E. Mehrabi Gohari; H.R. Matinfar; Ruhollah Taghizadeh-Mehrjardi; A. Jafari
Abstract
Introduction: Soil texture is the most important environmental variable because it plays a very important role in reducing the quality of land and water transfer processes, soil quality control and fertility. On the one hand, soil texture components are the basis of environmental predictive models and ...
Read More
Introduction: Soil texture is the most important environmental variable because it plays a very important role in reducing the quality of land and water transfer processes, soil quality control and fertility. On the one hand, soil texture components are the basis of environmental predictive models and digital mapping of soil and on the other hand, soils are temporally and spatially variable, thus distinguish zoning and their monitoring with traditional sampling methods and laboratory analysis is very costly and time consuming. As a result, the development of methods for analyzing the soil and for required information has become very important. Visible and near infrared spectroscopy (VIS-NIR) is widely used to estimate soil physical properties and estimate soil texture. The present study aims to predict soil texture using spectral measurements and artificial neural network models and partial least squares regression.
Materials and Methods: The study area in southeastern Iran is approximately 70 km from Kerman. In the study area, based on the hypercube technique, 115 profiles were identified and then horizons were sampled. In this way, for each point of study, the necessary information, including the location of the profile on the ground, the type of geomorphic unit and the type of materiel, were recorded and taken from the horizons of each profile. In all soil samples, after drying and passing through 2 mm soil, the soil texture was measured by hypercube. Spectral radiometer was used to measure the spectral reflection of soil samples. The soil samples were air dried and sieved and then placed in a petri dish with an approximate diameter of 10 cm and transferred to the dark room for spectral analysis. Each specimen was tested four times (for each 90 degree sequential rotation) to remove the effects of a change in the radiation geometry. Soil samples were scanned, and absolute reflections at a spectral range of 2500-350 nm yielded 2150 spectral data points (SDPs) per soil sample with a spectral resolution of one nanometer. Finally, to construct a suitable model for forecasting the percentage of clay, sand, and silt, the least squares model was used with the number of factors 1 to 10 by Artificial Neural Network (ANN) modeling using JMP software Work.
Results and Discussion: The reflectance spectrum of the visible range - near infrared - was measured for specimens. Since preprocessing of spectral data has an effective role in improving the calibration, in order to perform spectral preprocessing, two first nodes of the first and the end of the spectra were first removed in the range of 350-400 and 2450-2500 nm. In addition, the interruption due to the change in the detector in the range of 900 to 1000 nm was also eliminated. Types of preprocessing methods were performed on spectral data. Then, using partial least squares regression analysis, the best model was produced when the first derivative was fitted to reflection values. The explanation coefficients for this low and unacceptable model were obtained. Therefore, using partial least squares regression analysis, the best wavelengths were selected to predict the percentage of clay, sand, soil, and extracted from the model. Then it was used as input in the neural network model. To determine the best combination, root error index and error coefficient were used. The results of artificial neural network showed that the number of neurons 9.8 and 10 had the best composition for predicting clay, sand and soil silt. The root-squared error results for clay, sand, and soil silt were 3.42, 6.94, and 4.383 respectively. Also, the results of the explanatory factor were 0.84, 0.83 and 0.81, respectively. After obtaining the optimal structure in the artificial neural network training phase described above, the trained network has been tested on the test data to determine the accuracy of this model to predict clay, sand and silt of surface soil. The root-squared error results for clay, sand and silt components were obtained at 5.54.9.14 and 7.01. Also, the results of the explanatory factor were 0.76.0.70 and 0.73 respectively. The best result of the prediction for partial least squares regression was obtained for the sand sample. The results indicate that the neural network performance is better than partial least squares regression, which is consistent with Mouazenet. al (2010) and also ViscarraRossel R. et. al (2009). Acceptable performance of the artificial-neural network can be attributed to the ability of this model for non-linear behavior of soil texture in visible spectroscopy. In this study, specific wavelengths, which Ben Finder et al. (2003) obtained in the study on the soils of Israel, were used. This conclusion confirms that various types of soil can be modeled using specific wavelengths. The advantage of this study is that, when using the artificial neural network, no pre-processing of reflection data is required before applying the model. Since the relationship between the percentage of soil particles (clay and gravel) and the reflection of the soil is not linear, the neural network method is very useful for analyzing the relationship between soils. Finally, the map of clay, sand and silt and map of soil texture was prepared by artificial neural network method in GIS environment.
Conclusion: The results of this study showed that the neural-dynamic network has a better performance than partial least squares regression. Calibration models designed and used in this study can be transported for use with other soils. When the partial least squares regression model was implemented, it had a very low accuracy (R2 ~ 0.1-0.3); on the contrary, the neural network-based method had high accuracy and less error. Note that although neural-dynamic modeling estimates higher precision results from soil texture, both approaches depend on wavelength selections, and so wavelengths should be selected before using any of the two models. To be finally, a meaningful relationship between the selected wavelengths and the percentage of clay, sand and silt in the present study indicates that soil texture is not only possible but also reliable by reflection spectroscopy.
Saghar Fahandej saadi; Masoud Noshadi
Abstract
Introduction: Although the soil salinity as an effective factor on soil and water management is typically assessed by measuring the soil electrical conductivity (ECe), this conventional laboratory method is time-consuming and costly. Therefore, near-infrared spectroscopy (NIR) as a fast, cheap and non-destructive ...
Read More
Introduction: Although the soil salinity as an effective factor on soil and water management is typically assessed by measuring the soil electrical conductivity (ECe), this conventional laboratory method is time-consuming and costly. Therefore, near-infrared spectroscopy (NIR) as a fast, cheap and non-destructive method to assess soil salinity level can be considered as a valuable alternative method. Reviews of literature on the application of NIR spectroscopy for soil salinity prediction have shown that there is no sufficient information about the effect of soil texture on results accuracy; therefore, in this study the soil salinity was predicted under different soil salinity levels and various soil textures. The effect of different pre-processing methods was also investigated to improve the predicted soil salinity.
Materials and Methods: Twenty three surface soil samples were collected from different places in Fars province, then; some soil properties such as percentage of particles size and ECe were measured. These samples were artificially salted by adding the water in different salinity levels to the soil samples. The ECe of these soils were between 2.1 to 307.5 dS/m and then all samples dried to reach the field capacity level. Soil reflectance spectra were obtained in 350-2500 nm wavelength range. The absorbance and derivative of reflectance spectra were calculated based on the reflectance spectra. In order to determine the effect of smoothing technique, as a pre-processing method, 4 various methods (moving average, Gaussian, median and Savitzky-Golay filters) in 12 different segment sizes (3,5,7,9,11,13,15,17,19,21,23 and 25) were applied and the processed spectra introduced to Partial Least Square Regression (PLSR) model to predict soil salinity in two calibration and validation steps. At the first step, the soil salinity was predicted for all samples using of reflectance, absorbance and derivative of reflectance spectra under 4 pre-processing methods and 12 segment sizes. According to the R2 and RMSE indices, the best type of spectra, the effect of various pre-processing methods and the best segment size in prediction of soil salinity were determined as absorbance spectra, moving average and Savitzky-Golay filters for segment size of 25 and 15, respectively. In the second step, the effect of soil texture on prediction accuracy was investigated. For this purpose, soil samples were divided into the coarse and fine textures and soil salinity was predicted for each of these groups using different pre-processing methods and different segment sizes.
Results and Discussion: In prediction of soil salinity by absorbance, reflectance and derivative of reflectance spectra, the R2 values in validation step were 0.742, 0.706 and 0.670; and RMSE values were 29.92, 31.96 and 33.9 (dS.m-1), respectively. The absorbance spectra were the best spectra type in prediction of soil salinity. Therefore, in next step, absorbance spectra were used only for predicting the salinity in fine and coarse soil textures. Results showed that the prediction in coarse texture was better than that of the fine texture (R2= 0.836 and R2=0.756, respectively). It was also revealed that the highest R2 occurred in coarse texture and the accuracy of prediction was reduced in fine textures. The results showed that the performance of different pre-processing methods is related to the spectrum type. Although the pre-processing methods had no positive effect in using of reflectance spectra, but it improved the predicted values which were obtained using of absorbance and derivative of reflectance spectra. The best results were occurred when the absorbance spectra were used. Moving average method increased the accuracy of prediction more than the other pre-processing methods, and according to the results this method, for the segment size of 25, was the best technique in soil salinity prediction.
Conclusion: According to the R2 and RMSE indices, the prediction of soil salinity by absorbance spectra was more accurate than the prediction using reflectance and derivative of reflectance spectra (R2= 0.742, 0.706 and 0.670, respectively). Although the predicted soil salinity in coarse soils were more accurate than that in fine soils. Using of absorbance spectra to predict the soil salinity in all soil textures was efficient. The results showed that using of pre-processing methods improved the soil salinity prediction by absorbance and derivative of reflectance spectra, and the moving average and Savitzky-Golay filter were the best pre-processing methods.
