and in situ is difficult, time-consuming, and costly, so it is essential to explore a rapid, low-cost, and non-destructive method. The aim of this study was to estimate the UCS of forest roads using spectroscopy. The applied support vector machine (SVM) method determined the soil moisture classes (i.e., 14%, 25%, 31%, and 36%) with R2 of 0.98. Two methods of partial least squares regression (PLSR) and the normal difference index (NDI) were used to estimate the UCS at different moisture classes. The results showed that the NDI performed better than the PLSR to estimate the USC at four different moisture classes of 14% (R2 = 0.8, RMSE = 19.36, RPD = 2.61), 25% (R2 = 0.78, RMSE = 16.06, RPD = 1.64), 31% (R2 = 0.82, RMSE = 11.2, RPD = 2.28), and 36% (R2 = 0.83, RMSE = 7.49, RPD = 2.41). Also, a sampling interval method was applied to reduce spectral dimensionality and processing time. The sampling interval of 16 nm was selected using a genetic algorithm. Finally, the UCS was estimated at maximum soil moisture using the simple regression model (SRM) based on the results of NDI. Based on this current study, it has been found that using spectroscopy to estimate the UCS of soil could be considered an alternative method for developmental operations in identifying the UCS of soil due to the costly and time-consuming conventional laboratory methods. [ABSTRACT FROM AUTHOR]

• The potential of spectra to predict key engineering soil properties was assessed. • PLSR coupled with Vis-NIR spectroscopy provided robust models. • Best results were obtained for Ac, clay content, CEC, and D 10 (RPD > 1.80). • Spectroscopy is a promising alternative to predict soil engineering properties. The conventional methods for measuring soil properties are time-consuming and expensive. Over the past few decades, reflectance spectroscopy has been widely applied as a rapid and cost-effective technique to estimate soil properties. However, less attention has been given to estimating soil engineering properties using soil spectral data. To evaluate the efficiency of the technique, selected physical and mechanical properties of 220 soil samples from two study areas in Ghorveh-Dehgolan and Zrêbar regions in the Kurdistan province, west of Iran, were measured by standard laboratory methods. Spectral measurements were also performed on air-dried soil sub-samples using a laboratory spectroradiometer apparatus. After recording the spectra, the different pre-processing methods were tested to improve the estimations. Partial least squares regression (PLSR) was used to establish relationships between soil engineering properties and the spectra transformed via Savitzky–Golay first derivative. Based on the results, the prediction accuracy was very good for clay activity (Ac) and clay content (modeling efficiency (EF) = 0.75 and the ratio of performance to deviation (RPD) > 2), and good for cation exchange capacity (CEC) and effective diameter size (D 10) (EF > 0.68 and RPD > 1.81). Reasonable predictions were also obtained for Atterberg limits, silt and sand contents, particle density (PD), diameters corresponding to 30% and 60% finer (D 30 and D 60 , respectively), median particle size (D 50), and geometric mean diameter of soil particles (d g) and their standard deviation (δ g) (EF: 0.51–0.67, RPD: 1.44–1.76); however, the total porosity (n) and bulk density (BD) of soils were poorly predicted. The reliability and good quality of the estimations was probably due to the variability in the properties of the different soils collected from the two distinct geographical regions. Overall, the results confirmed the potential efficacy of Vis-NIR spectroscopy for a rapid estimation of different important soil engineering properties. [ABSTRACT FROM AUTHOR]

• The potential of previous spectral indices to predict Atterberg limits was confirmed. • Spectral indices were linked to the soil parameters with PLS and PLS-BPNN. • A range of R2 (0.62–0.99) found between Atterberg limits and spectral reflectance. • We tested non-linear neural net vs. linear PLSR to link spectra to soil properties. Conventional methods for the determination of Atterberg limits based on laboratory tests are time-consuming. Reflectance spectroscopy which is fast and cost-effective has been reported as an alternative method for estimating Atterberg limits. To assess the efficiency of the method, 60 forest soil samples were measured by visible-near infrared reflectance spectroscopy (VNIR) within the range of 350–2500 nm. The Savitzky-Golay (SG) smoothing method for spectral data was used to reduce signal noise and the first derivative reflectance (DR) was applied to accentuate the features and assemble the data for use in the modeling process. In this study, raw reflectance (R) and first derivative reflectance (DR) data were used to estimate Atterberg limits. All two-band combinations of three types of spectra (ratio index, normalized difference index and difference index) as well as PLS and PLS-BPNN were calculated to extract optimum waveband combination and calibrations between Atterberg limits and reflectance spectra. The correlation coefficients between Atterberg limits and reflectance spectra indicated both positive and negative correlation at various wavelengths across the spectrum. The highest correlation for liquid limit (r = −0.86), plastic limit (r = −0.76) and plasticity index (r = −0.7) was found at 1921, 1938 and 1913 nm, respectively. In addition, the results showed the spectral indices technique as a good method for estimating soil plasticity and improving the prediction accuracy of Atterberg limits. In the current study, PLS and PLS–BPNN were also used to develop the calibration models for estimating Atterberg limits using R and DR. The results demonstrated that the prediction accuracy of PLS-BPNN for both R and DR was higher than that of PLS. Correlation coefficients between shrinkage limit (SL) and reflectance spectra showed weak correlation, and overall reflectance had the same correlation. The results represented that this method could be used to estimate soil plasticity properties quickly, non-destructively, and with minimal sample preparation and high accuracy. These advantages may be more important, especially when a huge number of samples should be tested and analyzed within a short period of time. [ABSTRACT FROM AUTHOR]