This page has only limited features, please log in for full access.

Unclaimed
G.B.M. Heuvelink
Soil Geography and Landscape Group Wageningen University and Research Wageningen The Netherlands

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Original article
Published: 29 June 2021 in European Journal of Soil Science
Reads 0
Downloads 0

Spatial soil applications frequently involve binomial variables. If relevant environmental covariates are available, using a Bayesian generalised linear model (BGLM) might be a solution for mapping such discrete soil properties. The geostatistical extension, a Bayesian generalised linear geostatistical model (BGLGM) adds spatial dependence and is thus potentially better equipped. The objective of this work was to evaluate whether it pays off to extend from BGLM to BGLGM for mapping binary soil properties, evaluated in terms of prediction accuracy and modelling complexity. As motivating example, we mapped the presence/absence of the Pleistocene sand layer within 120 cm from the land surface in the Dutch province of Flevoland, using the BGLGM implementation in the R-package geoRglm. We found that BGLGM yields considerably better statistical validation metrics compared to BGLM, especially with – as in our case – a large (n = 1000) observation sample and few relevant covariates available. Also, the inferred posterior BGLGM parameters enable the quantification of spatial relationships. However, calibrating and applying a BGLGM is quite demanding with respect to the minimal required sample size, tuning the algorithm, and computational costs. We replaced manual tuning by an automated tuning algorithm (which eases implementing applications) and found a sample composition that delivers meaningful results within 50 hrs calculation time. With the gained insights and shared scripts spatial soil practitioners and researchers can – for their specific cases – evaluate if using BGLGM is feasible and if the extra gain is worth the extra effort.

ACS Style

Luc Steinbuch; Dick J. Brus; Gerard B. M. Heuvelink. Mapping depth to Pleistocene sand with Bayesian generalized linear geostatistical models. European Journal of Soil Science 2021, 1 .

AMA Style

Luc Steinbuch, Dick J. Brus, Gerard B. M. Heuvelink. Mapping depth to Pleistocene sand with Bayesian generalized linear geostatistical models. European Journal of Soil Science. 2021; ():1.

Chicago/Turabian Style

Luc Steinbuch; Dick J. Brus; Gerard B. M. Heuvelink. 2021. "Mapping depth to Pleistocene sand with Bayesian generalized linear geostatistical models." European Journal of Soil Science , no. : 1.

Original article
Published: 13 June 2021 in European Journal of Soil Science
Reads 0
Downloads 0

There is a growing demand for high quality soil data. However, soil measurements are subject to many error sources. We aimed to quantify uncertainties in synthetic and real-world wet chemistry soil data through a linear mixed-effects model, including batch and laboratory effects. The use of synthetic data allowed us to investigate how accurately the model parameters were estimated for various experimental measurement designs, whereas the real-world case served to explore if estimates of the random effect variances were still accurate for unbalanced datasets with few replicates. The variance estimates for synthetic pHH2O data were unbiased, but limited laboratory information led to imprecise estimates. The same was observed for unbalanced synthetic datasets, where 20 %, 50 % and 80 % of the data were removed randomly. Removal led to a sharp increase of the interquartile range (IQR) of the variance estimates for batch effect and the residual. The model was also fitted to real-world pHH2O and Total Organic Carbon (TOC) data, provided by the Wageningen Evaluating Programs for Analytical Laboratories (WEPAL). For pHH2O, the model yielded unbiased estimates with relatively small IQRs. However, the limited number of batches with replicate measurements (5.8 %) caused the batch effect to be larger than expected. A strong negative correlation between batch effect and residual variance suggested that the model could not distinguish well between these two random effects. For TOC, batch effect was removed from the model as no replicates were available within batches. Again, unbiased model estimates where obtained. However, the IQRs were relatively large, which could be attributed the smaller dataset with only a single replicate measurement. Our findings demonstrated the importance of experimental measurement design and replicate measurements in the quantification of uncertainties in wet chemistry soil data.

ACS Style

Cynthia C.E. van Leeuwen; Vera L. Mulder; Niels H. Batjes; Gerard B.M. Heuvelink. Statistical modelling of measurement error in wet chemistry soil data. European Journal of Soil Science 2021, 1 .

AMA Style

Cynthia C.E. van Leeuwen, Vera L. Mulder, Niels H. Batjes, Gerard B.M. Heuvelink. Statistical modelling of measurement error in wet chemistry soil data. European Journal of Soil Science. 2021; ():1.

Chicago/Turabian Style

Cynthia C.E. van Leeuwen; Vera L. Mulder; Niels H. Batjes; Gerard B.M. Heuvelink. 2021. "Statistical modelling of measurement error in wet chemistry soil data." European Journal of Soil Science , no. : 1.

Journal article
Published: 07 April 2021 in Agronomy
Reads 0
Downloads 0

It is vital for farmers to know if their land is suitable for the crops that they plan to grow. An increasing number of studies have used machine learning models based on land use data as an efficient means for mapping land suitability. This approach relies on the assumption that farmers grow their crops in the best-suited areas, but no studies have systematically tested this assumption. We aimed to test the assumption for specialty crops in Denmark. First, we mapped suitability for 41 specialty crops using machine learning. Then, we compared the predicted land suitabilities with the mechanistic model ECOCROP (Ecological Crop Requirements). The results showed that there was little agreement between the suitabilities based on machine learning and ECOCROP. Therefore, we argue that the methods represent different phenomena, which we label as socioeconomic suitability and ecological suitability, respectively. In most cases, machine learning predicts socioeconomic suitability, but the ambiguity of the term land suitability can lead to misinterpretation. Therefore, we highlight the need for increasing awareness of this distinction as a way forward for agricultural land suitability assessment.

ACS Style

Anders Møller; Vera Mulder; Gerard Heuvelink; Niels Jacobsen; Mogens Greve. Can We Use Machine Learning for Agricultural Land Suitability Assessment? Agronomy 2021, 11, 703 .

AMA Style

Anders Møller, Vera Mulder, Gerard Heuvelink, Niels Jacobsen, Mogens Greve. Can We Use Machine Learning for Agricultural Land Suitability Assessment? Agronomy. 2021; 11 (4):703.

Chicago/Turabian Style

Anders Møller; Vera Mulder; Gerard Heuvelink; Niels Jacobsen; Mogens Greve. 2021. "Can We Use Machine Learning for Agricultural Land Suitability Assessment?" Agronomy 11, no. 4: 703.

Preprint content
Published: 04 March 2021
Reads 0
Downloads 0

Since the establishment of Digital Soil Mapping (DSM) as a research field, the main focus has been on implementing new methods to improve the predictive performance of soil maps. However, considerably less effort has been invested in investigating the best way to communicate the quality of soil mapping products with users. This is essential for soil maps to be adopted by a broader community, future research guidance and most importantly, to ensure that they are used correctly. We introduce a high-resolution 3D soil modelling and mapping platform for the Netherlands (BIS-3D) using a quantile regression forest (QRF) for spatial interpolation approach that includes an assessment of the map quality using GlobalSoilMap (GSM) accuracy thresholds. Our objectives are twofold: a) providing accurate and high-resolution (25m) soil pH, soil organic carbon, and soil texture (clay, silt, and sand) maps over 3D space including prediction uncertainty; and b) providing an intuitive way to communicate accuracy of soil maps for users by means of accuracy thresholds. In this work, the first outputs of the modelling and mapping platform BIS-3D are being presented.

QRF models were trained and validated, yielding average predictions for each target location and depth as well as the 90% prediction interval. Predicted soil maps were evaluated using an independent validation data set based on a stratified random sampling design covering the entire Netherlands (1151 locations). Furthermore, at every validation location, predictions were assessed as A, AA or AAA quality using the GSM specifications.

First results for soil pH (KCl) using 15887 soil observations between depths 0-2 m and 180 covariates reveal a mean square error skill score (SSmse) = 0.88, RMSE = 0.49 and bias = 0.01 for out of bag predictions. Model evaluation using the independent validation set resulted in SSmse = 0.66, RMSE = 0.81 and bias = 0.12 across all depths. Prediction accuracy was highest for depths between 0-15 cm (SSmse = 0.66, RMSE = 0.76) and 60-100 cm (SSmse = 0.69, RMSE = 0.78) and lowest for 100-200 cm (SSmse = 0.61, RMSE = 0.86). The soil measurement (observation) was within the 90% prediction interval of model predictions in 83% of the cases, indicating that QRF is slightly over-optimistic in quantifying the prediction uncertainty. 61% of predictions that were independently validated over all depths were within the highest GSM accuracy threshold (AAA = +/- 0.5 pH), 23% were AA (+/- 1.0 pH), 9% were A (+/- 1.5 pH) and the remaining 7% were below A. A categorical physical geography map was the most important covariate, although other covariates associated with relief, geomorphology, land use and temperature were also effective. However, such variable importance measurements are merely indications and should be handled with care. The BIS-3D can easily be extended for predicting additional soil properties and it may provide a basis for decision makers to easily assess to what extent and in which areas soil maps can be used for their applications.

ACS Style

Anatol Helfenstein; Vera Leatitia Mulder; Gerard B.M. Heuvelink; Joop Okx. BIS-3D: high resolution 3D soil maps for the Netherlands using accuracy thresholds. 2021, 1 .

AMA Style

Anatol Helfenstein, Vera Leatitia Mulder, Gerard B.M. Heuvelink, Joop Okx. BIS-3D: high resolution 3D soil maps for the Netherlands using accuracy thresholds. . 2021; ():1.

Chicago/Turabian Style

Anatol Helfenstein; Vera Leatitia Mulder; Gerard B.M. Heuvelink; Joop Okx. 2021. "BIS-3D: high resolution 3D soil maps for the Netherlands using accuracy thresholds." , no. : 1.

Preprint content
Published: 04 March 2021
Reads 0
Downloads 0

Soil water content is a key property for modelling the water balance in hydrological, eco-hydrological and agro-hydrological models. Currently available global maps of soil water retention are mostly based on pedotransfer functions applied to maps of other basic soil properties. We developed global maps of the volumetric water content at 10, 33 and 1500 kPa by direct mapping based on soil water content data derived from the WoSIS Soil Profile Database and covariates describing vegetation, terrain morphology, climate, geology and hydrology using the SoilGrids workflow. The preparation of the input soil data consisted of the verification of available volumetric water content data and conversion of gravimetric to volumetric data using measured and estimated bulk density. In total we had 9609, 41082 and 49224 soil water content observations at 10, 33 and 1500 kPa, respectively, and prepared around 200 covariates as candidate predictors. After covariates selection, model tuning and cross-validation and final model fitting for 3D spatial prediction, results were presented for the globe with uncertainty estimation. The results were also compared to other available global maps of water retention to evaluate differences between direct mapping against other types of approaches. Directly developing global maps of soil water content, with associated uncertainty, is a novel approach for this type of properties, and contributes to improving global soil data availability and quality.

ACS Style

Maria Eliza Turek; Gerard Heuvelink; Niels Batjes; Laura Poggio. Global mapping of volumetric water content at 10, 33 and 1500 kPa using the WoSIS global database. 2021, 1 .

AMA Style

Maria Eliza Turek, Gerard Heuvelink, Niels Batjes, Laura Poggio. Global mapping of volumetric water content at 10, 33 and 1500 kPa using the WoSIS global database. . 2021; ():1.

Chicago/Turabian Style

Maria Eliza Turek; Gerard Heuvelink; Niels Batjes; Laura Poggio. 2021. "Global mapping of volumetric water content at 10, 33 and 1500 kPa using the WoSIS global database." , no. : 1.

Preprint content
Published: 04 March 2021
Reads 0
Downloads 0

Digital soil mapping (DSM) may be defined as the use of a statistical model to quantify the relationship between a certain observed soil property at various geographic locations, and a collection of environmental covariates, and then using this relationship to predict the soil property at locations where the property was not measured. It is also important to quantify the uncertainty with regards to prediction of these soil maps. An important source of uncertainty in DSM is measurement error which is considered as the difference between a measured and true value of a soil property.

The use of machine learning (ML) models such as random forests (RF) has become a popular trend in DSM. This is because ML models tend to be capable of accommodating highly non-linear relationships between the soil property and covariates. However, it is not clear how to incorporate measurement error into ML models. In this presentation we will discuss how to incorporate measurement error into some popular ML models, starting with incorporating weights into the objective function of ML models that implicitly assume a Gaussian error. We will discuss the effect that these modifications have on prediction accuracy, with reference to simulation studies.

ACS Style

Stephan van der Westhuizen; Gerard Heuvelink; David Hofmeyr. Measurement error-filtered machine learning in digital soil mapping. 2021, 1 .

AMA Style

Stephan van der Westhuizen, Gerard Heuvelink, David Hofmeyr. Measurement error-filtered machine learning in digital soil mapping. . 2021; ():1.

Chicago/Turabian Style

Stephan van der Westhuizen; Gerard Heuvelink; David Hofmeyr. 2021. "Measurement error-filtered machine learning in digital soil mapping." , no. : 1.

Preprint content
Published: 03 March 2021
Reads 0
Downloads 0

There is a growing demand for high quality soil data to model soil processes and map soil properties. However, wet chemistry measurements on soil properties are subjected to many error sources, such as the observer, the instrument and lack of standardised methodologies. Consequently, soil data are imperfect and uncertain because of these error sources. Uncertainties in measurements of fundamental soil properties can propagate through, e.g., pedotransfer functions, spectroscopic models and digital soil mapping algorithms. Therefore, it is important to provide detailed uncertainty information about soil measurements to potential data users. In practice, uncertainty estimates are rarely specified by providers of analytical soil data.

In this research, we aimed to quantify uncertainties in synthetic and real-world pH (1:1 soil-water suspension) and Total Organic Carbon (TOC) measurements. We assumed that uncertainty can be represented by a normal distribution. A linear mixed-effects model was applied to estimate the parameters of the normal distribution, i.e., mean and standard deviation, of both synthetic and real-world datasets. The model included ‘sample ID’ as a fixed effect, and ‘batch’ and ‘laboratory’ as random effects. The use of synthetic datasets allowed us to investigate how well the model parameters could be estimated given a specific experimental measurement design, whereas the real-world case served to explore if the parameter estimates were still accurate for such unbalanced datasets.

For a balanced dataset (n=20, n=100, n=200 and n=500), using synthetic pH data for three hypothetical laboratories (two batches per laboratory), the mean estimated standard deviations (σ) of the random effects were σbatch=0.10, σlaboratory=0.24 and σresidual=0.2. These estimates were in agreement with the σ for the respective random effects used to generate the synthetic dataset, meaning that the model could accurately estimate the model parameters. Subsequently, changes were made to the experimental measurement design by randomly removing 20%, 50% and 80% of the data, resulting in unbalanced datasets. In general, the interquartile range (IQR) of σ for each random effect increased with a larger percentage of removed data. However, the increase in IQR was larger for n=20 compared to, e.g., n=200. When comparing 0% and 80% randomly removed data, the IQR for the batch effect increased with 60.3%. Conversely, for n=200 an increase of only 23.5% was observed.

Subsequently, the same model was fitted on real-world pH and TOC data, provided by the Wageningen Evaluating Programs for Analytical Laboratories (WEPAL). The unbalanced dataset structure was first reconstructed and filled with synthetically generated data, based on sample means and standard deviations derived from the measured data. The model was fitted on both datasets. For measured pH, the model yielded σbatch=0.27, σlaboratory=0.17 and σresidual=0.10. The IQRs of the estimated σ from synthetic WEPAL data were 0.04 (batch), 0.06 (laboratory) and 0.02 (residual). The model fitted on the measured TOC data estimated σbatch=5.3%, σlaboratory=2.8% and σresidual=2.1%. For the synthetic WEPAL data, IQRs of 1.3% (batch), 1.4% (laboratory) and 0.4% (residual) were determined for the estimated σ. These findings suggest that despite having a highly unbalanced dataset, realistic model parameter estimates can still be obtained.

ACS Style

Cynthia van Leeuwen; Titia Mulder; Niels Batjes; Gerard Heuvelink. Statistical modelling of measurement error in wet chemistry soil data. 2021, 1 .

AMA Style

Cynthia van Leeuwen, Titia Mulder, Niels Batjes, Gerard Heuvelink. Statistical modelling of measurement error in wet chemistry soil data. . 2021; ():1.

Chicago/Turabian Style

Cynthia van Leeuwen; Titia Mulder; Niels Batjes; Gerard Heuvelink. 2021. "Statistical modelling of measurement error in wet chemistry soil data." , no. : 1.

Journal article
Published: 13 January 2021 in Hydrology and Earth System Sciences
Reads 0
Downloads 0

Uncertainty is often ignored in urban water systems modelling. Commercial software used in engineering practice often ignores the uncertainties of input variables and their propagation because of a lack of user-friendly implementations. This can have serious consequences, such as the wrong dimensioning of urban drainage systems (UDSs) and the inaccurate estimation of pollution released to the environment. This paper introduces an uncertainty analysis in urban drainage modelling, built on existing methods and applied to a case study in the Haute-Sûre catchment in Luxembourg. The case study makes use of the EmiStatR model which simulates the volume and substance flows in UDS using simplified representations of the drainage system and processes. A Monte Carlo uncertainty propagation analysis showed that uncertainties in chemical oxygen demand (COD) and ammonium (NH4) loads and concentrations can be large and have a high temporal variability. Furthermore, a stochastic sensitivity analysis that assesses the uncertainty contributions of input variables to the model output response showed that precipitation has the largest contribution to output uncertainty related with water quantity variables, such as volume in the chamber, overflow volume, and flow. Regarding the water quality variables, the input variable related to COD in wastewater has an important contribution to the uncertainty for the COD load (66 %) and COD concentration (62 %). Similarly, the input variable related to NH4 in wastewater plays an important role in the contribution of total uncertainty for the NH4 load (34 %) and NH4 concentration (35 %). The Monte Carlo (MC) simulation procedure used to propagate input uncertainty showed that, among the water quantity output variables, the overflow flow is the most uncertain output variable, with a coefficient of variation (cv) of 1.59. Among water quality variables, the annual average spill COD concentration and the average spill NH4 concentration were the most uncertain model outputs (coefficients of variation of 0.99 and 0.82, respectively). Also, low standard errors for the coefficient of variation were obtained for all seven outputs. These were never greater than 0.05, which indicates that the selected MC replication size (1500 simulations) was sufficient. We also evaluated how the uncertainty propagation can more comprehensively explain the impact of water quality indicators for the receiving river. While the mean model water quality outputs for COD and NH4 concentrations were slightly above the threshold, the 0.95 quantile was 2.7 times above the mean value for COD concentration and 2.4 times above the mean value for NH4. This implies that there is a considerable probability that these concentrations in the spilled combined sewer overflow (CSO) are substantially larger than the threshold. However, COD and NH4 concentration levels of the river water will likely stay below the water quality threshold, due to rapid dilution after CSO spill enters the river.

ACS Style

Jairo Arturo Torres-Matallana; Ulrich Leopold; Gerard B. M. Heuvelink. Multivariate autoregressive modelling and conditional simulation for temporal uncertainty analysis of an urban water system in Luxembourg. Hydrology and Earth System Sciences 2021, 25, 193 -216.

AMA Style

Jairo Arturo Torres-Matallana, Ulrich Leopold, Gerard B. M. Heuvelink. Multivariate autoregressive modelling and conditional simulation for temporal uncertainty analysis of an urban water system in Luxembourg. Hydrology and Earth System Sciences. 2021; 25 (1):193-216.

Chicago/Turabian Style

Jairo Arturo Torres-Matallana; Ulrich Leopold; Gerard B. M. Heuvelink. 2021. "Multivariate autoregressive modelling and conditional simulation for temporal uncertainty analysis of an urban water system in Luxembourg." Hydrology and Earth System Sciences 25, no. 1: 193-216.

Journal article
Published: 03 November 2020 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Reads 0
Downloads 0

The Surface Soil Moisture (SSM) products derived from microwave remote sensing have a coarse spatial resolution, therefore downscaling is required to obtain accurate SSM at high spatial resolution. An effective way to handle the stratified heterogeneity is to model for various stratifications, however the number of samples is often limited under each stratification, influencing the downscaling accuracy. In this study, a machine learning-based geostatistical model, which combines various ancillary information at fine spatial scale, is developed for spatial downscaling. The proposed support vector area-to-area regression kriging (SVATARK) model incorporates support vector regression and area-to-area kriging by considering the nonlinear relationships among variables for various stratifications. SVATARK also considers the change of support problem in the downscaling interpolation process as well as for solving the small sample size in trend prediction. The SVATARK method is evaluated in the Naqu region on the Tibetan Plateau, China to downscale the European Space Agency's (ESA) 25-km-resolution SSM product. The 1-km-resolution SSM predictions have been produced every 8 days over a six-year period (2010-2015). Compared with other five downscaling methods, the downscaled predictions from the SVATARK method performs the best with in-situ observations, resulting in a 24.4 percent reduction in root mean square error with 0.08 m3.m-3 and a 8.2 percent increase in correlation coefficient with 0.72, on average. Additionally, anomalously low SSM values, an indicator of drought, had a record low anomaly in mid-July for 2015, as noted by previous studies, indicating that SVATARK could be utilized for drought monitoring.

ACS Style

Yan Jin; Yong Ge; Yaojie Liu; Yuehong Chen; Haitao Zhang; Gerard B. M. Heuvelink. A Machine Learning-Based Geostatistical Downscaling Method for Coarse-Resolution Soil Moisture Products. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2020, 14, 1025 -1037.

AMA Style

Yan Jin, Yong Ge, Yaojie Liu, Yuehong Chen, Haitao Zhang, Gerard B. M. Heuvelink. A Machine Learning-Based Geostatistical Downscaling Method for Coarse-Resolution Soil Moisture Products. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2020; 14 (99):1025-1037.

Chicago/Turabian Style

Yan Jin; Yong Ge; Yaojie Liu; Yuehong Chen; Haitao Zhang; Gerard B. M. Heuvelink. 2020. "A Machine Learning-Based Geostatistical Downscaling Method for Coarse-Resolution Soil Moisture Products." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14, no. 99: 1025-1037.

Preprint content
Published: 10 July 2020
Reads 0
Downloads 0

Uncertainty is often ignored in urban water systems modelling. Commercial software used in engineering practice often ignores uncertainties of input variables and their propagation because of a lack of user-friendly implementations. This can have serious consequences, such as the wrong dimensioning of urban drainage systems (UDS) and the inaccurate estimation of pollution released to the environment. This paper introduces an uncertainty analysis framework in urban drainage modelling and applies it to a case study in the Haute-Sûre catchment in Luxembourg. The framework makes use of the EmiStatR model which simulates the volume and substance flows in UDS using simplified representations of the drainage system and processes. A Monte Carlo uncertainty propagation analysis showed that uncertainties in chemical oxygen demand (COD) and ammonium (NH4) loads and concentrations can be large and have a high temporal variability. Further, a stochastic sensitivity analysis that assesses the uncertainty contributions of input variables to the model output response showed that precipitation has the largest contribution to output uncertainty related with water quantity variables, such as volume in the chamber, overflow volume and flow. Regarding the water quality variables, the input variable related to COD in the wastewater has an important contribution to the uncertainty for COD load (66 %) and COD concentration (62 %). Similarly, the input variable related to NH4 in the wastewater plays an important role in the contribution of total uncertainty for NH4 load (34 %) and NH4 concentration (35 %). The Monte Carlo simulation procedure used to propagate input uncertainty showed that among the water quantity output variables, the overflow flow is the most uncertain output variable with a coefficient of variation (cv) of 1.59. Among water quality variables, the annual average spill COD oncentration and the average spill NH4 concentration were the most uncertain model outputs (coefficients of variation of 0.99 and 0.82, respectively). Also, low standard errors for the coefficient of variation were obtained for all seven outputs. These were never greater than 0.05, which indicates that the selected MC replication size (1,500 simulations) was sufficient. We also evaluated how uncertainty propagation can explain more comprehensively the impact of water quality indicators for the receiving river. While the mean model water quality outputs for COD and NH4 concentrations were slightly above the threshold, the 0.95 quantile was 2.7 times above the mean value for COD concentration, and 2.4 times above the mean value for NH4. This implies that there is a considerable probability that these concentrations in the spilled CSO are substantially larger than the threshold. However, COD and NH4 concentration levels of the river water will likely stay below the water quality threshold, due to rapid dilution after CSO spill enters the river.

ACS Style

Jairo Arturo Torres-Matallana; Ulrich Leopold; Gerard B. M. Heuvelink. Multivariate autoregressive modelling and conditional simulation for temporal uncertainty propagation in urban water systems. 2020, 1 -40.

AMA Style

Jairo Arturo Torres-Matallana, Ulrich Leopold, Gerard B. M. Heuvelink. Multivariate autoregressive modelling and conditional simulation for temporal uncertainty propagation in urban water systems. . 2020; ():1-40.

Chicago/Turabian Style

Jairo Arturo Torres-Matallana; Ulrich Leopold; Gerard B. M. Heuvelink. 2020. "Multivariate autoregressive modelling and conditional simulation for temporal uncertainty propagation in urban water systems." , no. : 1-40.

Journal article
Published: 25 May 2020 in Remote Sensing
Reads 0
Downloads 0

For many decades, kriging and deterministic interpolation techniques, such as inverse distance weighting and nearest neighbour interpolation, have been the most popular spatial interpolation techniques. Kriging with external drift and regression kriging have become basic techniques that benefit both from spatial autocorrelation and covariate information. More recently, machine learning techniques, such as random forest and gradient boosting, have become increasingly popular and are now often used for spatial interpolation. Some attempts have been made to explicitly take the spatial component into account in machine learning, but so far, none of these approaches have taken the natural route of incorporating the nearest observations and their distances to the prediction location as covariates. In this research, we explored the value of including observations at the nearest locations and their distances from the prediction location by introducing Random Forest Spatial Interpolation (RFSI). We compared RFSI with deterministic interpolation methods, ordinary kriging, regression kriging, Random Forest and Random Forest for spatial prediction (RFsp) in three case studies. The first case study made use of synthetic data, i.e., simulations from normally distributed stationary random fields with a known semivariogram, for which ordinary kriging is known to be optimal. The second and third case studies evaluated the performance of the various interpolation methods using daily precipitation data for the 2016–2018 period in Catalonia, Spain, and mean daily temperature for the year 2008 in Croatia. Results of the synthetic case study showed that RFSI outperformed most simple deterministic interpolation techniques and had similar performance as inverse distance weighting and RFsp. As expected, kriging was the most accurate technique in the synthetic case study. In the precipitation and temperature case studies, RFSI mostly outperformed regression kriging, inverse distance weighting, random forest, and RFsp. Moreover, RFSI was substantially faster than RFsp, particularly when the training dataset was large and high-resolution prediction maps were made.

ACS Style

Aleksandar Sekulić; Milan Kilibarda; Gerard B.M. Heuvelink; Mladen Nikolić; Branislav Bajat. Random Forest Spatial Interpolation. Remote Sensing 2020, 12, 1687 .

AMA Style

Aleksandar Sekulić, Milan Kilibarda, Gerard B.M. Heuvelink, Mladen Nikolić, Branislav Bajat. Random Forest Spatial Interpolation. Remote Sensing. 2020; 12 (10):1687.

Chicago/Turabian Style

Aleksandar Sekulić; Milan Kilibarda; Gerard B.M. Heuvelink; Mladen Nikolić; Branislav Bajat. 2020. "Random Forest Spatial Interpolation." Remote Sensing 12, no. 10: 1687.

Special issue article
Published: 20 May 2020 in European Journal of Soil Science
Reads 0
Downloads 0

Spatially resolved estimates of change in soil organic carbon (SOC) stocks are necessary for supporting national and international policies aimed at achieving land degradation neutrality and climate change mitigation. In this work we report on the development, implementation and application of a data‐driven, statistical method for mapping SOC stocks in space and time, using Argentina as a pilot. We used Quantile Regression Forest machine‐learning to predict annual SOC stock at 0–30 cm depth at 250 m resolution for Argentina between 1982 and 2017. The model was calibrated using over 5,000 SOC stock values from the 36‐year time period and 35 environmental covariates. We pre‐processed NDVI dynamic covariates using a temporal low‐pass filter to allow the SOC stock for a given year to depend on the NDVI of the current as well as preceding years. Predictions had modest temporal variation with an average decrease for the entire country from 2.55 kg C m−2 to 2.48 kg C m−2 over the 36‐year period (equivalent to a decline of 211 Gg C, 3.0% of the total 0–30 cm SOC stock in Argentina). The Pampa region had a larger estimated SOC stock decrease from 4.62 kg C m−2 to 4.34 kg C m−2 (5.9%) during the same period. For the 2001–2015 period, predicted temporal variation was 7‐fold larger than that obtained using the Tier 1 approach of the IPCC and UNCCD. Prediction uncertainties turned out to be substantial, mainly due to the limited number and poor spatial and temporal distribution of the calibration data, and the limited explanatory power of the covariates. Cross‐validation confirmed that SOC stock prediction accuracy was limited, with a Mean Error of 0.03 kg C m−2 and a Root Mean Squared Error of 2.04 kg C m−2. In spite of the large uncertainties, this work showed that machine learning methods can be used for space–time SOC mapping and may yield valuable information to land managers and policy makers, provided that SOC observation density in space and time is sufficiently large. This article is protected by copyright. All rights reserved.

ACS Style

Gerard B. M. Heuvelink; Marcos E. Angelini; Laura Poggio; Zhanguo Bai; Niels H. Batjes; Rik Van Den Bosch; Deborah Bossio; Sergio Estella; Johannes Lehmann; Guillermo F. Olmedo; Jonathan Sanderman. Machine learning in space and time for modelling soil organic carbon change. European Journal of Soil Science 2020, 1 .

AMA Style

Gerard B. M. Heuvelink, Marcos E. Angelini, Laura Poggio, Zhanguo Bai, Niels H. Batjes, Rik Van Den Bosch, Deborah Bossio, Sergio Estella, Johannes Lehmann, Guillermo F. Olmedo, Jonathan Sanderman. Machine learning in space and time for modelling soil organic carbon change. European Journal of Soil Science. 2020; ():1.

Chicago/Turabian Style

Gerard B. M. Heuvelink; Marcos E. Angelini; Laura Poggio; Zhanguo Bai; Niels H. Batjes; Rik Van Den Bosch; Deborah Bossio; Sergio Estella; Johannes Lehmann; Guillermo F. Olmedo; Jonathan Sanderman. 2020. "Machine learning in space and time for modelling soil organic carbon change." European Journal of Soil Science , no. : 1.

Preprint content
Published: 23 March 2020
Reads 0
Downloads 0

Heavy metal contamination in soil is a major environmental issue intensified by rapid industrial and population growth. Understanding the spatial distribution of soil contamination by heavy metals in the ecosystem is a necessary precondition to monitor soil health and to assess the ecological risks. The main sources of heavy metals in soil are natural and anthropogenic sources. Natural sources are typically released of heavy metals from rock by weathering and atmospheric precipitation. Anthropogenic sources are related to industrialization, rapid urbanization, agricultural practices, and military activities. We analyzed a total of 358 topsoil samples (0–30 cm) collected in Golestan province in the northeast of Iran based on a regular square grid networks with 1,700 squares each sized 2.5 km²(random sampling within the grid). From these samples, we determined the spatial distribution of Cd, Cu, Ni, Zn, and Pb using random forest (RF). A multi-spectral image (Landsat 8), and environmental derivatives calculated from terrain attributes, climatic parameters, parent material, land use maps, distances to mine sectors, main roads, industrial sites, and rivers were used as covariates to predict the spatial distribution of concentrations of heavy metals. The multi-collinearity of the predictors was examined by the variance inflation factor (VIF), and a feature selection process (genetic algorithm) was applied to avoid noise and optimize the selected input variables for the final model. The predictive accuracy of RF model was assessed by the mean prediction error (ME), root mean squared error (RMSE), and coefficient of determination (R2) using 5-fold cross-validation technique. The results showed that the concentration levels (mg kg-1) of Cd, Cu, Pb, Ni, and Zn varied from 0.02 to 2.75, 9.70 to 93.70, 6.80 to 114.20, 9.50 to 93.20, and 25.10 to 417.4, respectively. The best prediction performance was for Ni (RMSE=9.9 mg kg-1 and R2=56.6%), and the lowest prediction performance for Cd (RMSE=0.4 mg kg-1 and R2=28.0%). Environmental covariates that control soil moisture and water flow along with climatic factors were the most important variables to define the spatial distribution of soil heavy metals. We conclude that the RF model using easily accessible environmental covariates is a promising, cost-effective and fast approach to monitor the spatial distribution of heavy metal contamination in soils.

Keywords: Heavy metals; digital soil mapping; machine learning; random forest; spatial variation; soil pollution.

ACS Style

Mojtaba Zeraatpisheh; Rouhollah Mirzaei; Younes Garosi; Ming Xu; Gerard B.M. Heuvelink; Thomas Scholten; Ruhollah Taghizadeh-Mehrjardi. Feasibility of using environmental covariates and machine learning to predict the spatial variability of selected heavy metals in soils. 2020, 1 .

AMA Style

Mojtaba Zeraatpisheh, Rouhollah Mirzaei, Younes Garosi, Ming Xu, Gerard B.M. Heuvelink, Thomas Scholten, Ruhollah Taghizadeh-Mehrjardi. Feasibility of using environmental covariates and machine learning to predict the spatial variability of selected heavy metals in soils. . 2020; ():1.

Chicago/Turabian Style

Mojtaba Zeraatpisheh; Rouhollah Mirzaei; Younes Garosi; Ming Xu; Gerard B.M. Heuvelink; Thomas Scholten; Ruhollah Taghizadeh-Mehrjardi. 2020. "Feasibility of using environmental covariates and machine learning to predict the spatial variability of selected heavy metals in soils." , no. : 1.

Journal article
Published: 20 March 2020 in European Journal of Agronomy
Reads 0
Downloads 0

Nitrogen use efficiency (NUE) is crucial to establish efficient fertilizer application guidelines that balance crop yield, economic return and environmental sustainability. Although there are quite a few researches about the spatial and temporal variation of NUE, little work has been done on modelling NUE through deriving empirical relationships with explanatory environmental variables and exploring their relative importance quantitatively. The space-time patterns of NUE indicators (i.e., the Partial Factor Productivity of nitrogen, PFPN, and the Partial Nutrient Balance of nitrogen, PNBN) at provincial scale in China were derived and related to environmental covariates using stepwise multiple linear regression. PFPN was higher in east and south China than in central and west China and was smaller than 30 kg kg−1 yr−1 in most provinces, while PNBN was moderate in most provinces (0.41–0.50 kg kg−1 yr−1) and low (< 0.40 kg kg−1 yr−1) in south China. The national PFPN declined slightly from 32 kg kg−1 in 1978 to 27 kg kg−1 in 1995 and went up gradually to reach 38 kg kg−1 in 2015. The national PNBN decreased from 0.53 to 0.36 kg kg−1 from 1978 to 2003, thereafter stabilizing at around 0.40 kg kg−1 yr−1 between 2004 and 2015. The multiple linear regression models explained 74 % of the variance of PFPN and PNBN. The main explanatory variables of PFPN were planting area index of sugar crop (32 % of the R-square), followed by Arenosols (12 %), planting area index of oil crop (8 %), planting area index of vegetables (5 %), silt content (5 %) and total potassium (5 %). For PNBN, the variation was mainly attributed to mean annual daytime surface temperature (28 % of the R-square), planting area index of crops (beans 20 %, orchards 10 % and vegetables 9 %) and wet day frequency (5 %). The results of this study indicate that crop types, temperature and soil properties are important variables that determine NUE. These should be considered by policy makers when agricultural land development decisions are made in order to balance NUE and productivity (i.e., agronomy and environment).

ACS Style

Yingxia Liu; Gerard B.M. Heuvelink; Zhanguo Bai; Ping He; Xinpeng Xu; Jinchuan Ma; Dainius Masiliūnas. Space-time statistical analysis and modelling of nitrogen use efficiency indicators at provincial scale in China. European Journal of Agronomy 2020, 115, 126032 .

AMA Style

Yingxia Liu, Gerard B.M. Heuvelink, Zhanguo Bai, Ping He, Xinpeng Xu, Jinchuan Ma, Dainius Masiliūnas. Space-time statistical analysis and modelling of nitrogen use efficiency indicators at provincial scale in China. European Journal of Agronomy. 2020; 115 ():126032.

Chicago/Turabian Style

Yingxia Liu; Gerard B.M. Heuvelink; Zhanguo Bai; Ping He; Xinpeng Xu; Jinchuan Ma; Dainius Masiliūnas. 2020. "Space-time statistical analysis and modelling of nitrogen use efficiency indicators at provincial scale in China." European Journal of Agronomy 115, no. : 126032.

Journal article
Published: 06 February 2020 in Geoderma
Reads 0
Downloads 0

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.

ACS Style

Songchao Chen; Vera Leatitia Mulder; Gerard B.M. Heuvelink; Laura Poggio; Manon Caubet; Mercedes Román Dobarco; Christian Walter; Dominique Arrouays. Model averaging for mapping topsoil organic carbon in France. Geoderma 2020, 366, 114237 .

AMA Style

Songchao Chen, Vera Leatitia Mulder, Gerard B.M. Heuvelink, Laura Poggio, Manon Caubet, Mercedes Román Dobarco, Christian Walter, Dominique Arrouays. Model averaging for mapping topsoil organic carbon in France. Geoderma. 2020; 366 ():114237.

Chicago/Turabian Style

Songchao Chen; Vera Leatitia Mulder; Gerard B.M. Heuvelink; Laura Poggio; Manon Caubet; Mercedes Román Dobarco; Christian Walter; Dominique Arrouays. 2020. "Model averaging for mapping topsoil organic carbon in France." Geoderma 366, no. : 114237.

Conference paper
Published: 29 January 2020 in Security Education and Critical Infrastructures
Reads 0
Downloads 0

SoilGrids maps soil properties for the entire globe at medium spatial resolution (250 m cell side) using state-of-the-art machine learning methods. The expanding pool of input data and the increasing computational demands of predictive models required a prediction framework that could deal with large data. This article describes the mechanisms set in place for a geo-spatially parallelised prediction system for soil properties. The features provided by GRASS GIS – mapset and region – are used to limit predictions to a specific geographic area, enabling parallelisation. The Slurm job scheduler is used to deploy predictions in a high-performance computing cluster. The framework presented can be seamlessly applied to most other geo-spatial process requiring parallelisation. This framework can also be employed with a different job scheduler, GRASS GIS being the main requirement and engine.

ACS Style

Luís M. De Sousa; Laura Poggio; Gwen Dawes; Bas Kempen; Rik Van Den Bosch. Computational Infrastructure of SoilGrids 2.0. Security Education and Critical Infrastructures 2020, 24 -31.

AMA Style

Luís M. De Sousa, Laura Poggio, Gwen Dawes, Bas Kempen, Rik Van Den Bosch. Computational Infrastructure of SoilGrids 2.0. Security Education and Critical Infrastructures. 2020; ():24-31.

Chicago/Turabian Style

Luís M. De Sousa; Laura Poggio; Gwen Dawes; Bas Kempen; Rik Van Den Bosch. 2020. "Computational Infrastructure of SoilGrids 2.0." Security Education and Critical Infrastructures , no. : 24-31.

Journal article
Published: 02 August 2019 in Remote Sensing
Reads 0
Downloads 0

Super-resolution mapping (SRM) is used to obtain fine-scale land cover maps from coarse remote sensing images. Spatial attraction, geostatistics, and using prior geographic information are conventional approaches used to derive fine-scale land cover maps. As the convolutional neural network (CNN) has been shown to be effective in capturing the spatial characteristics of geographic objects and extrapolating calibrated methods to other study areas, it may be a useful approach to overcome limitations of current SRM methods. In this paper, a new SRM method based on the CNN (SRMCNN) is proposed and tested. Specifically, an encoder-decoder CNN is used to model the nonlinear relationship between coarse remote sensing images and fine-scale land cover maps. Two real-image experiments were conducted to analyze the effectiveness of the proposed method. The results demonstrate that the overall accuracy of the proposed SRMCNN method was 3% to 5% higher than that of two existing SRM methods. Moreover, the proposed SRMCNN method was validated by visualizing output features and analyzing the performance of different geographic objects.

ACS Style

Yuanxin Jia; Yong Ge; Yuehong Chen; Sanping Li; Gerard B.M. Heuvelink; Feng Ling. Super-Resolution Land Cover Mapping Based on the Convolutional Neural Network. Remote Sensing 2019, 11, 1815 .

AMA Style

Yuanxin Jia, Yong Ge, Yuehong Chen, Sanping Li, Gerard B.M. Heuvelink, Feng Ling. Super-Resolution Land Cover Mapping Based on the Convolutional Neural Network. Remote Sensing. 2019; 11 (15):1815.

Chicago/Turabian Style

Yuanxin Jia; Yong Ge; Yuehong Chen; Sanping Li; Gerard B.M. Heuvelink; Feng Ling. 2019. "Super-Resolution Land Cover Mapping Based on the Convolutional Neural Network." Remote Sensing 11, no. 15: 1815.

Journal article
Published: 11 April 2019 in Journal of Hydrology
Reads 0
Downloads 0

The importance of representing the spatial structure of rainfall accurately has been emphasized in various hydrological studies. It has also been widely acknowledged that there is a need to account for uncertainty in rainfall input. Common approaches focus on accounting for either point measurement or sampling uncertainty in rainfall estimation. We present a method that jointly considers three sources of uncertainty affecting the space-time mapping of rainfall: point measurement, sampling and neighborhood uncertainty. To our knowledge, neighborhood uncertainty has not been included in any prior rainfall uncertainty analysis. We generated an ensemble of 400 realizations of daily rainfall fields at a 2 km x 2 km spatial resolution for a catchment in Western Denmark (1055 km2). At the core of our method is the sequential Gaussian simulation (SGS) technique. Results indicate that our approach is able to reproduce key statistical features of the rainfall distribution. We examined the impact of different spatial (grid and catchment) and temporal supports (one day, one month, 5-year period) on the overall uncertainty. We also quantified the effect of each uncertainty source on rainfall field uncertainty. Finally, we compared our simulation results with those of a parallel expert elicitation study. We found that the expert elicitation uncertainty for average catchment rainfall in a 5-year period was considerably larger than quantified in our study (CV of 1.1 % vs. 5 %). An even larger discrepancy was found for the 5-year average of gauge rainfall, where expert elicitation resulted in a value that was an order of magnitude higher (CV of 0.2 % vs. 2 %). Possible reasons for this gap are discussed.

ACS Style

L.B. Ehlers; T.O. Sonnenborg; Gerard Heuvelink; Xin He; J.C. Refsgaard. Joint treatment of point measurement, sampling and neighborhood uncertainty in space-time rainfall mapping. Journal of Hydrology 2019, 574, 148 -159.

AMA Style

L.B. Ehlers, T.O. Sonnenborg, Gerard Heuvelink, Xin He, J.C. Refsgaard. Joint treatment of point measurement, sampling and neighborhood uncertainty in space-time rainfall mapping. Journal of Hydrology. 2019; 574 ():148-159.

Chicago/Turabian Style

L.B. Ehlers; T.O. Sonnenborg; Gerard Heuvelink; Xin He; J.C. Refsgaard. 2019. "Joint treatment of point measurement, sampling and neighborhood uncertainty in space-time rainfall mapping." Journal of Hydrology 574, no. : 148-159.

Special issue article
Published: 29 November 2018 in European Journal of Soil Science
Reads 0
Downloads 0

In 1992 pedometrics as a concept became Pedometrics in the formal sense, with the establishment of a Working Group of the International Union of Soil Sciences (IUSS) and a first conference in Wageningen, the Netherlands (de Gruijter et al., 1994). To celebrate its 25th anniversary, the pedometrics community therefore convened again in Wageningen in 2017. This special issue is one of two that contains selected papers presented at the 2017 Pedometrics conference. These special issues nicely show how pedometrics has matured over the past 25 years. This article is protected by copyright. All rights reserved.

ACS Style

G. B. M. Heuvelink; D. J. Brus; D G Rossiter; Z. Shi. Editorial for pedometrics 2017 special issue. European Journal of Soil Science 2018, 70, 25 -26.

AMA Style

G. B. M. Heuvelink, D. J. Brus, D G Rossiter, Z. Shi. Editorial for pedometrics 2017 special issue. European Journal of Soil Science. 2018; 70 (1):25-26.

Chicago/Turabian Style

G. B. M. Heuvelink; D. J. Brus; D G Rossiter; Z. Shi. 2018. "Editorial for pedometrics 2017 special issue." European Journal of Soil Science 70, no. 1: 25-26.

Journal article
Published: 01 September 2018 in Computers & Geosciences
Reads 0
Downloads 0
ACS Style

Milutin Pejović; Mladen Nikolić; Gerard B.M. Heuvelink; Tomislav Hengl; Milan Kilibarda; Branislav Bajat. Sparse regression interaction models for spatial prediction of soil properties in 3D. Computers & Geosciences 2018, 118, 1 -13.

AMA Style

Milutin Pejović, Mladen Nikolić, Gerard B.M. Heuvelink, Tomislav Hengl, Milan Kilibarda, Branislav Bajat. Sparse regression interaction models for spatial prediction of soil properties in 3D. Computers & Geosciences. 2018; 118 ():1-13.

Chicago/Turabian Style

Milutin Pejović; Mladen Nikolić; Gerard B.M. Heuvelink; Tomislav Hengl; Milan Kilibarda; Branislav Bajat. 2018. "Sparse regression interaction models for spatial prediction of soil properties in 3D." Computers & Geosciences 118, no. : 1-13.