Hyperspectral Estimation of Soil Organic Carbon Content Based on Continuous Wavelet Transform and Successive Projection Algorithm in Arid Area of Xinjiang, China

Abstract

Soil organic carbon (SOC), an important indicator to evaluate soil fertility, is essential in agricultural production. The traditional methods of measuring SOC are time-consuming and expensive, and it is difficult for these methods to achieve large area measurements in a short time. Hyperspectral technology has obvious advantages in soil information analysis because of its high efficiency, convenience and non-polluting characteristics, which provides a new way to achieve large-scale and rapid SOC monitoring. The traditional mathematical transformation of spectral data in previous studies does not sufficiently reveal the correlation between the spectral data and SOC. To improve this issue, we combine the traditional method with the continuous wavelet transform (CWT) for spectral data processing. In addition, the feature bands are screened with the successive projection algorithm (SPA), and four machine learning algorithms are used to construct the SOC content estimation model. After the spectral data is processed by CWT, the sensitivity of the spectrum to the SOC content and the correlation between the spectrum and the SOC content can be significantly improved (p < 0.001). SPA was used to compress the spectral data at multiple decomposition scales, greatly reducing the number of bands containing covariance and enabling faster screening of the characteristic bands. The support vector machine regression (SVMR) model of CWT-R′ gave the best prediction, with the coefficients of determination (R2) and the root mean square error (RMSE) being 0.684 and 1.059 g∙kg−1, respectively, and relative analysis error (RPD) value of 1.797 for its validation set. The combination of CWT and SPA can uncover weak signals in the spectral data and remove redundant bands with covariance in the spectral data, thus realizing the screening of characteristic bands and the fast and stable estimation of the SOC content.

Soil Organic Carbon Prediction Based on Different Combinations of Hyperspectral Feature Selection and Regression Algorithms

“…In our study of the feature selection process for soil hyperspectral data, we found that the SPA effectively retained spectral feature information. This finding is consistent with previous studies on SOC estimation conducted by Peng et al [18] in Jiangsu and Hubei province, and Huang et al [33] in the Arid Area of Xinjiang. However, a study conducted in Romania found that mutual information is the optimal algorithm for screening soil spectral features [23].…”

Improving the Accuracy of Soil Organic Carbon Estimation: CWT-Random Frog-XGBoost as a Prerequisite Technique for In Situ Hyperspectral Analysis

“…Oases are non-zonal landscapes formed under dry climatic conditions with a desert substrate, lakes, and oasis land as main patches, supporting high agricultural productivity. Physicochemical processes in lakeside oasis soil environments are controlled by soil organic carbon (SOC), which is also a key determinant of soil fertility and agricultural potential [1,2]. Therefore, the rapid monitoring of the SOC content could provide a scientific basis for the rational development of land resources and precision agriculture.…”

“…Continuous wavelet transformation (CWT) has an excellent capability for time-frequency analysis, and it has potential as an effective method for enhancing the spectral response, characterizing local features of the spectral signal, and more effectively extracting information of small spectral features in soil [12]. It has also been proven to be effective as a pre-processing method [2,13]. The accuracy of SOC content estimation is affected by various factors, such as outdoor temperature, vegetation cover, soil surface roughness, wind, and the redundancy of the full-band spectra.…”

“…Previous studies have shown that the feature variables are not simply linearly related to soil organic matter [16]. Therefore, various nonlinear models have been widely used for the estimation of SOC contents, including extreme gradient boosting machine (XGBoost), back propagation neural network (BPNN), and random forest (RF) [2,19]. This study mainly focused on the ability of (in situ) hyperspectral imaging systems to estimate the SOC content in a lakeside oasis in the dry zone of Xinjiang.…”

Estimating Organic Matter Content in Hyperspectral Wetland Soil Using Marine-Predators-Algorithm-Based Random Forest and Multiple Differential Transformations

“…At the moment, differential transform and wavelet transform are the major preprocessing techniques used for SOM spectral reflectance data. In their study, Huang et al [5] focused on arid soil data and utilized a continuous wavelet transform with different scales to eliminate noise in the data. They combined it with a continuous projection algorithm for feature band extraction and used multiple regression methods to construct an inversion model of the soil organic carbon content.…”