Estimation Of Soil Organic Matter Research Articles

Local wavelet packet decomposition of soil hyperspectral for SOM estimation

It is a critical work to accurate extraction of spectral characteristics of soil organic matter (SOM), which will help to improve the model performance for SOM estimation. In this paper, we propose a new SOM prediction model using local wavelet characteristics of soil spectrum. Specifically, six level local wavelet packets decomposition are considered with different moving window sizes and sliding lengths, and thus formulate two new spectral indicators, namely, local wavelet packet energy spectrum (LWE) and local logarithmic wavelet packet energy spectrum (LLWE). The LWE and LLWE are then viewed as model inputs, which are respectively used to forecast SOM content. We test the prediction performance of the LWE and LLWE based on the two prediction models, that is, multiple linear regression (MLR) and ridge regression with cross-validation (RCV). The result shows that the two new spectral indicators help to enhance the spectral response information of SOM. Among the four prediction models, the LLWE-MLR is the most outstanding. Compared to the original hyperspectral and energy features vectors, the LWE and LLWE bring the better model performance. Since both the high and low-frequency components of local information of soil hyperspectral are fully extracted, the two new spectral indicators significantly improve the prediction accuracy and reliability of SOM.

A Remotely Sensed Framework for Spatially-Detailed Dryland Soil Organic Matter Mapping: Coupled Cross-Wavelet Transform with Fractional Vegetation and Soil-Related Endmember Time Series

Soil organic matter (SOM) plays pivotal roles in characterizing dryland structure and function; however, remotely sensed spatially-detailed SOM mapping in these regions remains a challenge. Various digital soil mapping approaches based on either single-period remote sensing or spectral indices in other ecosystems usually produce inaccurate, poorly constrained estimates of dryland SOM. Here, a framework for spatially-detailed SOM mapping was proposed based on cross-wavelet transform (XWT) that exploits ecologically meaningful features from intra-annual fractional vegetation and soil-related endmember records. In this framework, paired green vegetation (GV) and soil-related endmembers (i.e., dark surface (DA), saline land (SA), sand land (SL)) sequences were adopted to extract 30 XWT features in temporally and spatially continuous domains of cross-wavelet spectrum. We then selected representative features as exploratory covariates for SOM mapping, integrated with four state-of-the-art machine learning approaches, i.e., ridge regression (RR), least squares-support vector machines (LS-SVM), random forests (RF), and gradient boosted regression trees (GBRT). The results reported that SOM maps from 13 coupled filtered XWT features and four machine learning approaches were consistent with soil-landscape knowledge, as evidenced by a spatially-detailed gradient from oasis to barren. This framework also presented more accurate and reliable results than arithmetically averaged features of intra-annual endmembers and existing datasets. Among the four approaches, both RF and GBRT were more appropriate in the XWT-based framework, showing superior accuracy, robustness, and lower uncertainty. The XWT synthetically characterized soil fertility from the consecutive structure of intra-annual vegetation and soil-related endmember sequences. Therefore, the proposed framework improved the understanding of SOM and land degradation neutrality, potentially leading to more sustainable management of dryland systems.

Vis-NIR-spectroscopy- and loss-on-ignition-based functions to estimate organic matter content of calcareous soils

ABSTRACT The study was carried out to derive pedotransfer (PTFs) and spectrotransfer (STF) functions to estimate soil organic matter (SOM) content measured by time-consuming and expensive Walkley–Black wet combustion (W-B), using SOM content obtained from loss on ignition (LOI) and spectra reflectance bands at visible (Vis) and near infrared (NIR) regions. In total, 171 soil samples were collected from calcareous soils of southern Iran. The SOM content of the samples was determined using W–B wet combustion (SOMW-B) and LOI at temperatures of 360 °C during 2 h (LOI360-2); 550 °C during 3 h (LOI550-3); and 375°C during 16 h (LOI375-16). For the spectroscopy method, partial least squares regression (SpectPLSR) and forward stepwise multiple linear regression (SpectSMLR) approaches were used for function development. The LOI360-2 procedure with R2 val of 0.9 for the validation dataset provided the best match with SOMW-B content. Furthermore, the SpectSMLR provided a STF using spectral reflectance bands at 495, 730, 970, 1906, 2262 and 2342 nm which predicted SOMW-B with R2 val of 0.87. Results indicated both the SpectSMLR and LOI360-2, as easy and inexpensive approaches, could be recommended to accurately assess SOM content of calcareous soils.

Combining Variable Selection and Multiple Linear Regression for Soil Organic Matter and Total Nitrogen Estimation by DRIFT-MIR Spectroscopy

The successful estimation of soil organic matter (SOM) and soil total nitrogen (TN) contents with mid-infrared (MIR) reflectance spectroscopy depends on selecting appropriate variable selection techniques and multivariate methods for regression analysis. This study aimed to explore the potential of combining a multivariate method and spectral variable selection for soil SOM and TN estimation using MIR spectroscopy. Five hundred and ten topsoil samples were collected from Quzhou County, Hebei Province, China, and their SOM and TN contents and reflectance spectra were measured using DRIFT-MIR spectroscopy (diffuse reflectance infrared Fourier transform in the mid-infrared range, MIR, wavenumber: 4000–400 cm−1; wavelength: 2500–25,000 nm). Two multivariate methods (partial least-squares regression, PLSR; multiple linear regression, MLR) combined with two variable selection techniques (stability competitive adaptive reweighted sampling, sCARS; bootstrapping soft shrinkage approach, BOSS) were used for model calibration. The MLR model combined with the sCARS method yielded the most accurate estimation result for both SOM (Rp2 = 0.72 and RPD = 1.89) and TN (Rp2 = 0.84 and RPD = 2.50). Out of the 2382 wavenumbers in a full spectrum, sCARS determined that only 31 variables were important for SOM estimation (accounting for 1.30% of all variables) and 27 variables were important for TN estimation (accounting for 1.13% of all variables). The results demonstrated that sCARS was a highly efficient approach for extracting information on wavenumbers and mitigating redundant wavenumbers. In addition, the current study indicated that MLR, which is simpler than PLSR, when combined with spectral variable selection, can achieve high-precision prediction of SOM and TN content. As such, DRIFT-MIR spectroscopy coupled with MLR and sCARS is a good alternative for estimating the SOM and TN of soils.

Evaluation of Landsat 8 image pansharpening in estimating soil organic matter using multiple linear regression and artificial neural networks

ABSTRACT In agricultural systems, the regular monitoring of Soil Organic Matter (SOM) dynamics is essential. This task is costly and time-consuming when using the conventional method, especially in a very fragmented area and with intensive agricultural activity, such as the area of Sidi Bennour. The study area is located in the Doukkala irrigated perimeter in Morocco. Satellite data can provide an alternative and fill this gap at a low cost. Models to predict SOM from a satellite image, whether linear or nonlinear, have shown considerable interest. This study aims to compare SOM prediction using Multiple Linear Regression (MLR) and Artificial Neural Networks (ANN). A total of 368 points were collected at a depth of 0–30 cm and analyzed in the laboratory. An image at 15 m resolution (MSPAN) was produced from a 30 m resolution (MS) Landsat-8 image using image pansharpening processing and panchromatic band (15 m). The results obtained show that the MLR models predicted the SOM with (training/validation) R 2 values of 0.62/0.63 and 0.64/0.65 and RMSE values of 0.23/0.22 and 0.22/0.21 for the MS and MSPAN images, respectively. In contrast, the ANN models predicted SOM with R 2 values of 0.65/0.66 and 0.69/0.71 and RMSE values of 0.22/0.10 and 0.21/0.18 for the MS and MSPAN images, respectively. Image pansharpening improved the prediction accuracy by 2.60% and 4.30% and reduced the estimation error by 0.80% and 1.30% for the MLR and ANN models, respectively.

Influence of rhizosphere activity on litter decomposition in subtropical forest: implications of estimating soil organic matter contributions to soil respiration

AbstractLitter decomposition plays an important role in the carbon cycle and is affected by many factors in forest ecosystems. This study aimed to quantify the rhizosphere priming effect on litter decomposition in subtropical forest southwestern China. A litter decomposition experiment including control and trenching treatments was conducted using the litter bag method, and the litter decomposition rate was calculated by litter dry mass loss. Trenching did not change soil temperature, but increased the soil water content by 14.5%. In this study, the interaction of soil temperature and soil water content controlled the litter decomposition rate, and explained 87.4 and 85.5% of the variation in litter decomposition in the control and trenching treatments, respectively. Considering changes in soil environmental factors due to trenching, the litter decomposition rates were corrected by regression models. After correction, the litter decomposition rates of the control and trenching treatments were 32.47 ± 3.15 and 25.71 ± 2.72% year–1, respectively, in the 2-year period. Rhizosphere activity significantly primed litter decomposition by 26.3%. Our study suggested a priming effect of rhizosphere activity on litter decomposition in the subtropical forest. Combining previous interaction effect results, we estimated the contributions of total soil organic matter (SOM) decomposition, total litter decomposition, and root respiration to soil respiration in the subtropical forest, and our new method of estimating the components of soil respiration provided basic theory for SOM decomposition research.

Estimation of Soil Organic Matter in Arid Zones with Coupled Environmental Variables and Spectral Features.

The soil organic matter (SOM) content is a key factor affecting the function and health of soil ecosystems. For measurements of land reclamation and soil fertility, SOM monitoring using visible and near-infrared spectroscopy (Vis-NIR) is one approach to quantifying soil quality, and Vis-NIR is important for monitoring the SOM content in a broad and nondestructive manner. To investigate the influence of environmental factors and Vis-NIR spectroscopy in estimating SOM, 249 soil samples were collected from the Werigan–Kuqa oasis in Xinjiang, China, and their spectral reflectance, SOM content and soil salinity were measured. To classify and improve the prediction accuracy, we also take into account the soil salinity content as a variable indicator. Relevant environmental variables were extracted using remote sensing datasets (land-use/land-cover (LULC), digital elevation model (DEM), World Reference Base for Soil Resources (WRB), and soil texture). On the basis of Savitzky–Golay (S-G) smoothing and first derivative (FD) preprocessing of the original spectrum, three clusters were obtained by K-means clustering through the use of Vis-NIR and used as spectral classification variables. Using Vis-NIR as Model 1, Vis-NIR combined with spectral classification as Model 2, environmental variables as Model 3, and the combination of all the above variables (Vis-NIR, spectral classification, environmental variables, and soil salinity) as Model 4, a SOM content estimation model was constructed using partial least squares regression (PLSR). Using the 249 soil samples, the modeling set contained 166 samples and the validation set contained 83 samples. The results showed that Model 2 (validation r2 = 0.78) was better than Model 1 (validation r2 = 0.76). The prediction accuracy for Model 4 (validation r2 = 0.85) was better than Model 2 (validation r2 = 0.78). Among these, Model 3 was the worst (validation r2 = 0.39). Therefore, the combination of environmental variables with Vis-NIR spectroscopy to estimate SOM content is an important method and has important implications for improving the accuracy of SOM predictions in arid regions.

Application of Hyperspectral Technology Combined With Bat Algorithm-AdaBoost Model in Field Soil Nutrient Prediction

This paper proposes a hyperspectral soil nutrient estimation method based on the bat algorithm (BA)-AdaBoost model. The spectral reflectance, the first derivative of the reflectance, and the reciprocal logarithm of the reflectance are analyzed based on the 800 field soil samples and their hyperspectral data collected. The first derivative of the reciprocal logarithm of the reflectance and the sensitive band was extracted using the correlation coefficient method, and the correlation of the content of soil organic matter, phosphorus, and potassium was solved. The BA is used to optimize the two core parameters of the AdaBoost model (i.e., the maximum number of iterations (n) and the weight reduction coefficient (v) of the weak learner), the classification and regression trees(CART) decision tree is selected as the weak regression learner of the model, and the coefficient of determination is used as parameter optimization. Based on the objective function value, a BA-AdaBoost model was constructed to estimate soil organic matter and phosphorus and potassium contents. The results show that the BA-AdaBoost combined model can better search for globally optimal parameters. The AdaBoost model optimized by BA significantly improved accuracy and reliability. Among the three elements, soil organic matter estimation accuracy is the highest, and the coefficient of determination and the root mean square error are 0.867 and 0.151g ∙ kg <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-1</sup> , respectively. Compared with the model before optimization, the model accuracy and reliability improved by 29.0% and 24.1%, respectively. The results indicate that hyperspectral technology combined with the BA-AdaBoost model has certain application prospects in field soil nutrient estimation.

Do model choice and sample ratios separately or simultaneously influence soil organic matter prediction?

This study was performed to examine the separate and simultaneous influence of predictive models’ choice alongside sample ratios selection in soil organic matter (SOM). The research was carried out in northern Morocco, characterized by relatively cold weather and diverse geological conditions. The dataset herein used accounted for 1591 soil samples, which were randomly split into the following ratios: 10% (∼150 sample ratio), 20% (∼250 sample ratio), 35% (∼450 sample ratio), 50% (∼600 sample ratio) and 95% (∼1200 sample ratio). Models herein involved were ordinary kriging (OK), regression kriging (RK), multiple linear regression (MLR), random forest (RF), quantile regression forest (QRF), Gaussian process regression (GPR) and an ensemble model. The findings in the study showed that the accuracy of SOM prediction is sensitive to both predictive models and sample ratios. OK combined with 95% sample ratio performed equally to RF in conjunction with all the sample ratios, as the latter did not show much sensitivity to sample ratios. ANOVA results revealed that RF with a ∼10% sample ratio could also be optimum for predicting SOM in the study area. In conclusion, the findings herein reported could be instrumental for producing cost-effective detailed and accurate spatial estimation of SOM in other sites. Furthermore, they could serve as a baseline study for future research in the region or elsewhere. Therefore, we recommend conducting series of simulation of all possible combinations between various predictive models and sample ratios as a preliminary step in soil organic matter prediction.

Rapid assessment of soil water repellency indices using Vis-NIR spectroscopy and pedo-transfer functions

Soil water repellency (SWR) is an important soil physical property that may restrict water infiltration and soil water retention. Common laboratory and field techniques for assessing SWR are laborious, time-consuming, and costly. Meanwhile, Visible–Near-Infrared (Vis-NIR) spectroscopy has been reported as a rapid, cost-effective, and alternative technique to estimate several soil properties. To investigate the efficacy of this technique for predicting SWR indices [soil water repellency index (RI) and soil–water contact angle (β)] at dry condition, 100 soil samples collected from farmlands, orchards, rangelands and forests of Zrêbar lake watershed in Kurdistan province, Iran, were measured by Vis-NIR spectroscopy within the 350–2500 nm range. The Savitzky–Golay first derivative method was applied for denoising the spectral data. The RI and β were measured by the intrinsic sorptivity method (using water and ethanol as absorbing liquids). The other basic soil properties were also measured by standard laboratory methods. Stepwise multiple linear regression (SMLR) and partial least squares regression (PLSR) were utilized to establish pedo-transfer functions (PTFs) and spectro-transfer functions (STFs) using basic soil properties and spectral absorbance data, respectively, to estimate soil organic matter (SOM) content and SWR indices. We obtained good predictions for SOM with R2 = 0.67 and RPIQ (the ratio of performance to interquartile range) = 1.92 using the PLSR-based STF. The results also revealed that although the SMLR-based STFs achieved slightly better estimates of the SWR indices (RI and β) than the SMLR-based PTFs (R2 values of 0.28 to 0.39 vs. 0.19 to 0.23, respectively); but, overall, none of these transfer functions for estimating these indices showed acceptable predictive capability. However, the PLSR-based STFs could provide a reasonable prediction for the studied SWR indices (R2 > 0.52 and RPIQ > 2.27). The majority of important adsorption bands in the Vis-NIR PLSR models for the SWR prediction was related to both the quantity and quality of SOM. Overall, the results demonstrated that the Vis-NIR PLSR could be applied to predict SOM and SWR indices rapidly, non-destructively, and with fair accuracy.

Predicting spatial distribution of soil organic matter using regression approaches at the regional scale (Eastern Azerbaijan, Iran).

Soil organic matter (SOM) is one of the important factors in arid and semiarid areas, which describes the soil quality. Spatial estimation of SOM is important to understand the SOM storage and the emphasis of the SOM in the global carbon cycle and environmental issues. Mapping of SOM content can have significant uses in environmental modeling. In the current study, various methods have been evaluated for estimating the SOM content through soil samples and using auxiliary variables in the west of Eastern Azerbaijan province, Iran. In this study, support vector machine (SVM), multi-factor regression (MFR), and multi-factor weighted regression model (MWRM) approaches have been suggested for predicting and investigating the spatial distribution of SOM. In total, 155 surface soil samples (from the depth of 0 to 30cm) were obtained. These soil samples were randomly divided into training data set (105 soil samples) and testing data set (50 samples). According to the results, SOM is affected by soil properties as well as environmental factors (normalized difference vegetation index (NDVI)). In this study, clay, silt/sand, NDVI, and soil moisture were used as auxiliary variables in the estimation of SOM. Three methods were compared to determine a suitable method for spatial estimation of SOM, and results showed that SVM has the lowest estimation error (RMSE = 0.100, MAE = 0.07, and MRE = 3.32) and highest regression coefficient (R2 = 0.719) during SOM estimation. The present results show the indirect effect of elevation by controlling auxiliary variables and confirm the importance of auxiliary variables in spatial distribution patterns of SOM.

Evaluating the Precision and Accuracy of Proximal Soil vis–NIR Sensors for Estimating Soil Organic Matter and Texture

Measuring soil texture and soil organic matter (SOM) is essential given the way they affect the availability of crop nutrients and water during the growing season. Among the different proximal soil sensing (PSS) technologies, diffuse reflectance spectroscopy (DRS) has been deployed to conduct rapid soil measurements in situ. This technique is indirect and, therefore, requires site- and data-specific calibration. The quality of soil spectra is affected by the level of soil preparation and can be accessed through the repeatability (precision) and predictability (accuracy) of unbiased measurements and their combinations. The aim of this research was twofold: First, to develop a novel method to improve data processing, focusing on the reproducibility of individual soil reflectance spectral elements of the visible and near-infrared (vis–NIR) kind, obtained using a commercial portable soil profiling tool, and their direct link with a selected set of soil attributes. Second, to assess both the precision and accuracy of the vis–NIR hyperspectral soil reflectance measurements and their derivatives, while predicting the percentages of sand, clay and SOM content, in situ as well as in laboratory conditions. Nineteen locations in three agricultural fields were identified to represent an extensive range of soils, varying from sand to clay loam. All measurements were repeated three times and a ratio spread over error (RSE) was used as the main indicator of the ability of each spectral parameter to distinguish among field locations with different soil attributes. Both simple linear regression (SLR) and partial least squares regression (PLSR) models were used to define the predictability of % SOM, % sand, and % clay. The results indicated that when using a SLR, the standard error of prediction (SEP) for sand was about 10–12%, with no significant difference between in situ and ex situ measurements. The percentage of clay, on the other hand, had 3–4% SEP and 1–2% measurement precision (MP), indicating both the reproducibility of the spectra and the ability of a SLR to accurately predict clay. The SEP for SOM was only a quarter lower than the standard deviation of laboratory measurements, indicating that SLR is not an appropriate model for this soil property for the given set of soils. In addition, the MPs of around 2–4% indicated relatively strong spectra reproducibility, which indicated the need for more expanded models. This was apparent since the SEP of PLSR was always 2–3 times smaller than that of SLR. However, the relatively small number of test locations limited the ability to develop widely applicable calibration models. The most important finding in this study is that the majority of vis–NIR spectral measurements were sufficiently reproducible to be considered for distinguishing among diverse soil samples, while certain parts of the spectra indicate the capability to achieve this at α = 0.05. Therefore, the innovative methodology of evaluating both the precision and accuracy of DRS measurements will help future developers evaluate the robustness and applicability of any PSS instrument.

Comparative Analysis for Grey Relation Estimation Models of Soil Organic Matter based on Hyperspectral Data

Rapid and accurate acquisition of farmland soil organic matter content is of great significance for the rapid monitoring soil fertility and the development of precision agriculture. Based on the hyperspectral data and organic matter content data of 74 soil samples in Zhangqiu District, Jinan City, Shandong Province, first transform soil spectral reflectance by the logarithm of the first-order differential, square, reciprocal, logarithm and square root, the estimation factors were selected according to the principle of maximum relation. Second, the hyperspectral estimation of soil organic matter was carried out by using six models such as grey close relation degree, and the estimation results of different methods were combined and analyzed. The results show that the combined grey relation model can effectively improve the estimation accuracy, and the average relative error of 16 test samples is 8.931%. Studies have shown that using the combined model of grey relation degree to estimate soil organic matter content with hyperspectral data is valid.

Soil Nutrient Estimation and Mapping in Farmland Based on UAV Imaging Spectrometry.

Soil nutrient is one of the most important properties for improving farmland quality and product. Imaging spectrometry has the potential for rapid acquisition and real-time monitoring of soil characteristics. This study aims to explore the preprocessing and modeling methods of hyperspectral images obtained from an unmanned aerial vehicle (UAV) platform for estimating the soil organic matter (SOM) and soil total nitrogen (STN) in farmland. The results showed that: (1) Multiplicative Scattering Correction (MSC) performed better in reducing image scattering noise than Standard Normal Variate (SNV) transformation or spectral derivatives, and it yielded a result with higher correlation and lower signal-to-noise ratio; (2) The proposed feature selection method combining Successive Projections Algorithm (SPA) and Competitive Adaptive Reweighted Sampling algorithm (CARS), could provide selective preference for hyperspectral bands. Exploiting this method, 24 and 22 feature bands were selected for SOM and STN estimation, respectively; (3) The particle swarm optimization (PSO) algorithm was employed to obtain optimized input weights and bias values of the extreme learning machine (ELM) model for more accurate prediction of SOM and STN. The improved PSO-ELM model based on the selected preference bands achieved higher prediction accuracy (R2 of 0.73 and RPD of 1.91 for SOM, R2 of 0.63, and RPD of 1.53 for STN) than support vector machine (SVM), partial least squares regression (PLSR), and the ELM model. This study provides an important guideline for monitoring soil nutrient for precision agriculture with imaging spectrometry.

Hyperspectral estimation of soil organic matter and clay content in loess plateau of China

AbstractVisible and near‐infrared reflectance (Vis‐NIR) spectroscopy is considered a promising tool for the estimation of soil properties. Soil clay content and soil organic matter (SOM) are main components affecting soil spectra. Accurate assessment of clay content and SOM is essential before achieving accurate prediction for other soil properties. Selecting the proper spectral transformation technique and optimal calibration method are important processes to improve model performance. In this study, a total of 240 soil samples were collected from the main area of winter wheat (Triticum aestivum L.) fields in the Southwest region of Shanxi province, northern China. Six spectral pre‐treatments and three multivariate methods were utilized to realize the estimation of clay content and SOM. Finally, the important spectral wavelengths were identified as 440, 762, 1,150, 1,410, 1,460, 1,860, 1,900, 2,250, 2,400 nm for clay content and 410, 450, 550, 625, 780, 850, 1,410, 1,670, 1,730, 1,860, 1,910, 1,960, 2,250 nm for SOM. Specifically, the wavelengths around 440 (450), 1,900 (1,910) nm and wavebands of 1,410, 1,860, and 2,250 nm were highly related to both clay content and SOM. The optimal prediction was obtained when multiple linear regression (MLR) was combined with standard normal variate (SNV) pre‐processing (R2 = .714, RMSE = 3.982, RPD = 1.584) for clay content and multiplicative scatter correction (MSC) pre‐processing (R2 = .856, RMSE = 2.994, RPD = 2.443) for SOM. This study implied that spectral transformation had an evident effect on spectral curves shape, correlation, and model performance. The choice of pre‐processing transformation should depend on the multivariate technique which has a determined ability to improve the model accuracy.

Hyper-spectral estimation of soil organic matter in apple orchard based on CWT

In the quantitative estimation by spectra of soil organic matter (SOM), there are great difficulties in the extraction of characteristic spectral information. It is difficult to effectively improve the correlation with SOM by ordinary spectral transformations, and the spectral estimation models are not high in accuracy and applicability. The purpose of this paper is to explore a more accurate and more suitable non-destructive evaluation model for apple orchard soil. In this paper, an apple orchard in Shuangquan Town, Changqing District, Jinan City, was selected as the study area. The continuous wavelet transform (CWT) was used to process the original soil spectra at multiple scales, and the effect of the estimation model on the SOM correlation at different resolutions was investigated. The results showed that the CWT treatment significantly improved the degree of spectral response to SOM in the orchard. Compared with the original spectra, the prediction accuracy of the model constructed by CWT was higher. After wavelet algorithm processing, the prediction ability of the model tends to increase with the decrease of spectral resolution. The best prediction accuracy was found at the spectral resolution of 20 nm, with the coefficient of determination R2= 0.7547 and the root means square error RMSE=0.0042; the validation accuracy R2=0.8015 and the root mean square error RMSE=0.0039. The model achieved a more satisfactory prediction result at the spectral resolution of 5 nm also. The results show that the broad-band spectral data processed by CWT can be used for accurate monitoring of SOM in apple orchards.

Estimating and mapping of soil organic matter content in a typical river basin of the Qinghai-Tibet Plateau

Spectroscopy is a fast, non-destructive, and cheap method, which has been widely used in the estimation of soil organic matter (SOM) concentration. This study presented a methodology to estimate and map SOM content by crop canopy reflectance spectra combining with land parameters in the Yarlung Zangbo River (YZR) basin. The reflectance spectra of the oat canopy were collected in the field, and then were processed by savitzky-golay filtering (S-G), continuous removal (CR), and first derivative of reflectivity (FDR). The principal components were extracted from the processed spectral data. Land parameters such as elevation, slope, NDVI, and land surface temperature (LST) were selected to establish 18 models to estimate SOM content. The results showed that the estimation accuracy of SOM content could be improved by combining crop canopy reflectance spectra with land parameters. FDR-BPNN model with land parameters had the best estimation effect (R2 = 0.973, MAE = 0.847 g·kg−1).

Partial Least Squares Improved Multivariate Adaptive Regression Splines for Visible and Near-Infrared-Based Soil Organic Matter Estimation Considering Spatial Heterogeneity

Under the influence of complex environmental conditions, the spatial heterogeneity of soil organic matter (SOM) is inevitable, and the relationship between SOM and visible and near-infrared (VNIR) spectra has the potential to be nonlinear. However, conventional VNIR-based methods for soil organic matter estimation cannot simultaneously consider the potential nonlinear relationship between the explanatory variables and predictors and the spatial heterogeneity of the relationship. Thus, the regional application of existing VNIR spectra-based SOM estimation methods is limited. This study combines the proposed partial least squares–based multivariate adaptive regression spline (PLS–MARS) method and a regional multi-variable associate rule mining and Rank–Kennard-Stone method (MVARC-R-KS) to construct a nonlinear prediction model to realize local optimality considering spatial heterogeneity. First, the MVARC-R-KS method is utilized to select representative samples and alleviate the sample global underrepresentation caused by spatial heterogeneity. Second, the PLS–MARS method is proposed to construct a nonlinear VNIR spectra-based estimation model with local optimization based on selected representative samples. PLS–MARS combined with the MVARC-R-KS method is illustrated and validated through a case study of Jianghan Plain in Hubei Province, China. Results showed that the proposed method far outweighs some available methods in terms of accuracy and robustness, suggesting the reliability of the proposed prediction model.

Reducing the Moisture Effect and Improving the Prediction of Soil Organic Matter With VIS-NIR Spectroscopy in Black Soil Area

Soil organic matter (SOM) is rich in black soil area. It has a significant effect on soil health and luxuriant vegetation. The agricultural production activities can thus be guided by measurements of SOM at different periods. Most of previous work estimated SOM using reflectance spectra measurements on dried soil samples, to remove the effect of soil moisture content (SMC). However, it is time-consuming and almost conduct-prohibitive in the field. In this study, we utilized the continuous wavelet transform (CWT) on visible (VIS) and near infrared (NIR) spectra to test its effect on eliminating the SMC influence, and proposed to use the PCA-RF method coupled with CWT to predict SOM from the wet samples. Multi-scale coefficients can amplify the response of spectra to SOM in varying degrees, while improving the correlation of characteristic wavebands and minimizing the moisture interference on SOM specific wavelength. By analysing the multi-scale coefficients, we found that wavelengths ranging around the peaks of $580nm$ , $820nm$ , and especially the narrow region around $1400nm$ are highly correlated regions to SOM. Furthermore, the accuracy of SOM estimation models illustrated the effectiveness of the CWT. Results of the validation model using the dataset of wet samples on CWT scale 6 ( $R^{2}$ = 0.84, $Mse$ = 0.23%, and $RPD$ = 2.53) can be statistically equivalent to dataset of dried samples ( $R^{2}$ = 0.86, $Mse$ = 0.20%, and $RPD$ = 2.68). Combined with the PCA-RF method, SOM estimation can be perfectly performed with fewer features as input variables and has a great improved. The best prediction of validation model was on scale 6 with features extracted from 4 PCs, compared with the EPO-PLSR method ( $R^{2}$ = 0.85, $Mse$ = 0.25%, and $RPD$ = 2.54), the proposed method has a better result ( $R^{2}$ = 0.94, $Mse$ = 0.09%, and $RPD$ = 4.08).

Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in Shanghai

Soil organic matter (SOM) plays an important role in the field of climate change and terrestrial ecosystems. SOM in large areas, especially in urban areas, is difficult to monitor and estimate by traditional methods. Urban land structure is complex, and soil is a mixture of organic and inorganic constituents with different physical and chemical properties. Previous studies showed that remote sensing techniques that provide diverse data in the visible-near-infrared (VNIR)-shortwave infrared (SWIR) spectral range, are promising in the prediction of SOM content on a large scale. Sentinel-2 covers the important spectral bands (VNIR-SWIR) for SOM prediction with a short revisit time. Thus, this article aimed to evaluate the capacity of Sentinel-2 for SOM prediction in an urban area (i.e., Shanghai). 103 bare soil samples filtrated from 398 soil samples at a depth of 20 cm were selected. Three methods, partial least square regression (PLSR), artificial neural network (ANN), and support vector machine (SVM), were applied. The root mean square error (RMSE) of modelling (mRMSE) and the coefficient of determination ( $R^{2}$ ) of modelling $(mR^{2})$ were used to reflect the accuracy of the model. The results show that PLSR has the poorest performance. ANN has the highest modelling accuracy (mRMSE = 7.387 g kg $^{-1}$ , $mR^{2}=0.446$ ). The ANN prediction accuracy of RMSE (pRMSE) is 4.713 g kg $^{-1}$ and the prediction accuracy of $R^{2}~(pR^{2})$ is 0.723. For SVR, the pRMSE is 4.638 g kg $^{-1}$ , and the $pR^{2}$ is 0.732. The prediction accuracy of SVR is slightly higher than that of ANN. The spatial distribution of SOM demonstrates that the value obtained by ANN is the closest to the range of the bare soil samples, and ANN performs better in vegetation-covered areas. Therefore, Sentinel-2 can be used to estimate SOM content in urban areas, and ANN is a promising method for SOM estimation.