Search

• It was assumed that soils covered by forest can be considered as saturated in SOC. • Cubist-based PTF was developed for predicting and mapping saturated SOC content. • Environmental conditions are also important factors in predicting SOC saturation. • Significant SOC deficit was revealed on large part of Hungary with high variability. • Highest SOC deficits occur in areas with medium to high SOC content. Stakeholders and policymakers have been becoming more and more interested not just in the potential organic carbon (SOC) saturation level of soils but also in spatially explicit information on the degree of SOC deficit, which can support future policy and sustainable management strategies, and carbon sequestration-associated spatial planning. Thus the objective of our study was to develop a cubist-based pedotransfer function (PTF) for predicting and mapping the saturated SOC content of the topsoils (0–30 cm) in Hungary and then compare the resulting map with the actual SOC map to determine and assess the degree of SOC deficit. It was assumed that topsoils covered by permanent forests can be practically considered as saturated in SOC. Using the monitoring points of the Hungarian Soil Information and Monitoring System located in forests as reference soil profiles, we developed a cubist-based PTF. The transparent model structure provided by cubist allowed to show that not just the physicochemical properties of soils (e.g., texture, and pH) but also environmental conditions, such as topography (e.g., slope, altitude, and topographical position) and climate (e.g., long-term mean annual temperature, and evaporation), characterizing landscape are important factors in predicting the level of SOC saturation. Our results also pointed out that there is SOC deficit on large part of the country (∼80%) showing high spatial variability. It was also revealed that the most considerable potential for additional SOC sequestration can be found related to soils with medium to high actual SOC content. [ABSTRACT FROM AUTHOR]

[Display omitted] • Predicting SOC and SIC from two sampling periods (1990 vs 2015); • Quantifying the impact of environmental variables on SOC and SIC changes; • Mapping soil carbon stocks change during 25 years (1990–2015). Soil organic carbon (SOC) and soil inorganic carbon (SIC) has important effects on soil physical, chemical and biological properties. They play an important role in coordinating the relationship between soil water and air, increasing soil water holding capacity and improving plant productivity. In this study, a boosted regression trees (BRT) model was developed to map the spatial distribution carbon stocks in the semi-arid region of Northeast China in 1990 and 2015. During the two periods, 10-fold cross-validation technology was used to test the performance and uncertainty of BRT model. In order to construct the model, 9 environmental variables (derived from climate, topography and biology) and 173 (1990) and 223 (2015) topsoil (0–30 cm) samples were used. The comparison between estimated and observed data shows that the RMSE of SOC and SIC stocks were 0.53 kgm−2 and 0.19 kgm−2 in 1990, and 0.65 kgm−2 and 0.20 kgm−2 in 2015, respectively. Elevation, normalized difference vegetation index, mean annual precipitation and Landsat band 3 were identifies as critical environmental factors for simulating the spatial distribution of SOC, accounting for 76.6 % and 70.3 % of the total relative importance in 1990 and 2015, respectively. Mean annual precipitation, mean annual temperature and topographic wetness index were the critical environmental factors for simulating the spatial variation of SIC during the two periods. Land use change also played an important role in the spatial variability of SOC and SIC stocks. In the past 25 years, soil carbon stocks decreased from 6.2 kg m−2 in 1990 to 5.9 kg m−2 in 2015. The spatial distribution pattern of SOC was high in northeastern area and low in southwestern area during the two periods, while the spatial distribution pattern of SIC was opposite to that of SOC stocks. The mapped soil carbon stock distribution is fundamental to future study of soil carbon cycle and regional carbon balance in semi-arid regions. [ABSTRACT FROM AUTHOR]

Soil organic carbon (SOC) plays an important role in soil fertility and carbon sequestration, and a better understanding of the spatial patterns of SOC is essential for soil resource management. In this study, we used boosted regression tree (BRT) and random forest (RF) models to map the distribution of topsoil organic carbon content at the northeastern edge of the Tibetan Plateau in China. A set of 105 soil samples and 12 environmental variables (including topography, climate and vegetation) were analyzed. The performance of the models was evaluated using a 10-fold cross-validation procedure. Maps of the mean values and standard deviations of SOC were generated to illustrate model variability and uncertainty. The results indicate that the BRT and RF models exhibited very similar performance and yielded similar predicted distributions of SOC. The two models explained approximately 70% of the total SOC variability. The BRT and RF models robustly predicted the SOC at low observed SOC values, whereas they underestimated high observed SOC values. This underestimation may have been caused by biased distributions of soil samples in the SOC space. Vegetation-related variables were assigned the highest importance in both models, followed by climate and topography. Both models produced spatial distribution maps of SOC that were closely related to vegetation cover. The SOC content predicted by the BRT model was clearly higher than that of the RF model in areas with greater vegetation cover because the contributions of vegetation-related variables in the two models (65% and 43%, respectively) differed significantly. The predicted SOC content increased from the northwestern to the southeastern part of the study area, average values produced by the BRT and RF models were 27.3 g kg −1 and 26.6 g kg −1 , respectively. We conclude that the BRT and RF methods should be calibrated and compared to obtain the best prediction of SOC spatial distribution in similar regions. In addition, vegetation variables, including those obtained from remote sensing imagery, should be taken as the main environmental indicators and explicitly included when generating SOC maps in Alpine environments. [ABSTRACT FROM AUTHOR]

• We developed static SOC mapping to space–time SOC modeling during 1980–2015. • GWRK-RothC presented the higher prediction accuracy than GWRK and RothC. • Mechanisms of the RothC model can be integrated into the GWRK algorithm. • Integration of mechanistic model into the DSM can be extended to different areas. Soil organic carbon (SOC) in intensively human-impacted areas often presents extremely complicated patterns in space and time, which brought a new challenge to space–time SOC modelling. Here we attempt to create a space-for-time GWRK-RothC model by incorporating the predictions of the process-based RothC model into the geographically weighted regression kriging (GWRK) for improving the space–time modelling of SOC in intensively human-impacted area. We collected a total of 1219 topsoil samples (0–20 cm) from southern Jiangsu Province of China in 1980, 2000, and 2015, and modelled the spatiotemporal dynamics of SOC by using the modified RothC model (with a newly-added pH modifier for representing the impact of soil acidification on SOC decomposition), the space-for-time GWRK, and the proposed space-for-time GWRK-RothC model. Results showed that the change trends in SOC derived by the three methods were similar, with an overall trend of SOC increase during 1980–2000 and SOC decline in the subsequent 15 years (2000–2015). However, their performances for space–time SOC modelling were different. The proposed space-for-time GWRK-RothC model had the highest accuracy in representing the spatiotemporal evolution of SOC in the study area, with the lowest root mean square error (RMSE) (3.06 g kg−1), mean error (ME) (-0.19 g kg−1), and the highest coefficient of determination (R2) (0.61), compared to the accuracy of space-for-time GWRK (RMSE = 3.53 g kg−1, ME = -0.36 g kg−1, and R2 = 0.45) and RothC model (RMSE = 4.23 g kg−1, ME = 0.20 g kg−1, and R2 = 0.20). These results highlighted the importance of integrating process-model-derived SOC spatiotemporal dynamics information in space-for-time digital soil mapping (DSM) for improving the space–time SOC modelling. We believe that outputs from this study may offer valuable guidance for developing space–time DSM model to achieve better performance of SOC modelling in space and time, especially for areas affected by strong anthropogenic activities. [ABSTRACT FROM AUTHOR]

[Display omitted] • Quantifying the potential human factors on SOC content in topsoil of agroecosystems. • Mapping the spatial distribution of SOC content in agroecosystems of Northeast China. • Evaluating the predictive performance and application potential of the predictive model. Both natural and anthropogenic variables affect soil C distribution and its pool, however studies about anthropogenic influence on soil C distribution are very limited in the literature. This study investigated anthropogenic effects on soil organic carbon (SOC) changes in the cultivated lands of Northeast China. A total of 196 topsoil samples (0–30 cm) were collected, and analyzed for SOC content, and 12 environmental variables (natural and anthropogenic) were selected as SOC predictors. Natural factors included elevation, slope gradient, slope aspect (SA), topographic wetness index (TWI), mean annual temperature, mean annual precipitation, and normalized difference vegetation index, while population (POP), gross domestic product (GDP), distance to the socioeconomic center, distance to roads, and reclamation period (PER) represented anthropogenic variables. Three different boosted-regression trees models with different combination of SOC predictors were constructed, and the model performance was evaluated with 10-fold cross-validation. We found that the model that included all predictors had the best performance, followed by the model with topography and climate variables, and the model with only anthropogenic variables. However, adding the anthropogenic variables in the model greatly improved its performance. Results showed that PER, POP and GDP were the key environmental variables affecting SOC content in the topsoil agroecosystems in Northeast China. This study suggests that anthropogenic variables should be selected as the main environmental variable in predicting of SOC content in agroecosystem with a higher human influence. We believe that the accurate prediction and mapping of SOC content in the topsoil agroecosystem will help formulate farmland soil management policies and promote soil carbon sequestration. [ABSTRACT FROM AUTHOR]

• Investigate the most statistically significant covariates to predict topsoil (0–0.3 m) organic carbon (SOC). • Assess proximal and remote sensors versatility either in combination or alone. • Examine geostatistical, machine learning and hybrid models. • Identify optimal calibration sample size. • Determine nitrogen (N) fertiliser practices considering mineralisation from SOC. Nitrogen (N) is essential for sugarcane growth, with one source mineralisation of soil organic carbon (SOC, %). To assist farmers determine suitable N fertiliser rates, the Six-Easy-Steps nutrient guidelines were devised by Sugar Research Australia and based on topsoil (0–0.3 m) SOC. Given the heterogeneous nature of SOC, a digital soil mapping (DSM) approach may be useful to map SOC at the field scale. This study aims to examine various models to predict SOC, including ordinary kriging (OK), regression kriging (RK), machine learning (ML) such as random forest (RF) and support vector machine (SVM), and hybrid models that combine ML with RK (i.e., RFRK and SVMRK). Various digital data sources, including proximal (i.e., gamma-ray [γ-ray] and electromagnetic [EM] induction data) and remote (i.e., land surface temperature [LST, oC]) sensing data were explored in combination and alone. Minimum calibration sample size (i.e., 110–10) was also investigated. The comparisons were validated using a hold-out dataset, with prediction agreement (Lin's concordance correlation coefficient [LCCC]) and accuracy (ratio of performance to deviation [RPD]) assessed. The most statistically significant digital data used in combination included γ-ray (i.e., total count [TC]), EM (i.e., 1mHcon and 2mHcon), remote (i.e., LST) and northing. The SVMRK model performed best when using all calibration data, producing moderate agreement (LCCC = 0.73) and fair (RPD = 1.65) accuracy. This was also the case when sample size was >= 50, but when it was < 50, RFRF returned equivalent agreement (0.70) and accuracy (1.55). Similar results were achieved when only γ-ray (i.e., TC) was used, however, RFRK produced moderate agreement and fair accuracy using as few as 20 and as many as 70 samples, with the optimal being 40 (i.e., LCCC = 0.79 and RPD = 1.7). By comparison, OK and RK generally produced poor agreement (<= 0.65) and accuracy (<= 1.4) regardless of sample size. The final DSM using RFRK provided an indication of soil condition that limits soil capability to store N as a function of SOC and acts a means to replenish soil capital with N application rates according to the Six-Easy-Steps. Specifically, Tenosols and Rudosols require 130 kg/ha to 120 kg/ha, whereas Kandosols require 110 and 100 kg/ha. The DSM equates to a potential ∼ 22 % decrease in the cost of N fertiliser application, relative to a one-size fits all approach. [ABSTRACT FROM AUTHOR]

In agronomy, soil organic carbon (SOC) content is important for the development and growth of crops. From an environmental monitoring viewpoint, SOC sequestration is essential for mitigating the emission of greenhouse gases into the atmosphere. SOC dynamics in cropland soils should be further studied through various approaches including remote sensing. In order to predict SOC content over croplands in southwestern France (area of 22,177 km²), this study addresses (i) the influence of the dates on which Sentinel-2 (S2) images were acquired in the springs of 2017–2018 as well as the influence of the soil sampling period of a set of samples collected between 2005 and 2018, (ii) the use of soil moisture products (SMPs) derived from Sentinel-1/2 satellites to analyze the influence of surface soil moisture on model performance when included as a covariate, and (iii) whether the spatial distribution of SOC as mapped using S2 is related to terrain-derived attributes. The influences of S2 image dates and soil sampling periods were analyzed for bare topsoil. The dates of the S2 images with the best performance (RPD ≥ 1.7) were 6 April and 26 May 2017, using soil samples collected between 2016 and 2018. The soil sampling dates were also analyzed using SMP values. Soil moisture values were extracted for each sample and integrated into partial least squares regression (PLSR) models. The use of soil moisture as a covariate had no effect on the prediction performance of the models; however, SMP values were used to select the driest dates, effectively mapping topsoil organic carbon. S2 was able to predict high SOC contents in the specific soil types located on the old terraces (mesas) shaped by rivers flowing from the southwestern Pyrénées. [ABSTRACT FROM AUTHOR]

Wetland ecosystems contain large amounts of soil organic carbon. Their natural environment is often both at the junction of land and water with good conditions for carbon sequestration. Therefore, the study of accurate prediction of soil organic carbon (SOC) density in coastal wetland ecosystems of flat terrain areas is the key to understanding their carbon cycling. This study used remote sensing data to study SOC density potentials of coastal wetland ecosystems in Northeast China. Eleven environmental variables including normalized difference vegetation index (NDVI), difference vegetation index (DVI), soil adjusted vegetation index (SAVI), renormalization difference vegetation index (RDVI), ratio vegetation index (RVI), topographic wetness index (TWI), elevation, slope aspect (SA), slope gradient (SG), mean annual temperature (MAT), and mean annual precipitation (MAP) were selected to predict SOC density. A total of 193 soil samples (0–30 cm) were divided into two parts, 70% of the sampling sites data were used to construct the boosted regression tree (BRT) model containing three different combinations of environmental variables, and the remaining 30% were used to test the predictive performance of the model. The results show that the full variable model is better than the other two models. Adding remote sensing-related variables significantly improved the model prediction. This study revealed that SAVI, NDVI and DVI were the main environmental factors affecting the spatial variation of topsoil SOC density of coastal wetlands in flat terrain areas. The mean (±SD) SOC density of full variable models was 18.78 (±1.95) kg m−2, which gradually decreased from northeast to southwest. We suggest that remote sensing-related environmental variables should be selected as the main environmental variables when predicting topsoil SOC density of coastal wetland ecosystems in flat terrain areas. Accurate prediction of topsoil SOC density distribution will help to formulate soil management policies and enhance soil carbon sequestration. [ABSTRACT FROM AUTHOR]

• Topsoil SOC (0–20 cm) was mapped in an alluvial plain region at 30 m resolution. • Random Forests performed better than the Stepwise MLR-Kriging. • Silt content and river proximity were most important predictors of SOC. • Uncertainty was quantified using Quantile Regression Forests. • Highest SOC content was found in Calcaric Phaeozems under shrubs and forest. Topsoil (0–20 cm) soil organic carbon content (SOC, g kg−1) was predicted and mapped at 30 m resolution on an intensively cultivated alluvial plain in the Sarlahi district of Nepal. It has been reported that SOC content in this region has decreased to alarmingly low levels; however, no documented work on the mapping of SOC at high spatial resolutions has been found. We compared the performance of the Stepwise-Multiple-Linear-Regression-Kriging (SMLRK) and Random Forest (RF) techniques for mapping SOC content. Environmental covariates of SOC were selected following the SCORPAN framework of digital soil mapping. Prediction uncertainty was quantified using Quantile Regression Forest technique. Predicted SOC was further calculated for different soil and land cover unit combinations. It was found that RF performed better than SMLRK as evidenced by more favourable error statistics. Silt content, distance to major river systems, precipitation during coldest quarter of the year, and NDVI for January-February were found to be the most important variables affecting SOC content in this region. Mean SOC of the study area was predicted as 10.98 ± 0.01 g kg−1. Calcaric Phaeozems under Shrubs (14.85 ± 0.09 g kg−1) and forests (14.54 ± 0.02 g kg−1) had the highest mean SOC contents. Cultivated lands within irrigation command areas had less SOC content (9.41 ± 0.01 g kg−1) than those outside the areas (11.84 ± 0.01 g kg−1). The SOC spatial distribution map could guide efforts to prioritize SOC content enhancement activities in this area. It was concluded that in such low-relief alluvial regions, the processes of silt deposition due to the proximity to river systems are key predictors than other variables, and that the RF technique could predict SOC content better than SMLRK. The success of activities to raise SOC contents might thus be subject to the control of silt deposition from the upstream hills. [ABSTRACT FROM AUTHOR]

• Production of a digital map of topsoil organic carbon. • Individual and hybrid machine learning models were compared. • The most appropriate covariates were selected by PCA. • The geomorphometric and remote sensing (GR) scenario was better than the remote sensing (R). • The hybrid model (RF-OK) predicted the most accurate of SOC map. Digital mapping of soil organic carbon (SOC) is crucial to evaluate its spatial variability and also to assess environmental factors controlling it at field scale. The current study was conducted to compare one statistical method include partial least squares regression (PLSR), four individual machine learning(ML) algorithms including random forest (RF), quantile regression forest (QRF), cubist (CB), fuzzy logic (SoLIM) along with two hybrid methods including the random forest-ordinary kriging (RF-OK) and quantile random regression forest-ordinary kriging (QRF-OK) to map SOC. A number of 146 soil samples (0–30 cm) were collected in Khorramabad plain (680 ha). For the quantitative evaluation of SOC spatial variability, two scenarios were considered to use remote sensing data (R) and a combination of geo-morphometric and remote sensing data (GR). The data randomly were split into 80% (117 points) for training and 20% (29 points) for validation. The model performances were evaluated by the statistical indices as the coefficient of determination (R2), root mean square error (RMSE). According to principal component analysis (PCA), nine covariates including transformed soil adjusted vegetation index (TSAVI), relative vegetation index (RVI), Band 10, Band 11,Digital Elevation Model (DEM), Standard height(Standard_he), Valley_Dep, terrain surface texture (texture), and terrain surface convexity (Convexity) were selected as the environmental predictors. Results showed that the hybrid model RF-OK (RMSE = 0.05and R2 = 0.93) and SoLIM model (RMSE = 0.47and R2 = 0.41) with scenario GR had the highest and lowest accurate respectively. TSAVI, DEM, and Band 10 were the most important predictors and explanation more than 50% of SOC spatial variability in the study area. Generally, using hybrid machine learning models in combination with geo-morphometric and remote sensing covariates make it possible to model and predict SOC with acceptable accurate in the field-scale croplands. [ABSTRACT FROM AUTHOR]

• Three SOC maps were compared in mainland France. • Five model averaging approaches were tested in improving SOC map. • SOC map can be improved using more than 100 soil samples for model averaging. • Variance Weighted approach performed best. • Merging maps using model averaging is also applicable to data-poor situations. The soil organic carbon (SOC) pool is the largest terrestrial carbon (C) pool and is two to three times larger than the C stored in vegetation and the atmosphere. SOC is a crucial component within the C cycle, and an accurate baseline of SOC is required, especially for biogeochemical and earth system modelling. This baseline will allow better monitoring of SOC dynamics due to land use change and climate change. However, current estimates of SOC stock and its spatial distribution have large uncertainties. In this study, we test whether we can improve the accuracy of the three existing SOC maps of France obtained at national (IGCS), continental (LUCAS), and global (SoilGrids) scales using statistical model averaging approaches. Soil data from the French Soil Monitoring Network (RMQS) were used to calibrate and evaluate five model averaging approaches, i.e., Granger-Ramanathan, Bias-corrected Variance Weighted (BC-VW), Bayesian Modelling Averaging, Cubist and Residual-based Cubist. Cross-validation showed that with a calibration size larger than 100 observations, the five model averaging approaches performed better than individual SOC maps. The BC-VW approach performed best and is recommended for model averaging. Our results show that 200 calibration observations were an acceptable calibration strategy for model averaging in France, showing that a fairly small number of spatially stratified observations (sampling density of 1 sample per 2500 km2) provides sufficient calibration data. We also tested the use of model averaging in data-poor situations by reproducing national SOC maps using various sized subsets of the IGCS dataset for model calibration. The results show that model averaging always performs better than the national SOC map. However, the Modelling Efficiency dropped substantially when the national SOC map was excluded in model averaging. This indicates the necessity of including a national SOC map for model averaging, even if produced with a small dataset (i.e., 200 samples). This study provides a reference for data-poor countries to improve national SOC maps using existing continental and global SOC maps. [ABSTRACT FROM AUTHOR]