Search

Sampling design can significantly reduce the uncertainty in geospatial predictions. In this paper, we developed an adaptive uncertainty-guided stepwise sampling (AUGSS) method to select sampling locations to supplement existing legacy sample points whose representation should be improved. The proposed method selects supplemental samples in a stepwise manner as guided by an objective function with two weighted sub-objectives. One reduces the area with high prediction uncertainty, and the other minimizes the overall prediction uncertainty for the entire area. The method takes an adaptive approach to adjust weights for the two sub-objectives and to tune an uncertainty threshold controlling whether a location can be reliably predicted during the sampling procedure. A case study on soil property prediction shows that AUGSS outperforms the stratified random sampling (SRS) and the non-adaptive uncertainty guided sampling method (UGSS) in terms of RMSE and Lin's concordance correlation coefficient with different sample sizes. This study shows that the AUGSS method offers a potential for effectively adding supplemental samples to existing samples which are insufficient for spatial prediction. The adaptive strategy guided by predicted uncertainty provides an efficient support to improve the spatial pattern of samples, which plays a key role in the result accuracy of geospatial predictive mapping. [ABSTRACT FROM AUTHOR]

The soil organic carbon (SOC) pool is larger than the biotic and atmospheric carbon pools, and understanding cultivated land SOC is critical for evaluating soil fertility and local agricultural management. Digital soil mapping (DSM) efficiently predicts soil properties by utilizing spatially distributed information. To date, many machine learning techniques have been applied in DSM, but model ensemble methods have rarely been used. In this study, two model ensemble methods, including the Granger-Ramanathan averaging and Bayesian model averaging, and three individual mathematical algorithms, such as the random forest, quantile regression forests, and multivariate adaptive regression splines models, were used to estimate SOC at a local level with limited soil samples. The prediction performances of the five methods were compared using an independent validation dataset composed of field observations of soil samples. The results showed that the prediction accuracy of the ensemble methods was higher than that of the individual methods (ΔR2 = 0.02 to 0.21). Compared to the other methods, the Granger-Ramanathan method had a lower root mean square error (RMSE) and mean absolute error and a higher prediction uncertainty. Therefore, the results of this study show the effectiveness of using ensemble methods in mapping SOC with limited soil samples. [ABSTRACT FROM AUTHOR]

Accurate mapping of soil organic carbon (SOC) and inorganic carbon (SIC) contents at regional scales can be very important for sustainable agriculture and soil management. Low variation in terrain attributes (classically used for digital soil mapping) at low relief areas calls for additional spatial data to explain soil variability. The main objective of this study was to evaluate the predictive capability of Sentinel-1 (radar) and Sentinel-2 (optical) time series and statistics, summarized as multi-temporal features (MTF) to improve the spatial predictions of SOC and SIC in Ghorveh plain, located in Kurdistan Province, Western Iran. A systematic grid sampling was then employed to collect 150 soil surface samples (0–30 cm) for SOC and SIC measurements. We applied boosted regression trees (BRT) and random forest (RF) to predict SOC and SIC contents by using covariate sets compiled from radar and optical time series and topographic attributes. Model performance, evaluated by 10-fold cross-validation, showed that RF using the covariate set containing time series of Sentinel-1, Sentinel-2 and topographic attributes performed the best in predicting SOC (RMSE = 0.23, ME = 0.005, R2 = 0.29). On the other hand, for SIC, the covariate set containing MTF of Sentinel-1, Sentinel-2 and topographic attributes ranked the best with BRT (RMSE = 0.77, ME= −0.001, R2 = 0.48). The study indicates that using the time series and MTF from multiple dates of remote sensing data with topographic attributes results in improved predictions. However, model performance for SIC and SOC was moderate to poor, respectively. Therefore more substantial studies would be required to verify if the computational effort is likely justified by an increase in accuracy in general. [ABSTRACT FROM AUTHOR]

The spatial distribution of soil pH, electrical conductivity, available nitrogen, phosphorus and potassium concentrations at Anaimalai block of Coimbatore district, India was interpolated by geostatistical analysis to create digital maps of soil NPK that renders numerous information for agro based policy making. 1627 soil samples in 30,700 acres were gathered by composite soil sampling method and rendered interpolation analysis to predict the soil parameters at unsampled locations. Based on geostatistical, deterministic and interpolation with barriers methods 13 interpolation models were generated and compared to validate the precision. Interpolation reveals the deficiency of soil available nitrogen and phosphorus whereas available potassium was in sufficient range. Radial basis function, inverse distance weighting, probability kriging, empirical Bayesian kriging and local polynomial interpolations were validated by linear correlation method that reveals the precisions of models with R2 values of 0.74, 0.82, 0.98, 0.89 and 0.79 (soil pH, EC, nitrogen, phosphorus and potassium respectively). [ABSTRACT FROM AUTHOR]

The aim of this study was to generate models to predict the salinity of the soils in the geothermal zone which is located in Michoacán, México, over space and time. Systematic sampling was performed at locations 400 m apart with a sampling period every 48 days. At each site, two soil samples, from depths of 0-30 cm and 30-60 cm, were collected and analysed in laboratory. Regression-Kriging was used to make spatial predictions of the electrical conductivity of soil (ECs). Spherical and Gaussian theoretical models fit the experimental semivariograms. The results showed that the soil samples ranged from slightly saline (2.1-4 dS m−1) to strongly saline (8.1-16 dS m−1). In addition, the ECs was greater at a depth of 30-60 cm than it was at a depth of 0-30 cm. The ECs decreased from more than 8.0 dS m−1 to less than 4.0 dS m−1 after the first sampling period. [ABSTRACT FROM AUTHOR]