Accurate and detailed spatial soil information is essential for environmental modelling, risk assessment and decision making. The use of Remote Sensing data as secondary sources of information in digital soil mapping has been found to be cost effective and less time consuming compared to traditional soil mapping approaches. But the potentials of Remote Sensing data in improving knowledge of local scale soil information in West Africa have not been fully explored. This study investigated the use of high spatial resolution satellite data (RapidEye and Landsat), terrain/climatic data and laboratory analysed soil samples to map the spatial distribution of six soil properties–sand, silt, clay, cation exchange capacity (CEC), soil organic carbon (SOC) and nitrogen–in a 580 km2 agricultural watershed in south-western Burkina Faso. Four statistical prediction models–multiple linear regression (MLR), random forest regression (RFR), support vector machine (SVM), stochastic gradient boosting (SGB)–were tested and compared. Internal validation was conducted by cross validation while the predictions were validated against an independent set of soil samples considering the modelling area and an extrapolation area. Model performance statistics revealed that the machine learning techniques performed marginally better than the MLR, with the RFR providing in most cases the highest accuracy. The inability of MLR to handle non-linear relationships between dependent and independent variables was found to be a limitation in accurately predicting soil properties at unsampled locations. Satellite data acquired during ploughing or early crop development stages (e.g. May, June) were found to be the most important spectral predictors while elevation, temperature and precipitation came up as prominent terrain/climatic variables in predicting soil properties. The results further showed that shortwave infrared and near infrared channels of Landsat8 as well as soil specific indices of redness, coloration and saturation were prominent predictors in digital soil mapping. Considering the increased availability of freely available Remote Sensing data (e.g. Landsat, SRTM, Sentinels), soil information at local and regional scales in data poor regions such as West Africa can be improved with relatively little financial and human resources.

No abstract

Predicting taxonomic classes can be challenging with dataset subject to substantial irregularities due to the involvement of many surveyors. A data pruning approach was used in the present study to reduce such source errors by exploring whether different data pruning methods, which result in different subsets of a major reference soil groups (RSG) – the Plinthosols – would lead to an increase in prediction accuracy of the minor soil groups by using Random Forest (RF). This method was compared to the random oversampling approach. Four datasets were used, including the entire dataset and the pruned dataset, which consisted of 80% and 90% respectively, and standard deviation core range of the Plinthosols data while cutting off all data points belonging to the outer range. The best prediction was achieved when RF was used with recursive feature elimination along with the non-oversampled 90% core range dataset. This model provided a substantial agreement to observation, with a kappa value of 0.57 along with 7% to 35% increase in prediction accuracy for smaller RSG. The reference soil groups in the Dano catchment appeared to be mainly influenced by the wetness index, a proxy for soil moisture distribution.

No abstract

Abstract. The status of the soil organic carbon (SOC) stock at any position in the landscape is subject to a complex interplay of soil state factors operating at different scales and regulating multiple processes resulting either in soils acting as a net sink or net source of carbon. Forest landscapes are characterized by high spatial variability, and key drivers of SOC stock might be specific for sub-areas compared to those influencing the whole landscape. Consequently, separately calibrating models for sub-areas (local models) that collectively cover a target area can result in different prediction accuracy and SOC stock drivers compared to a single model (global model) that covers the whole area. The goal of this study was therefore to (1) assess how global and local models differ in predicting the humus layer, mineral soil, and total SOC stock in Swedish forests and (2) identify the key factors for SOC stock prediction and their scale of influence. We used the Swedish National Forest Soil Inventory (NFSI) database and a digital soil mapping approach to evaluate the prediction performance using random forest models calibrated locally for the northern, central, and southern Sweden (local models) and for the whole of Sweden (global model). Models were built by considering (1) only site characteristics which are recorded on the plot during the NFSI, (2) the group of covariates (remote sensing, historical land use data, etc.) and (3) both site characteristics and group of covariates consisting mostly of remote sensing data. Local models were generally more effective for predicting SOC stock after testing on independent validation data. Using the group of covariates together with NFSI data indicated that such covariates have limited predictive strength but that site-specific covariates from the NFSI showed better explanatory strength for SOC stocks. The most important covariates that influence the humus layer, mineral soil (0–50 cm), and total SOC stock were related to the site-characteristic covariates and include the soil moisture class, vegetation type, soil type, and soil texture. This study showed that local calibration has the potential to improve prediction accuracy, which will vary depending on the type of available covariates.

No abstract

<p>Indicators of soil production function such as soil fertility index can potentially be a key decision tool in spatial planning for sustainable land management. The establishment of such soil fertility index requires basic soil properties which can be modelled for spatial mapping. The objective of this study was to take advantage of the soil legacy data of Benin to produce a digital soil map of soil fertility index at a national scale based on 8 soil properties (soil organic carbon matter, nitrogen, pH, exchangeable potassium, assimilable phosphorus, sum of base, cation exchange capacity and base saturation). Specific research aims were: (1) to model and develop digital soil maps; (2) to identify important factors influencing soil nutrients; (3) to establish soil fertility potentials using digital soil maps. For each soil property, modelling procedures involved the use of different covariates including soil type, topographic, bioclimatic and spectral data along with the comparative assessment of the Cubist and Quantile Random Forest model. Results revealed that apart from N and exchangeable K, significant models can be produced for most of the soil properties with R-square varying between 28% and 72% with the Quantile Random Forest presenting a more accurate prediction interval coverage probability. The analysis revealed that the distance to the nearest stream has strong predictive ability for all the soil properties along with the bioclimatic variables. Visualisation of the soil fertility map showed that most of the soils in Benin have low fertility level suggesting that the use of fertilizers and organic materials will be critical in sustaining crop productivity. A limited number of high and average fertility level soils were found in the low elevation areas of southern Benin and policy could advocate for their sole use for agriculture purpose as well as promote sustainable management practices.</p>

The manuscript is well written and generally clear, with an appropriate structure and the information provided in tables and figures is useful and necessary, although I have some specific comments for the presentation of some figures. The length of the paper is appropriate, as the presentation of the results is synthetic, and the discussion gives a concise explanation of the observed results supported by other findings in the SOC literature. This research paper investigated the key variables for predicting soil organic carbon (SOC) stocks in the litter layer, mineral soil, and total SOC of forest soils in Sweden, and maps its spatial distribution using random forest models. The study compares the accuracy of global models (calibrated for the whole study area, Sweden) and local models for north, central and southern Sweden. The calibration data originated from the Swedish National Forest and as predictor variables they compared three different sets: 1) only site variables observed at the sampling plots, 2) remote sensing variables, and 3) all variables. My main comment may be more a suggestion for the follow-up study. Mapping some of the site variables that were more decisive for SOC prediction (soil moisture class, vegetation type, soil type and soil texture) and including them as covariates for mapping may improve the model accuracy for mapping. However, as these variables will be themselves estimated with statistical models, there may be an increase in the uncertainty due to error propagation. Hence, the uncertainty of the map for a model including all variables may be a conservative estimate. Also, in that future scenario, consider that if you calibrate the model with the data observed at the plots but map it with the gridded estimates of the site variables, the accuracy may also overestimated. If you calibrate the model with the gridded predictions for soil C2 SOILD