Records 1 - 20 / 97

  • help
  • export

    Export search results

Check title to add to marked list
Evaluating different soil compaction measurement techniques: simplicity versus Complexity
Schierholz, Robert ; Orsouw, T.L. van; Mulder, V.L. ; Schoorl, J.M. ; Heuvelink, G.B.M. - 2019
In: Understanding soil functions, Wageningen Soil Conference. - - p. 56 - 56.
The problem of soil compaction in agricultural fields through trampling, drying and wetting processes, and tillage is well known in the Netherlands. It leads to a change in soil structure which impacts soil properties and processes. Consequently, crop yields will reduce causing financial losses to farmers. Therefore, there is a need for cost-effective soil compaction measurement techniques. However, soil compaction cannot be directly assessed by a specific measurement technique. Therefore, a reliable proxy is needed allowing to identify and quantify soil compaction. For this, a field experiment was set up involving 31 persons and four contemporary methods were tested for the estimation of in-situ soil bulk density 1) core sampling, 2) the ‘knife method’, 3) Penetrologger, 4) RhoC.
In this field experiment various sources of error were accounted for using basic statistical analysis, including the uncertainties in the measurement equipment, human error or small-scale variability. Results show that the Penetrologger was capable to identify the start of the compacted layer but was not capable to estimate the depth of the layer and was prone to ‘human’ error. Therefore, the Penetrologger was deemed the least suitable method. Considering the simplicity of the knife method it performed very well, even inexperienced people were able to identify the start of soil compaction. Yet it remains a qualitative and more uncertain method, due to its subjectivity of the human’s perception of changes in bulk density and soil strength. The RhoC was the best alternative method compared to the core samples to quantify bulk density.

Challenges for soil functions assessment and mapping at continental scale and some preliminary results
Poggio, Laura ; Batjes, N.H. ; Leeuw, Jan de; Heuvelink, G.B.M. ; Leenaars, J.G.B. ; Mantel, S. ; Turdukulov, Ulan ; Kempen, B. ; Rossiter, David ; Bosch, H. van den; Lynden, G.W.J. van - 2019
In: Geophysical Research Abstracts. - EGU - 1 p.
SoilGrids: consistent soil information to assess and map soil functions at global scale
Poggio, Laura ; Duque Moreira de Sousa, Luïs ; Heuvelink, G.B.M. ; Kempen, B. ; Batjes, N.H. ; Leenaars, J.G.B. ; Mantel, S. ; Bai, Z.G. ; Turdukulov, Ulan ; Ruiperez Gonzalez, M. ; Carvalho Ribeiro, E.D. ; Rossiter, David ; Bosch, H. van den - 2019
In: Wageningen Soil Conference: Understanding Soil Functions. - Wageningen : ISRIC - p. 50 - 51.
Space-time mapping of soil organic carbon concentration and stock to support land degradation neutrality and climate mitigation policies.
Heuvelink, G.B.M. ; Poggio, Laura ; Angelini, M.E. ; Bai, Z.G. ; Batjes, N.H. ; Bosch, H. van den; Bossio, Deborah ; Lehmann, J. ; Martinez, A. ; Olmedo, G.F. ; Tobes, P.P. ; Sanderman, Jonathan - 2019
In: Wageningen Soil Conference: Understanding Soil Functions. - Wageningen : ISRIC - p. 26 - 26.
The science base of a strategic research agenda - Executive Summary
Bray, A.W. ; Kim, J.H. ; Schrumpf, M. ; Peacock, C. ; Banwart, S. ; Schipper, L. ; Angers, D. ; Chirinda, N. ; Lopes Zinn, Y. ; Albrecht, A. ; Kuikman, P.J. ; Jouquet, P. ; Demenois, J. ; Farrell, M. ; Fontaine, S. ; Soussana, J.F. ; Kuhnert, M. ; Milne, E. ; Taghizadeh-Toosi, A. ; Cerri, C.E.P. ; Corbeels, M. ; Cardinael, R. ; Alcántara Cervantes, V. ; Olesen, J.E. ; Batjes, N.H. ; Heuvelink, G.B.M. ; Maia, S.M.F. ; Keesstra, S.D. ; Claessens, L.F.G. ; Madari, B.E. ; Verchot, L. ; Nie, W. - 2019
EU - 16 p.
A summary presenting the challenges for soil carbon sequestration research, hypotheis to be further tested and key research (and innvation) products.
Spatio-temporal statistical methods for analysis of hydrological events and related hazards
Varouchakis, Emmanouil A. ; Hristopulos, Dionissios T. ; Heuvelink, Gerard B.M. ; Corzo Perez, Gerald A. - 2019
Spatial Statistics 34 (2019). - ISSN 2211-6753
Sampling design optimization for soil mapping with random forest
Wadoux, Alexandre M.J.C. ; Brus, Dick J. ; Heuvelink, Gerard B.M. - 2019
Geoderma 355 (2019). - ISSN 0016-7061
Conditioned Latin Hypercube - k-means - LUCAS - Optimal design - Pedometrics - Random forest - Spatial coverage - Spatial simulated annealing - Uncertainty assessment

Machine learning techniques are widely employed to generate digital soil maps. The map accuracy is partly determined by the number and spatial locations of the measurements used to calibrate the machine learning model. However, determining the optimal sampling design for mapping with machine learning techniques has not yet been considered in detail in digital soil mapping studies. In this paper, we investigate sampling design optimization for soil mapping with random forest. A design is optimized using spatial simulated annealing by minimizing the mean squared prediction error (MSE). We applied this approach to mapping soil organic carbon for a part of Europe using subsamples of the LUCAS dataset. The optimized subsamples are used as input for the random forest machine learning model, using a large set of readily available environmental data as covariates. We also predicted the same soil property using subsamples selected by simple random sampling, conditioned Latin Hypercube sampling (cLHS), spatial coverage sampling and feature space coverage sampling. Distributions of the estimated population MSEs are obtained through repeated random splitting of the LUCAS dataset, serving as the population of interest, into subsets used for validation, testing and selection of calibration samples, and repeated selection of calibration samples with the various sampling designs. The differences between the medians of the MSE distributions were tested for significance using the non-parametric Mann-Whitney test. The process was repeated for different sample sizes. We also analyzed the spread of the optimized designs in both geographic and feature space to reveal their characteristics. Results show that optimization of the sampling design by minimizing the MSE is worthwhile for small sample sizes. However, an important disadvantage of sampling design optimization using MSE is that it requires known values of the soil property at all locations and as a consequence is only feasible for subsampling an existing dataset. For larger sample sizes, the effect of using an MSE optimized design diminishes. In this case, we recommend to use a sample spread uniformly in the feature (i.e. covariate) space of the most important random forest covariates. The results also show that for our case study, cLHS sampling performs worse than the other sampling designs for mapping with random forest. We stress that comparison of sampling designs for calibration by splitting the data just once is very sensitive to the data split that one happens to use if the validation set is small.

Super-resolution land cover mapping based on the convolutional neural network
Jia, Yuanxin ; Ge, Yong ; Chen, Yuehong ; Li, Sanping ; Heuvelink, Gerard B.M. ; Ling, Feng - 2019
Remote Sensing 11 (2019)15. - ISSN 2072-4292
Convolutional neural network - Land cover - Remote sensing imagery - Super-resolution mapping

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.

Joint treatment of point measurement, sampling and neighborhood uncertainty in space-time rainfall mapping
Ehlers, L.B. ; Sonnenborg, T.O. ; Heuvelink, G.B.M. ; He, X. ; Refsgaard, J.C. - 2019
Journal of Hydrology 574 (2019). - ISSN 0022-1694 - p. 148 - 159.
Neighborhood uncertainty - Rain gauge - Rainfall uncertainty - Sequential Gaussian simulation - Spatial and temporal support effects

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 × 2 km spatial resolution for a catchment in Western Denmark (1055 km 2 ). 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.

Editorial for pedometrics 2017 special issue
Heuvelink, G.B.M. ; Brus, D.J. ; Rossiter, D.G. ; Shi, Z. - 2019
European Journal of Soil Science 70 (2019)1. - ISSN 1351-0754 - p. 25 - 26.
Burgess, T.M. & Webster, R. 1980. Optimal interpolation and isarithmic mapping of soil properties. I. The semi-variogram and punctual kriging. Journal of Soil Science, 31, 315–331. : Commentary on the impact of Burgess & Webster (1980a) by R.M. Lark, G.B.M. Heuvelink and T.F.A. Bishop
Lark, R.M. ; Heuvelink, G.B.M. ; Bishop, T.F.A. - 2019
European Journal of Soil Science 70 (2019)1. - ISSN 1351-0754 - p. 7 - 10.
Recent insights on uncertainties present in integrated catchment water quality modelling
Tscheikner-Gratl, Franz ; Bellos, Vasilis ; Schellart, Alma ; Moreno-Rodenas, Antonio ; Muthusamy, Manoranjan ; Langeveld, Jeroen ; Clemens, Francois ; Benedetti, Lorenzo ; Rico-Ramirez, Miguel Angel ; Carvalho, Rita Fernandes de; Breuer, Lutz ; Shucksmith, James ; Heuvelink, Gerard B.M. ; Tait, Simon - 2019
Water Research 150 (2019). - ISSN 0043-1354 - p. 368 - 379.
Complexity management - Integrated catchment modelling - Sub-models of integrated modelling - Uncertainty - Water quality

This paper aims to stimulate discussion based on the experiences derived from the QUICS project (Quantifying Uncertainty in Integrated Catchment Studies). First it briefly discusses the current state of knowledge on uncertainties in sub-models of integrated catchment models and the existing frameworks for analysing uncertainty. Furthermore, it compares the relative approaches of both building and calibrating fully integrated models or linking separate sub-models. It also discusses the implications of model linkage on overall uncertainty and how to define an acceptable level of model complexity. This discussion includes, whether we should shift our attention from uncertainties due to linkage, when using linked models, to uncertainties in model structure by necessary simplification or by using more parameters. This discussion attempts to address the question as to whether there is an increase in uncertainty by linking these models or if a compensation effect could take place and that overall uncertainty in key water quality parameters actually decreases. Finally, challenges in the application of uncertainty analysis in integrated catchment water quality modelling, as encountered in this project, are discussed and recommendations for future research areas are highlighted.

Sparse regression interaction models for spatial prediction of soil properties in 3D
Pejović, Milutin ; Nikolić, Mladen ; Heuvelink, Gerard B.M. ; Hengl, Tomislav ; Kilibarda, Milan ; Bajat, Branislav - 2018
Computers and Geosciences 118 (2018). - ISSN 0098-3004 - p. 1 - 13.
3D - Interactions - Lasso - Nested cross-validation - Soil organic carbon - Spatial prediction

An approach for using lasso (Least Absolute Shrinkage and Selection Operator) regression in creating sparse 3D models of soil properties for spatial prediction at multiple depths is presented. Modeling soil properties in 3D benefits from interactions of spatial predictors with soil depth and its polynomial expansion, which yields a large number of model variables (and corresponding model parameters). Lasso is able to perform variable selection, hence reducing the number of model parameters and making the model more easily interpretable. This also prevents overfitting, which makes the model more accurate. The presented approach was tested using four variable selection approaches – none, stepwise, lasso and hierarchical lasso, on four kinds of models – standard linear model, linear model with polynomial expansion of depth, linear model with interactions of covariates with depth and linear model with interactions of covariates with depth and its polynomial expansion. This framework was used to predict Soil Organic Carbon (SOC) in three contrasting study areas: Bor (Serbia), Edgeroi (Australia) and the Netherlands. Results show that lasso yields substantial improvements in accuracy over standard and stepwise regression — up to 50 % of total variance. It yields models which contain up to five times less nonzero parameters than the full models and that are usually more sparse than models obtained by stepwise regression, up to three times. Extension of the standard linear model by including interactions typically improves the accuracy of models produced by lasso, but is detrimental to standard and stepwise regression. Regarding computation time, it was demonstrated that lasso is several orders of magnitude more efficient than stepwise regression for models with tens or hundreds of variables (including interactions). Proper model evaluation is emphasized. Considering the fact that lasso requires meta-parameter tuning, standard cross-validation does not suffice for adequate model evaluation, hence a nested cross-validation was employed. The presented approach is implemented as publicly available sparsereg3D R package.

Deriving temporally continuous soil moisture estimations at fine resolution by downscaling remotely sensed product
Jin, Yan ; Ge, Yong ; Wang, Jianghao ; Heuvelink, Gerard B.M. - 2018
International Journal of applied Earth Observation and Geoinformation 68 (2018). - ISSN 1569-8432 - p. 8 - 19.
AMSR-E - Downscaling - Geographically weighted regression - Soil moisture - Temporal continuity - Tibetan plateau

Land surface soil moisture (SSM) has important roles in the energy balance of the land surface and in the water cycle. Downscaling of coarse-resolution SSM remote sensing products is an efficient way for producing fine-resolution data. However, the downscaling methods used most widely require full-coverage visible/infrared satellite data as ancillary information. These methods are restricted to cloud-free days, making them unsuitable for continuous monitoring. The purpose of this study is to overcome this limitation to obtain temporally continuous fine-resolution SSM estimations. The local spatial heterogeneities of SSM and multiscale ancillary variables were considered in the downscaling process both to solve the problem of the strong variability of SSM and to benefit from the fusion of ancillary information. The generation of continuous downscaled remote sensing data was achieved via two principal steps. For cloud-free days, a stepwise hybrid geostatistical downscaling approach, based on geographically weighted area-to-area regression kriging (GWATARK), was employed by combining multiscale ancillary variables with passive microwave remote sensing data. Then, the GWATARK-estimated SSM and China Soil Moisture Dataset from Microwave Data Assimilation SSM data were combined to estimate fine-resolution data for cloudy days. The developed methodology was validated by application to the 25-km resolution daily AMSR-E SSM product to produce continuous SSM estimations at 1-km resolution over the Tibetan Plateau. In comparison with ground-based observations, the downscaled estimations showed correlation (R ≥ 0.7) for both ascending and descending overpasses. The analysis indicated the high potential of the proposed approach for producing a temporally continuous SSM product at fine spatial resolution.

Spatial uncertainty propagation analysis with the spup R package
Sawicka, Kasia ; Heuvelink, Gerard B.M. ; Walvoort, Dennis J.J. - 2018
RFID Journal 10 (2018)2. - ISSN 2073-4859 - p. 180 - 199.

Many environmental and geographical models, such as those used in land degradation, agroecological and climate studies, make use of spatially distributed inputs that are known imperfectly. The R package spup provides functions for examining the uncertainty propagation from input data and model parameters onto model outputs via the environmental model. The functions include uncertainty model specification, stochastic simulation and propagation of uncertainty using Monte Carlo (MC) techniques. Uncertain variables are described by probability distributions. Both numerical and categorical data types are handled. The package also accommodates spatial auto-correlation within a variable and cross-correlation between variables. The MC realizations may be used as input to the environmental models written in or called from R. This article provides theoretical background and three worked examples that guide users through the application of spup.

SoilGrids: using big data solutions and machine learning algorithms for global soil mapping
Sousa, L.M. De; Heuvelink, G.B.M. ; Batjes, N.H. ; Kempen, B. - 2018
- 1 p.
Soil resources and element stocks in drylands to face global issues
Plaza, César ; Zaccone, Claudio ; Sawicka, Kasia ; Méndez, Ana M. ; Tarquis, Ana ; Gascó, Gabriel ; Heuvelink, Gerard B.M. ; Schuur, Edward A.G. ; Maestre, Fernando T. - 2018
Scientific Reports 8 (2018)1. - ISSN 2045-2322

Drylands (hyperarid, arid, semiarid, and dry subhumid ecosystems) cover almost half of Earth’s land surface and are highly vulnerable to environmental pressures. Here we provide an inventory of soil properties including carbon (C), nitrogen (N), and phosphorus (P) stocks within the current boundaries of drylands, aimed at serving as a benchmark in the face of future challenges including increased population, food security, desertification, and climate change. Aridity limits plant production and results in poorly developed soils, with coarse texture, low C:N and C:P, scarce organic matter, and high vulnerability to erosion. Dryland soils store 646 Pg of organic C to 2 m, the equivalent of 32% of the global soil organic C pool. The magnitude of the historic loss of C from dryland soils due to human land use and cover change and their typically low C:N and C:P suggest high potential to build up soil organic matter, but coarse soil textures may limit protection and stabilization processes. Restoring, preserving, and increasing soil organic matter in drylands may help slow down rising levels of atmospheric carbon dioxide by sequestering C, and is strongly needed to enhance food security and reduce the risk of land degradation and desertification.

Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables
Hengl, Tomislav ; Nussbaum, Madlene ; Wright, Marvin N. ; Heuvelink, Gerard B.M. ; Gräler, Benedikt - 2018
PeerJ 6 (2018). - ISSN 2167-8359
Geostatistics - Kriging - Pedometrics - Predictive modeling - R statistical computing - Random forest - Sampling - Spatial data - Spatiotemporal data

Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the crossvalidation residuals, indicates that the predictions are maybe biased, and this is suboptimal. This paper presents a random forest for spatial predictions framework (RFsp) where buffer distances from observation points are used as explanatory variables, thus incorporating geographical proximity effects into the prediction process. The RFsp framework is illustrated with examples that use textbook datasets and apply spatial and spatio-temporal prediction to numeric, binary, categorical, multivariate and spatiotemporal variables. Performance of the RFsp framework is compared with the state-of-the-art kriging techniques using fivefold cross-validation with refitting. The results show that RFsp can obtain equally accurate and unbiased predictions as different versions of kriging. Advantages of using RFsp over kriging are that it needs no rigid statistical assumptions about the distribution and stationarity of the target variable, it is more flexible towards incorporating, combining and extending covariates of different types, and it possibly yields more informative maps characterizing the prediction error. RFsp appears to be especially attractive for building multivariate spatial prediction models that can be used as knowledge engines'' in various geoscience fields. Some disadvantages of RFsp are the exponentially growing computational intensity with increase of calibration data and covariates and the high sensitivity of predictions to input data quality. The key to the success of the RFsp framework might be the training data quality-especially quality of spatial sampling (to minimize extrapolation problems and any type of bias in data), and quality of model validation (to ensure that accuracy is not effected by overfitting). For many data sets, especially those with lower number of points and covariates and close-to-linear relationships, model-based geostatistics can still lead to more accurate predictions than RFsp.

Bayesian Generalized Linear Geostatistical Modelling for mapping subsoil ripening
Steinbuch, L. ; Heuvelink, G.B.M. - 2018
Bayesian Generalized Linear Geostatistical Modelling for mapping subsoil ripening
Steinbuch, L. ; Heuvelink, G.B.M. - 2018
Check title to add to marked list
<< previous | next >>

Show 20 50 100 records per page

 
Please log in to use this service. Login as Wageningen University & Research user or guest user in upper right hand corner of this page.