Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS–NIR) spectroscopy, Ebinur Lake Wetland, Northwest China

Abstract

Soil salinization is one of the most common forms of land degradation. The detection and assessment of soil salinity is critical for the prevention of environmental deterioration especially in arid and semi-arid areas. This study introduced the fractional derivative in the pretreatment of visible and near infrared (VIS–NIR) spectroscopy. The soil samples (n = 400) collected from the Ebinur Lake Wetland, Xinjiang Uyghur Autonomous Region (XUAR), China, were used as the dataset. After measuring the spectral reflectance and salinity in the laboratory, the raw spectral reflectance was preprocessed by means of the absorbance and the fractional derivative order in the range of 0.0–2.0 order with an interval of 0.1. Two different modeling methods, namely, partial least squares regression (PLSR) and random forest (RF) with preprocessed reflectance were used for quantifying soil salinity. The results showed that more spectral characteristics were refined for the spectrum reflectance treated via fractional derivative. The validation accuracies showed that RF models performed better than those of PLSR. The most effective model was established based on RF with the 1.5 order derivative of absorbance with the optimal values of R2 (0.93), RMSE (4.57 dS m−1), and RPD (2.78 ≥ 2.50). The developed RF model was stable and accurate in the application of spectral reflectance for determining the soil salinity of the Ebinur Lake wetland. The pretreatment of fractional derivative could be useful for monitoring multiple soil parameters with higher accuracy, which could effectively help to analyze the soil salinity.

Assessing Soil Organic Matter Content in a Coal Mining Area through Spectral Variables of Different Numbers of Dimensions

“…Random forest (RF) is a machine learning method widely used in the field of classification and regression in recent years [25]. Multiple soil properties have been linked to the Vis-NIR spectrum through this algorithm, such as soil organic carbon (SOC) [26], soil cadmium (Cd) [27], forage phosphorus (P) [28] and soil pH [29]. Numerous research results indicate that RF provides better prediction results than the classical partial least-squares regression (PLSR) [29][30][31].…”

“…Multiple soil properties have been linked to the Vis-NIR spectrum through this algorithm, such as soil organic carbon (SOC) [26], soil cadmium (Cd) [27], forage phosphorus (P) [28] and soil pH [29]. Numerous research results indicate that RF provides better prediction results than the classical partial least-squares regression (PLSR) [29][30][31]. Furthermore, compared to other machine learning technologies such as artificial neural networks (ANN) and support vector machine (SVM), the RF model can provide the relative importance of each predictor, which makes the results of the model highly interpretable [27,32].…”

Performance Comparison of Machine Learning Algorithms for Estimating the Soil Salinity of Salt-Affected Soil Using Field Spectral Data

“…Wang et al used the PLSR algorithm and the random forest (RF) algorithm to measure soil salinity. According to the validation accuracies, the RF models outperformed the PLSR models [34]. These studies were conducted in different data and different environments, and the results obtained cannot be put together for comprehensive evaluation of these models.…”

“…The regularization can reduce the influence of collinearity by adding offset to the optimization function [30]. With the deep research of machine learning methods, the results are uneven and many studies in which machine learning methods are used to estimate soil salinity have been reported [4,21,24,[32][33][34]. Jiang et al monitored soil salinity by integrating multiple biophysical indicators with support vector machine (SVM) and artificial neural network (ANN) regression algorithms.…”

Impact of Fractional Calculus on Correlation Coefficient between Available Potassium and Spectrum Data in Ground Hyperspectral and Landsat 8 Image

“…However, the hyperspectral inversion models established for available potassium are mainly constructed based on 1-order or 2-order derivative for spectral reflectance, reciprocal, and logarithm. However, related research points out that traditional integer-order differential transformation ignores the gradual fractional differential information [18,19], especially for high-dimensional data sources such as hyperspectral images with massive information, which may cause some information to be lost or be difficult to extract, and restrict the modeling accuracy.Fractional calculus theory is a mathematical problem for studying the properties of differential and integral operators of any order and its application. First proposed in 1695, its development is almost in synchronization with the theory of integer-order calculus.…”