جستجوی مقالات مرتبط با کلیدواژه « partial least squares regression (plsr) » در نشریات گروه « آب و خاک »

The present research performed to estimate soil texture using visible near-infrared spectrometry in Semirom, Isfahan. A total number of 200 soil samples (0-10 cm) were collected from the Semirom area (51º 17' - 52º 3' E; 30º 42' - 31º 51' N), Isfahan. The samples were air dried and passed through a 2 mm sieve, and soil particles percentage was determined in the laboratory using hydrometry method. Reflectance spectra of all samples were measured using an ASD field spectrometer. Different pre-processing methods i.e., First Derivatives and Savitzky-Golay Filter, Multiplicative Scatter Correction and Standard Normal Variable were applied and performed on spectral data. The Partial Least Squares Regression, Support Vector Machine Regression and Artificial Neural Network models were used to estimate soil texture. The best result was obtained for Silt estimation, with excellent values of RPD >2, R2 =0.98 and RMSE=1.08 using Artificial Neural Network model with MSC pre-processing technique. The results indicated the desirable capability of Artificial Neural Network model with MSC and SNV pre-processing techniques in estimating the Clay (RPD >2, R2=0.94 and RMSE=1.21) and Sand (RPD >2, R2=0.84 and RMSE=6.24) contents of the soils, respectively. In general, based on the results of this study, VNIR spectroscopy was successful in estimating soil particles percentage and showed its potential for substituting laboratory analyses.

 Estimating soil properties on large scales using experimental methods requires specialized equipments and can be extremely time-consuming and expensive, especially when dealing with a high spatial sampling density. Soil Visible and Near-InfraRed (V-NIR) reflectance spectroscopy has proven to be a fast, cost-effective, non-destructive, environmental-friendly, repeatable, and reproducible analytical technique. V-NIR reflectance spectroscopy has been used for more than 30 years to predict an extensive variety of soil properties like organic and inorganic carbon, nitrogen, organic carbon, moisture, texture and salinity. The objectives of this study were to estimate soil properties (carbonate calcium equivalent (CCE), electrical conductivity (EC), pH, and organic carbon (OC)) using visible near-infrared and short-wave Infrared (SWIR) reflectance spectroscopy (350-2500 nm). In this study, the best predictions of all the soil properties, model and pre-processing technique were also determined. The Partial Least Squares Regression (PLSR), Artificial Neural Network, Support Vector Machine Regression and Principal Component Regression (PCR) models were also compared to estimate soil properties.

 A total number of 200 surface soil samples (0-10 cm) were collected from the Semirom region (51º 17' - 52º 3' E; 30º 42' - 31º 51' N), Isfahan, Iran. The samples were air dried and passed through a 2 mm sieve, and using standard procedures soil properties were determined in the laboratory. Accordingly, soil pH and the EC contents of soil samples were determined in saturated pastes and extracts, respectively. The CCE content of the soils were measured using back titration, and the OC contents of the samples were measured using Walkley-Black method. The Reflectance spectra of all samples were measured using an ASD field spectrometer. The selection of the best model was done according to the value of the Ratio of Performance to Deviation (RPD), the coefficient of determination (R2), and the Root Mean Square Eerror (RMSE).

 Once the models were constructed using PLSR, ANN, SVMR and PCR approaches, descriptive analysis was carried out for each property, for the data measured in the laboratory. The parameters calculated for the properties were mean, coefficient of variation (CV), minimum and maximum, standard deviation and range. Coefficient of variation for the organic carbon, CCE, pH, and EC values were 21.7, 12.4, 1.34, and 28.74, respectively. Wilding (1985) proposed low, medium, and high variability for the CV values less than 15%, 15-35%, and greater than 35%, respectively. Accordingly, the organic carbon and EC of soils could be classified in the group with moderate variability. However, the calcium carbonate equivalent and pH are in the group with low variability. Since spectral data preprocessing has an effective role on improving the calibration, in order to perform spectral preprocessing, two first nodes at the first (350-400 nm) and the end (2450-2500 nm) of each spectrum were removed. In addition, two interruptions were eliminated, due to the change in the detector in the range of 900 to 1700 nm. Different preprocessing methods i.e., Standard Normal Variable (SNV) and First (FD) and Second Derivatives (SD) and Savitzky-Golay preprocessing techniques were performed on spectral data. Then, using PLSR, the cross‐validation method was used to evaluate soil properties calibration and validation. According to Stenberg (2002), for agricultural applications, The values of RPD greater than 2 indicate that the models provide precise predictions, the values of RPD between 1.5 and 2 are considered to be reasonably representative, and the values of RPD less than 1.5 indicate poor predictive performance. The results indicated the desirable capability of the PLSR method in estimating the EC (RPD > 2, R2 = 0.94), CCE (RPD > 2, R2 = 0.88), and OC (RPD > 2, R2 = 0.89). The best results of the pH (RPD > 2, R2 = 0.79) were estimated by the SVMR method. In this study the best methods of preprocessing techniques were First (FD) and Second Derivatives (SD) and Savitzky-Golay filter.

 In general, based on the results of this study, VNIR spectroscopy was successful in estimating soil properties and showed its potential for substituting laboratory analyses. Moreover, spectroscopy could be considered as a simple, fast, and low-cost method in predicting soil properties. The PLSR model with First and Second derivatives and Savitzky-Golay pre-processing techniques seems to be more robust algorithm for estimating EC, OC, and CCE. The best results of the pH were estimated by the SVMR method with First and Second derivatives and Savitzky-Golay pre-processing techniques.

Soil texture is one of the majorphysical properties of soils thatplays important roles inwater holding capacity, soil fertility, environmental quality and agricultural developments. Measurement of soil texture elements in large scales is time consuming and costly due to the high volume of sampling and laboratory analysis. Therefore, assessing and using simple, quick, low-cost and advanced methods such as soil spectroscopy can be useful. The objectives of this study were to examine two statistical models of Partial Least Squares Regression (PLSR) and Principal Component Regression (PCR) to estimate soil texture elements using Visible and Near-Infrared (VNIR) and Short-Wave Infrared (SWIR) reflectance spectroscopy (400-2450nm).
A total of 120 composite soil samples (0-10 cm) were collected from the Kafemoor basin (55º 15' - 55º 25' E; 28º 51' - 29º 11' N), Sirjan, Iran. The samples were air dried and passed through a 2 mm sieve and soil texture components were determined by the hydrometer method (Miller and Keeny 1992). Reflectance spectra of all samples were measured using an ASD field-portable spectrometer in the laboratory. Soil samples were divided into two random groups (80% and 20%) for calibration and validation of models. PLSR and PCR models and different pre-processing methods i.e.First (FD) and Second Derivatives (SD), Multiplicative Scatter Correction (MSC) and Standard Normal Variate (SNV) were applied and compared to estimate texture elements. The cross‐validation method was used to evaluate calibration and validation sets in the first part (80%) and coefficient of determination (R2), Root Mean Square Error (RMSE) and Residual Prediction Deviation (RPD) were also calculated. For testing predictive models, the second part of data (20%) was used and R2 and RMSE of predictive accuracy were calculated.
The results of applying two statistical models for estimatingLogClay (%) showed that R2of calibration (R2CV) and validation (R2VAL) datasetranged from 0.22 to 0.72 and 0.12 to 0.54, respectively. The lowest RMSE was computed for PLSR model with SD pre-processing. The highest RPD of calibration (RPDCV) and validation (RPDVAL) were obtained for PLSR with SD pre-processing technique which was classified as a very good and good model, respectively. The results indicated possible prediction of soil clay content by using PCR model with SD pre-processing techniques. In addition, the PCR predicted soil texture elements poorly according to RPD values while the PLSR model with SD pre-processing was the best model for predict¬ing soil clay content. The R2CV and R2VAL of PLSR models for LogSilt (%) varied from 0.34 to 0.73 and 0.27 to 0.58, respectively. The RMSECV varied from 0.14 for FD pre-processing to 0.23 for no-preprocessing and the RMSEVAL rangedbetween 0.18 and0.24. The highest RPDCV (2.07) and RPDVAL (1.59) were obtained for PLSR with FD pre-processing which were classified as very good and good models, respectively. The results of PCR model developments for estimating LogSilt (%) indicated that the highest RPDCV and RPDVAL were, respectively, 1.31 and 1.25 for MSC pre-processing techniques which were rated as poor models. On the contrary to PLSR models, PCR models were not reliable for predicting LogSilt (%).Theresultsof PLSR models for estimatingLogSand (%) revealedthat the highest R2CV and R2VAL were 0.56 and 0.47, respectively and the lowest RMSECV and RMSEVAL were 0.14 and 0.16, respectively which were obtained for SD pre-processing. The RPDCV and RPDVAL values for SD pre-processing in PLSR model were 1.59 and 1.39 which were rated as good and poor performance of predictions, respectively. The highest RPDCV and RPDVALfor PCR models were obtained with the MSC pre-processing indicating poor model. Therefore, PLSR model with SD pre-processing techniques was superior model for estimation of LogSand(%).Overall, PLSR model with SD pre-processing techniques performed better in estimatingclay and sand and PLSR model with FD pre-processing gave better estimate of silt content.
Our finding indicated thatclay and silt contentcan be estimated by using electromagnetic spectrum between VNIR-SWIR region. Further, spectroscopy could be considered as a simple, fast and low cost method in predicting soil texture and PLSR model with SD and FD pre-processing seems to be more robust algorithm to estimateLogClay and LogSilt, respectively.