Soil Organic Carbon Prediction Accuracy Research Articles

Soil Organic Carbon Prediction Based on Vis-NIR Spectral Classification Data Using GWPCA-FCM Algorithm.

Soil visible and near-infrared reflectance spectroscopy is an effective tool for the rapid estimation of soil organic carbon (SOC). The development of spectroscopic technology has increased the application of spectral libraries for SOC research. However, the direct application of spectral libraries for SOC prediction remains challenging due to the high variability in soil types and soil-forming factors. This study aims to address this challenge by improving SOC prediction accuracy through spectral classification. We utilized the European Land Use and Cover Area frame Survey (LUCAS) large-scale spectral library and employed a geographically weighted principal component analysis (GWPCA) combined with a fuzzy c-means (FCM) clustering algorithm to classify the spectra. Subsequently, we used partial least squares regression (PLSR) and the Cubist model for SOC prediction. Additionally, we classified the soil data by land cover types and compared the classification prediction results with those obtained from spectral classification. The results showed that (1) the GWPCA-FCM-Cubist model yielded the best predictions, with an average accuracy of R2 = 0.83 and RPIQ = 2.95, representing improvements of 10.33% and 18.00% in R2 and RPIQ, respectively, compared to unclassified full sample modeling. (2) The accuracy of spectral classification modeling based on GWPCA-FCM was significantly superior to that of land cover type classification modeling. Specifically, there was a 7.64% and 14.22% improvement in R2 and RPIQ, respectively, under PLSR, and a 13.36% and 29.10% improvement in R2 and RPIQ, respectively, under Cubist. (3) Overall, the prediction accuracy of Cubist models was better than that of PLSR models. These findings indicate that the application of GWPCA and FCM clustering in conjunction with the Cubist modeling technique can significantly enhance the prediction accuracy of SOC from large-scale spectral libraries.

Coupling of microbial-explicit model and machine learning improves the prediction and turnover process simulation of soil organic carbon

Modeling soil organic carbon (SOC) is helpful for understanding its distribution and turnover processes, which can guide the implementation of effective measures for carbon (C) sequestration and enhance land productivity. Process-based simulation with high interpretability and extrapolation, and machine learning modeling with high flexibility are two common methods for investigating SOC distribution and turnover. To take advantage of both methods, we developed a hybrid model by coupling of a two-carbon pool microbial model and machine learning for SOC modeling. Here, we assessed the SOC model's predictive, mapping, and interpretability capabilities for the SOC turnover process on Ningbo region. The results indicate that the microbial model with density-dependence (β ​= ​2) and microbial biomass carbon simulation performed better in modeling the parameters of the microbial-based C cycle, such as microbial carbon use efficiency (CUE), microbial mortality rate, and assimilation rate. By integrating this optimal microbial model and random forest (RF) model, the hybrid model improved the prediction accuracy of SOC, with an increased R2 from 0.74 to 0.84, residual prediction deviation increased from 1.97 to 2.50, and reduced the root-mean-square error from 4.65 to 3.67 ​g ​kg−1 compared to the conventional RF model. As a result, the predicted SOC distribution exhibited high spatial variation and provided abundant details. Microbial CUE and potential C input, represented by net primary productivity, emerged as the primary factors driving SOC distribution in Ningbo region. Projections of SOC under the CMIP6 SSP2-4.5 scenario revealed that regional C loss in high SOC areas was mainly caused by decreased microbial CUE and C input, induced by climate change. Our findings highlight the potential of combining the microbial-explicit model and machine learning to improve SOC prediction accuracy and understand SOC feedback in a changing climate.

Improving soil organic carbon mapping in farmlands using machine learning models and complex cropping system information

Obtaining accurate spatial maps of soil organic carbon (SOC) in farmlands is crucial for assessing soil quality and achieving precision agriculture. The cropping system is an important factor that affects the soil carbon cycle in farmlands, and different agricultural managements under different cropping systems lead to spatial heterogeneity of SOC. However, current research often ignores differences in the main controlling factors of SOC under different cropping systems, especially when the cropping pattern is complex, which is not conducive to farmland zoning management. This study aims to (i) obtain the spatial distribution map of six cropping systems by using multi-phase HJ-CCD satellite images; (ii) explore the stratified heterogeneous relationship between SOC and environmental variables under different cropping systems by using the Cubist model; and (iii) predict the spatial map of SOC. The Xiantao, Tianmen, and Qianjiang cities, which are the core agricultural areas of the Jianghan Plain, were selected as the study area. Results showed that the SOC content in rice–wheat rotation was the highest among the six cropping systems. The Cubist model outperformed random forest, ordinary kriging, and multiple linear regression in SOC mapping. The results of the Cubist model showed that cropping system, climate, soil attributes, and vegetation index were important influencing factors of SOC in farmlands. The main controlling factors of SOC under different cropping systems were different. Specifically, summer crop types had a greater influence on spatial variations in SOC than winter crops. Paddy–upland rotation was more affected by river distance and NDVI, while upland–upland rotation was more affected by irrigation-related factors. This work highlights the differentiated main controlling factors of SOC under different cropping systems and provides data support for farmland zoning management. The Cubist model can improve the prediction accuracy of SOC under complex cropping systems.

Exploring the inter-decadal variability of soil organic carbon in China

Spatiotemporal variability in soil organic carbon (SOC) plays key roles in ecosystem stability and terrestrial carbon cycling. However, the inter-decadal characteristics of SOC variability and its climate drivers in China from the 1980s to 2010s remain unclear. In this study, a modeling framework for combining spatiotemporal prediction models was proposed. Within this model, soil samples from each of the two periods were combined and calibrated to obtain three models, and their prediction outputs were selectively combined to obtain SOC maps for the different inter-decadal periods. A total of 8473 soil samples from three periods (1980s, 2000s and 2010s) were used for model validation. The results suggested that the SOC prediction accuracy in the top 0–20 cm of soil (SOC020) was better than that of the first meter of soil (SOC0100), and the predicted spatial patterns shared characteristics with findings from previous studies. Predictions for the 1990s exhibited relatively high uncertainty, especially in the Tibetan Plateau, Tien Shan, and Northeast China. Both individual and coupled climatic factors exerted scale- and location-specific effects on the SOC. Coupled climatic factors accounted for more than 65% of the SOC variability in both soil layers. The regional SOC in North and Northeast China exhibited inter-decadal decline. Soil in China functioned as carbon sinks from the 1980s to 2010s at a national scale, with SOC020 increasing from 30.40 Pg to 33.97 Pg and SOC0100 from 79.29 Pg to 82.26 Pg. Overall, our results provide reliable baseline data for optimizing carbon cycle models of terrestrial ecosystems, and to guide future carbon sequestration policies.

Illumination levels affect the prediction of soil organic carbon using smartphone-based digital images

Soil organic carbon (SOC) analyses based on wet chemistry are labor-intensive and time-consuming and smartphone-based digital images have been used as a rapid, and low-cost alternative for the assessment of SOC content. We explored the effect of four illumination levels (300, 600, 900, and 1,200 lx) on the prediction accuracy of SOC using smartphone-based digital images. A total of 611 surfaces (0–20 cm) soil samples were collected from under pasture, agriculture, and in a former lakebed. Under controlled conditions, digital images were captured using an Apple iPhone 11 under four illumination levels. A total of 5 color coordinates (RGB, HSV, CIE L*a*b*, CIE L*u*v*, and CIE XYZ) were extracted from the images for each illumination level, and these were used to predict SOC by means of Lasso, elastic net (en), ridge, random forest (rf), and support vector machine (svm) models. The R, G, B, S, V, L*, a*, b*, u*, v*, X, Y, and Z color parameters were significantly affected (P < 0.05) by the illumination levels. The 300 lx illumination level had a fair prediction accuracy for SOC (r2 = 0.42 to 0.70) using random forest. The a*, R, and H color parameters were the best variables based on the 300 lx dataset for the prediction of SOC. We conclude that illumination levels significantly affected the prediction accuracy of SOC; lower illumination levels improved the prediction accuracy of SOC content.

Exploring the Impacts of Data Source, Model Types and Spatial Scales on the Soil Organic Carbon Prediction: A Case Study in the Red Soil Hilly Region of Southern China

Rapid and accurate mapping of soil organic carbon (SOC) is of great significance to understanding the spatial patterns of soil fertility and conducting soil carbon cycle research. Previous studies have dedicated considerable efforts to the spatial prediction of SOC content, but few have systematically quantified the effects of environmental covariates selection, the spatial scales and the model types on SOC prediction accuracy. Here, we spatially predicted SOC content through digital soil mapping (DSM) based on 186 topsoil (0–20 cm) samples in a typical hilly red soil region of southern China. Specifically, we first determined an optimal covariate set from different combinations of multiple environmental variables, including multi-sensor remote sensing images (Sentinel-1 and Sentinel-2), climate variables and DEM derivatives. Furthermore, we evaluated the impacts of spatial resolution (10 m, 30 m, 90 m, 250 m and 1000 m) of covariates and the model types (three linear and three non-linear machine learning techniques) on the SOC prediction. The results of the performance analysis showed that a combination of Sentinel-1/2-derived variables, climate and topographic predictors generated the best predictive performance. Among all variables, remote sensing covariates, especially Sentinel-2-derived predictors, were identified as the most important explanatory variables controlling the variability of SOC content. Moreover, the prediction accuracy declined significantly with the increased spatial scales and achieved the highest using the XGBoost model at 10 m resolution. Notably, non-linear machine learners yielded superior predictive capability in contrast with linear models in predicting SOC. Overall, our findings revealed that the optimal combination of predictor variables, spatial resolution and modeling techniques could considerably improve the prediction accuracy of the SOC content. Particularly, freely accessible Sentinel series satellites showed great potential in high-resolution digital mapping of soil properties.

Impact of Atmospheric Correction Methods Parametrization on Soil Organic Carbon Estimation Based on Hyperion Hyperspectral Data

Visible Near infrared and Shortwave Infrared (VNIR/SWIR, 400–2500 nm) remote sensing data is becoming a tool for topsoil properties mapping, bringing spatial information for environmental modeling and land use management. These topsoil properties estimates are based on regression models, linking a key topsoil property to VNIR/SWIR reflectance data. Therefore, the regression model’s performances depend on the quality of both topsoil property analysis (measured on laboratory over-ground soil samples) and Bottom-of-Atmosphere (BOA) VNIR/SWIR reflectance which are retrieved from Top-Of-Atmosphere radiance using atmospheric correction (AC) methods. This paper examines the sensitivity of soil organic carbon (SOC) estimation to BOA images depending on two parameters used in AC methods: aerosol optical depth (AOD) in the FLAASH (Fast Line-of-Sight Atmospheric Analysis of Spectral Hypercubes) method and water vapor (WV) in the ATCOR (ATmospheric CORrection) method. This work was based on Earth Observing-1 Hyperion Hyperspectral data acquired over a cultivated area in Australia in 2006. Hyperion radiance data were converted to BOA reflectance using seven values of AOD (from 0.2 to 1.4) and six values of WV (from 0.4 to 5 cm), in FLAASH and ATCOR, respectively. Then a Partial Least Squares regression (PLSR) model was built from each Hyperion BOA data to estimate SOC over bare soil pixels. This study demonstrated that the PLSR models were insensitive to the AOD variation used in the FLAASH method, with R2cv and RMSEcv of 0.79 and 0.4%, respectively. The PLSR models were slightly sensitive to the WV variation used in the ATCOR method, with R2cv ranging from 0.72 to 0.79 and RMSEcv ranging from 0.41 to 0.47. Regardless of the AOD values, the PLSR model based on the best parametrization of the ATCOR model provided similar SOC prediction accuracy to PLSR models using the FLAASH method. Variation in AOD using the FLAASH method did not impact the identification of bare soil pixels coverage which corresponded to 82.35% of the study area, while a variation in WV using the ATCOR method provided a variation of bare soil pixels coverage from 75.04 to 84.04%. Therefore, this work recommends (1) the use of the FLAASH AC method to provide BOA reflectance values from Earth Observing-1 Hyperion Hyperspectral data before SOC mapping or (2) a careful selection of the WV parameter when using ATCOR.

Estimation of Soil Organic Carbon Using Vis-NIR Spectral Data and Spectral Feature Bands Selection in Southern Xinjiang, China.

Soil organic carbon (SOC) plays an important role in the global carbon cycle and soil fertility supply. Rapid and accurate estimation of SOC content could provide critical information for crop production, soil management and soil carbon pool regulation. Many researchers have confirmed the feasibility and great potential of visible and near-infrared (Vis-NIR) spectroscopy in evaluating SOC content rapidly and accurately. Here, to evaluate the feasibility of different spectral bands variable selection methods for SOC prediction, we collected a total of 330 surface soil samples from the cotton field in the Alar Reclamation area in the southern part of Xinjiang, which is located in the arid region of northwest China. Then, we estimated the SOC content using laboratory Vis-NIR spectral. The Particle Swarm optimization (PSO), Competitive adaptive reweighted sampling (CARS) and Ant colony optimization (ACO) were adopted to select SOC feature bands. The partial least squares regression (PLSR), random forest (RF) and convolutional neural network (CNN) inversion models were constructed by using full-bands (400–2400 nm) spectra (R) and feature bands, respectively. And we also analyzed the effects of spectral feature band selection methods and modeling methods on the prediction accuracy of SOC. The results indicated that: (1) There are significant differences in the feature bands selected using different methods. The feature bands selected methods substantially reduced the spectral variable dimensionality and model complexity. The models built by the feature bands selected by CARS, PSO and ACO methods showed the different potential of improvement in model accuracy compared with the full-band models. (2) The CNN model had the best performance for predicting SOC. The R2 of the optimal CNN model is 0.90 in the validation, which was improved by 0.05 and 0.04 in comparison with the PLSR and RF model, respectively. (3) The highest prediction accuracy was archived by the CNN model using the feature bands selected by CARS (validation set R2 = 0.90, RMSE = 0.97 g kg−1, RPD = 3.18, RPIQ = 3.11). This study indicated that using the CARS method to select spectral feature bands, combined with the CNN modeling method can well predict SOC content with higher accuracy.

Prediction of topsoil organic carbon content with Sentinel-2 imagery and spectroscopic measurements under different conditions using an ensemble model approach with multiple pre-treatment combinations

Estimating soil organic carbon (SOC) using visible near infrared (Vis-NIR) spectroscopy has proven to be a rapid and reliable approach. However, when working across large geographical scales, remote sensing may be more suitable. Acquiring these spectra data normally under different measurement conditions could introduce artefacts that reduce SOC prediction accuracy. A common procedure has been using calibration or multivariate techniques in conjunction with one or more pre-treatment algorithms. The results of several comparative studies based on these predictive calibration techniques used alone were inconsistent. Moreover, protocols to select the most appropriate pre-treatment algorithms rarely exist. This study combines predictions from different techniques into a single model based on an ensemble learning approach. The main objective is to improve the accuracy of SOC prediction by assessing the effectiveness of using different calibration techniques individually against an ensemble model consisting of one statistical method, which includes partial least squares regression (PLSR), and three machine learning (ML) algorithms, including random forest (RF), support vector machine regression (SVMR), and Cubist. Several pre-treatment algorithms were also employed to improve the spectral data before prediction. Spectra data were collected from three different agricultural fields (with different soil types), under different spectral measurement conditions (field, wet and dry). Additionally, Sentinel-2 (S2) data was collected from one of these fields. Furthermore, to ascertain the effectiveness of the developed model on regional scale dataset, two options were employed: (1) merged data from all fields, and (2) merged data from fields measured under the same spectral measurement conditions. The models were evaluated using root mean square error of prediction (RMSEPCV), the coefficient of determination (R²CV), the ratio of performance to interquartile range (RPIQ), the ratio of performance to deviation (RPD) and BIAS. The results show that, across the three agricultural fields, the ensemble model predicted SOC more accurately than each of the individual calibration techniques (R2CV = 0.92, RMSEPCV (g/kg) = 1.00, RPD = 3.06, RPIQ = 3.74, BIAS (g/kg) = 0.067). The models derived from merged data (regional dataset) show that the ensemble approach predicted SOC more accurately with option 2 than option 1. Finally, while the ensemble model improves SOC accuracy with S2 data, the final output was poor. Further research to determine the underlying problem is strongly recommended. Nonetheless, these results indicate that the ensemble model is advantageous because it improved the prediction accuracy of SOC and reduced the error margin.

Improving the spatial prediction of soil organic carbon using environmental covariates selection: A comparison of a group of environmental covariates

In the digital soil mapping (DSM) framework, machine learning models quantify the relationship between soil observations and environmental covariates. Generally, the most commonly used covariates (MCC; e.g., topographic attributes and single-time remote sensing data, and legacy maps) were employed in DSM studies. Additionally, remote sensing time-series (RST) data can provide useful information for soil mapping. Therefore, the main aims of the study are to compare the MCC, the monthly Sentinel-2 time-series of vegetation indices dataset, and the combination of datasets (MCC + RST) for soil organic carbon (SOC) prediction in an arid agroecosystem in Iran. We used different machine learning algorithms, including random forest (RF), Cubist, support vector machine (SVM), and partial least square regression (PLSR). A total of 237 soil samples at 0–20 cm depths were collected. The 5-fold cross-validation technique was used to evaluate the modeling performance, and 50 bootstrap models were applied to quantify the prediction uncertainty. The results showed that the Cubist model performed the best with the MCC dataset (R2 = 0.35, RMSE = 0.26%) and the combined dataset of MCC and RST (R2 = 0.33, RMSE = 0.27%), while the RF model showed better results for the RST dataset (R2 = 0.10, RMSE = 0.31%). Soil properties could explain the SOC variation in MCC and combined datasets (66.35% and 50.82%, respectively), while NDVI was the most controlling factor in the RST (50.22%). Accordingly, results showed that time-series vegetation indices did not have enough potential to increase SOC prediction accuracy. However, the combination of MCC and RST datasets produced SOC spatial maps with lower uncertainty. Therefore, future studies are required to explicitly explain the efficiency of time-series remotely-sensed data and their interrelationship with environmental covariates to predict SOC in arid regions with low SOC content.

Sentinel-2 and Landsat-8 Multi-Temporal Series to Estimate Topsoil Properties on Croplands

The spatial and temporal monitoring of soil organic carbon (SOC), and other soil properties related to soil erosion, is extremely important, both from the environmental and economic perspectives. Sentinel-2 (S2) and Landsat-8 (L8) time series increase the probability to observe bare soil fields in croplands, and thus, monitor soil properties over large regions. In this regard, this work suggests an automated pixel-based approach to select only pure soil pixels in S2 and L8 time series, and to make a synthetic bare soil image (SBSI). The SBSIs and the soil properties measured in the framework of the European LUCAS survey were used to calibrate SOC, clay, and CaCO3 prediction models. The results highlight a high correlation between laboratory soil spectra and the SBSIs median spectra, especially for the SBSI obtained by a three-year S2 collection, which provides satisfactory results in terms of SOC prediction accuracy (RPD: 1.74). The comparison between S2 and L8 results demonstrated the higher capability of the S2 sensor in terms of SOC prediction accuracy, mainly due to the greater spatial resolution of the bands in the visible region. Whereas, neither S2 nor L8 could accurately predict the clay and CaCO3 content. This is because of the low spectral and spatial resolution of their SWIR bands that prevent the exploitation of the narrow spectral features related to these two soil attributes. The results of this study prove that large S2 time series can estimate and monitor SOC in croplands using an automated pixel-based approach that selects pure soil pixels and retrieves reliable synthetic soil spectra.

Evaluating the capability of a UAV‐borne spectrometer for soil organic carbon mapping in bare croplands

AbstractHigh‐resolution, field‐scale soil organic carbon (SOC) mapping in croplands is crucial for effective and precise agricultural management. Recent developments in unmanned aerial vehicles (UAVs) combined with miniaturized visible–near infrared spectrometers have enabled the rapid and low‐cost field‐scale SOC mapping. However, a field‐specific spectrotransfer model is often needed for such UAV‐based hyperspectral measurements, implying local sampling and model development are still required, and this hampers the widespread application of UAV‐based methods. In this study, we aim to test to what extent SOC prediction models derived from an existing regional soil spectral library (SSL) can be applied to UAV‐based hyperspectral data, without the need for additional field sampling. To this end, an UAV survey was conducted over a bare cropland within the Belgian Loam Belt for field‐scale SOC mapping. We evaluated two calibration approaches, one based on local sampling and model development, and one where we capitalized on an existing (laboratory‐based) regional SSL. For the local calibration approach, we obtained a good prediction performance with RMSE of 0.57 g kg−1 and RPIQ of 2.35. For the regional model, a spectral alignment procedure was needed to resolve the discrepancy between UAV‐ and laboratory‐based measurements. This resulted in a fair SOC prediction accuracy with RMSE of 0.93 g kg−1 and RPIQ of 1.45. The comparison of SOC maps derived from the two approaches, along with an external validation showed a high consistency, indicating that UAV‐based spectral measurements, in combination with SSLs have the potential to improve the efficiency of high‐resolution SOC mapping.

Using environmental variables and Fourier Transform Infrared Spectroscopy to predict soil organic carbon

Soil Organic Carbon (SOC) content is a key element for soil fertility and productivity, nutrient availability and potentially represents a measurement of the sink for greenhouse gas abatement. Improving our knowledge on the spatial distribution of SOC is hence essential for sustainable nutrient management and carbon storage capacity. The objective of this study was to evaluate the performance of six tree-based machine-learning models when using environmental variables (i.e., remote sensing and terrain attributes - scenario 1), Fourier Transform Infrared Spectroscopy (FTIR) data (scenario 2) and combination of environmental variables and FTIR data (scenario 3) as predictors in prediction of SOC content. The models included Random Forest, Cubist, Conditional Inference Forest, Conditional Inference Trees, Extreme Gradient Boosting and Classification, Regression Trees. Furthermore, we explored if the Bat optimization algorithm can improve the prediction accuracy of the models. The study was conducted across a 7000 ha field in the Miandoab County, Northern Iran, with a total of 80 soil samples collected systematically in a regular grid (700 × 1000 m). According to Leave-One-Out Cross-Validation, the best prediction performance was achieved by the Cubist+Bat model when environmental variables and FTIR spectra (scenario 3) were used (Coefficient of determination = 0.73, Concordance Correlation Coefficient = 0.77, Root Mean Square Error = 0.36, Mean Absolute Error = 0.31, Median Absolute Error = 0.28). FTIR data had the highest influence on the prediction accuracy of SOC. Therefore, it can be concluded that the combination of environmental variables and FTIR data with Cubist+Bat model as a precise approach to monitor SOC in semi-arid soils of Iran. The final Digital Soil Map (DSM) of SOC revealed that improvements in prediction might be possible with the collection of more soil samples in areas where the land use and topography changed over short spatial scales.

Digital Mapping of Soil Organic Carbon Using Sentinel Series Data: A Case Study of the Ebinur Lake Watershed in Xinjiang

As an important evaluation index of soil quality, soil organic carbon (SOC) plays an important role in soil health, ecological security, soil material cycle and global climate cycle. The use of multi-source remote sensing on soil organic carbon distribution has a certain auxiliary effect on the study of soil organic carbon storage and the regional ecological cycle. However, the study on SOC distribution in Ebinur Lake Basin in arid and semi-arid regions is limited to the mapping of measured data, and the soil mapping of SOC using remote sensing data needs to be studied. Whether different machine learning methods can improve prediction accuracy in mapping process is less studied in arid areas. Based on that, combined with the proposed problems, this study selected the typical area of the Ebinur Lake Basin in the arid region as the study area, took the sentinel data as the main data source, and used the Sentinel-1A (radar data), the Sentinel-2A and the Sentinel-3A (multispectral data), combined with 16 kinds of DEM derivatives and climate data (annual average temperature MAT, annual average precipitation MAP) as analysis. The five different types of data are reconstructed by spatial data and divided into four spatial resolutions (10, 100, 300, and 500 m). Seven models are constructed and predicted by machine learning methods RF and Cubist. The results show that the prediction accuracy of RF model is better than that of Cubist model, indicating that RF model is more suitable for small areas in arid areas. Among the three data sources, Sentinel-1A has the highest SOC prediction accuracy of 0.391 at 10 m resolution under the RF model. The results of the importance of environmental variables show that the importance of Flow Accumulation is higher in the RF model and the importance of SLOP in the DEM derivative is higher in the Cubist model. In the prediction results, SOC is mainly distributed in oasis and regions with more human activities, while SOC is less distributed in other regions. This study provides a certain reference value for the prediction of small-scale soil organic carbon spatial distribution by means of remote sensing and environmental factors.

Combination of soil texture with Nix color sensor can improve soil organic carbon prediction

The optimum ecosystem functioning is reliant on soil organic carbon (SOC) content which is traditionally measured in the laboratory via a cumbersome wet-chemistry method. This preliminary research tested whether a combination of Nix color sensor and portable X-ray fluorescence (PXRF) spectrometer data with soil texture data can improve soil SOC prediction accuracy relative to using them independently. A total of 371 samples representing diverse soil texture and SOC content were collected from three different ecoregions of eastern India: coastal saline zone, red and lateritic zone, and Gangetic alluvial zone. All dried, ground, and sieved samples were scanned via Nix and PXRF and random forest (RF) regression was used to predict soil SOC with different combinations of data. Soils were grouped into nine textural classes while soil SOC content exhibited substantial variability (0.08–2.26%). Comparing soil SOC with texture (sand + silt + clay), satisfactory prediction accuracy was observed (validation R2 = 0.70). Combining Nix extracted color parameters with texture substantially improved the model performance, producing the validation determination coefficient of 0.81. In contrast, PXRF-Rb, as a proxy of soil clay content was unable to achieve satisfactory prediction performance (R2 = 0.24), indicating the heterogeneity in soil mineralogical composition. The RF variable importance plot using Nix alone identified redness (a*) and yellowness to blueness (b*) as influential predictors, manifesting the impact of red color from Fe and Al-oxides and their significant negative correlation with soil SOC (r = −0.62 and −0.57 for a* and b*, respectively). These color parameters were again identified by the RF variable importance plot of (Texture + Nix)-model, implying that the SOC prediction improvement may be linked with the Nix sensor’s capability of extracting useful information in the visible range. Summarily, a combination of Nix color variables and texture data was adept at predicting soil SOC in lieu of traditional laboratory analysis. The robustness of the (Texture + Nix)-based SOC prediction model can be augmented by incorporating more soil samples representing all 12 soil textural classes and variable SOC content, showing all possible soil colors in the pedogenic environment.

Reducing moisture effects on soil organic carbon content prediction in visible and near-infrared spectra with an external parameter othogonalization algorithm

Field spectroscopy and other efficient hyperspectral techniques have been widely used to measure soil properties, including soil organic carbon (SOC) content. However, reflectance measurements based on field spectroscopy are quite sensitive to uncontrolled variations in surface soil conditions, such as moisture content; hence, such variations lead to drastically reduced prediction accuracy. The goals of this work are to (i) explore the moisture effect on soil spectra with different SOC levels, (ii) evaluate the selection of optimal parameter for external parameter othogonalization (EPO) in reducing moisture effect, and (iii) improve SOC prediction accuracy for semi-arid soils with various moisture levels by combing the EPO with machine learning method. Soil samples were collected from grassland regions of Inner Mongolia in North China. Rewetting laboratory experiments were conducted to make samples moisturized at five levels. Visible and near-infrared spectra (350–2500 nm) of soil samples rewetted were observed using a hand-held SVC HR-1024 spectroradiometer. Our results show that moisture influences the correlation between SOC content and soil reflectance spectra and that moisture has a greater impact on the spectra of samples with low SOC. An EPO algorithm can quantitatively extract information of the affected spectra from the spectra of moist soil samples by an optimal singular value. A SOC model that effectively couples EPO with random forest (RF) outperforms partial least-square regression (PLSR)-based models. The EPO–RF model generates better results with R2 of 0.86 and root-mean squared error (RMSE) of 3.82 g kg−1, whereas a PLSR model gives R2 of 0.79 and RMSE of 4.68 g kg−1.

Regional soil organic carbon prediction model based on a discrete wavelet analysis of hyperspectral satellite data

Most studies have the achieved rapid and accurate determination of soil organic carbon (SOC) using laboratory spectroscopy; however, it remains difficult to map the spatial distribution of SOC. To predict and map SOC at a regional scale, we obtained fourteen hyperspectral images from the Gaofen-5 (GF-5) satellite and decomposed and reconstructed the original reflectance (OR) and the first derivative reflectance (FDR) using discrete wavelet transform (DWT) at different scales. At these different scales, as inputs, we selected the 3 optimal bands with the highest weight coefficient using principal component analysis and chose the normalized difference index (NDI), ratio index (RI) and difference index (DI) with the strongest correlation with the SOC content using a contour map method. These inputs were then used to build regional-scale SOC prediction models using random forest (RF), support vector machine (SVM) and back-propagation neural network (BPNN) algorithms. The results indicated that: 1) at a low decomposition scale, DWT can effectively eliminate the noise in satellite hyperspectral data, and the FDR combined with DWT can improve the SOC prediction accuracy significantly; 2) the method of selecting inputs using principal component analysis and a contour map can eliminate the redundancy of hyperspectral data while retaining the physical meaning of the inputs. For the model with the highest prediction accuracy, the inputs were all derived from the wavelength range of SOC variations; 3) the differences in prediction accuracy among the different prediction models are small; and 4) the SOC prediction accuracy using hyperspectral satellite data is greatly improved compared with that of previous SOC prediction studies using multispectral satellite data. This study provides a highly robust and accurate method for predicting and mapping regional SOC contents.

Influence of Sampling Point Discretization on the Regional Variability of Soil Organic Carbon in the Red Soil Region, China

Research on the regional variability of soil organic carbon (SOC) has focused mostly on the influence of the number of soil sampling points and interpolation methods. Little attention has typically been paid to the influence of sampling point discretization. Based on dense soil sampling points in the red soil area of Southern China, we obtained four sample discretization levels by a resampling operation. Then, regional SOC distributions were obtained at four levels by two interpolation methods: ordinary Kriging (OK) and Kriging combined with land use information (LuK). To evaluate the influence of sample discretization on revealing SOC variability, we compared the interpolation accuracies at four discretization levels with uniformly distributed validation points. The results demonstrated that the spatial distribution patterns of SOC were roughly similar, but the contour details in some local areas were different at the various discretization levels. Moreover, the predicted mean absolute errors (MAE) and root mean square errors (RMSE) of the two Kriging methods all rose with an increase in discretization. From the lowest to the largest discretization level, the MAEs of OK and LuK rose from 4.47 and 3.02 g kg−1 to 5.46 and 3.54 g kg−1, and the RMSEs rose from 5.13 and 3.95 g kg−1 to 5.76 and 4.76 g kg−1, respectively. Though the trend of prediction errors varied with discretization levels, the interpolation accuracies of the two Kriging methods were both influenced by the sample discretization level. Furthermore, the spatial interpolation uncertainty of OK was more sensitive to the discretization level than that of the LuK method. Therefore, when the spatial distribution of SOC is predicted using Kriging methods based on the same sample quantity, the more uniformly distributed sampling points are, the more accurate the spatial prediction accuracy of SOC will be, and vice versa. The results of this study can act as a useful reference for evaluating the uncertainty of SOC spatial interpolation and making a soil sampling scheme in the red soil region of China.

Parameter calibration in global soil carbon models using surrogate-based optimization

Abstract. Soil organic carbon (SOC) has a significant effect on carbon emissions and climate change. However, the current SOC prediction accuracy of most models is very low. Most evaluation studies indicate that the prediction error mainly comes from parameter uncertainties, which can be improved by parameter calibration. Data assimilation techniques have been successfully employed for the parameter calibration of SOC models. However, data assimilation algorithms, such as the sampling-based Bayesian Markov chain Monte Carlo (MCMC), generally have high computation costs and are not appropriate for complex global land models. This study proposes a new parameter calibration method based on surrogate optimization techniques to improve the prediction accuracy of SOC. Experiments on three types of soil carbon cycle models, including the Community Land Model with the Carnegie–Ames–Stanford Approach biogeochemistry submodel (CLM-CASA') and two microbial models show that the surrogate-based optimization method is effective and efficient in terms of both accuracy and cost. Compared to predictions using the tuned parameter values through Bayesian MCMC, the root mean squared errors (RMSEs) between the predictions using the calibrated parameter values with surrogate-base optimization and the observations could be reduced by up to 12 % for different SOC models. Meanwhile, the corresponding computational cost is lower than other global optimization algorithms.

Hybrid atmospheric correction algorithms and evaluation on VNIR/SWIR Hyperion satellite data for soil organic carbon prediction

ABSTRACTVisible near-infrared and shortwave infrared data acquired by spaceborne sensors contain atmospheric noise, along with target reflectance that may affect its end applications, e.g. geological, vegetation, soil surface studies, etc. Several atmospheric correction algorithms have been already developed to remove unwanted atmospheric components of a spectral signature of Earth targets obtained from airborne/spaceborne hyperspectral image. In spite of this, choosing of an appropriate atmospheric correction algorithm is an ongoing research. In this study, two hybrid atmospheric correction (HAC) algorithms incorporating a modified empirical line (ELm) method were proposed. The first HAC model (named HAC_1) combines (i) a radiative transfer (RT) model based on the concepts of RT equations, which uses real-time in situ atmospheric and climatic data, and (ii) an ELm technique. The second one (named HAC_2) combines (i) the well-known ATmospheric CORrection (ATCOR) model and (ii) an ELm technique. Both HAC algorithms and their component single atmospheric correction algorithms (ATCOR, RT, and ELm) were applied to radiance data acquired by Hyperion satellite sensor over study sites in Australia. The performances of both HAC algorithms were analysed in two ways. First, the Hyperion reflectances obtained by five atmospheric correction algorithms were analysed and compared using spectral metrics. Second, the performance of each atmospheric correction algorithm was analysed for prediction of soil organic carbon (SOC) using Hyperion reflectances obtained from atmospheric correction algorithms. The prediction model of SOC was built using partial least square regression model. The results show that (i) both the hybrid models produce a good spectrum with lower Spectral Angle Mapper and Spectral Information Divergence values and (ii) both hybrid algorithms provided better SOC prediction accuracy, in terms of coefficient of determination (R2), residual prediction deviation (RPD), and ratio of performance to interquartile (RPIQ), with R2 ≥ 0.75, RPD ≥ 2, and RPIQ ≥ 2.58 than single algorithms. HAC algorithms, developed using ELm technique, may be recommended for atmospheric correction of Hyperion radiance data, when archived Hyperion reflectance data have to be used for SOC prediction mapping.