Articles | Volume 8, issue 2
https://doi.org/10.5194/soil-8-541-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/soil-8-541-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
On the benefits of clustering approaches in digital soil mapping: an application example concerning soil texture regionalization
Max Planck Institute for Meteorology, Hamburg, Germany
Department Soil System Science, Helmholtz Centre for Environmental Research – UFZ, Halle (Saale), Germany
Mareike Ließ
Department Soil System Science, Helmholtz Centre for Environmental Research – UFZ, Halle (Saale), Germany
Related authors
Peter Pfleiderer, Anna Merrifield, István Dunkl, Homer Durand, Enora Cariou, Julien Cattiaux, and Sebastian Sippel
EGUsphere, https://doi.org/10.5194/egusphere-2025-2397, https://doi.org/10.5194/egusphere-2025-2397, 2025
Short summary
Short summary
Due to changes in atmospheric circulation some regions are warming quicker than others. Statistical methods are used to estimate how much of the local summer temperature trends are due to circulation changes. We evaluate these methods by comparing their estimates to special simulations representing only temperature changes related to circulation changes. By applying the methods to observations of 1979–2023 we find that half of the warming over parts of Europe is related to circulation changes.
István Dunkl, Ana Bastos, and Tatiana Ilyina
Earth Syst. Dynam., 16, 151–167, https://doi.org/10.5194/esd-16-151-2025, https://doi.org/10.5194/esd-16-151-2025, 2025
Short summary
Short summary
While the El Niño–Southern Oscillation, a climate mode, has a similar impact on CO2 growth rates across Earth system models, there is significant uncertainty in the processes behind this relationship. We found a compensatory effect that masks differences in the sensitivity of carbon fluxes to climate anomalies and observed that the carbon fluxes contributing to global CO2 anomalies originate from different regions and are caused by different drivers.
István Dunkl, Nicole Lovenduski, Alessio Collalti, Vivek K. Arora, Tatiana Ilyina, and Victor Brovkin
Biogeosciences, 20, 3523–3538, https://doi.org/10.5194/bg-20-3523-2023, https://doi.org/10.5194/bg-20-3523-2023, 2023
Short summary
Short summary
Despite differences in the reproduction of gross primary productivity (GPP) by Earth system models (ESMs), ESMs have similar predictability of the global carbon cycle. We found that, although GPP variability originates from different regions and is driven by different climatic variables across the ESMs, the ESMs rely on the same mechanisms to predict their own GPP. This shows that the predictability of the carbon cycle is limited by our understanding of variability rather than predictability.
István Dunkl, Aaron Spring, Pierre Friedlingstein, and Victor Brovkin
Earth Syst. Dynam., 12, 1413–1426, https://doi.org/10.5194/esd-12-1413-2021, https://doi.org/10.5194/esd-12-1413-2021, 2021
Short summary
Short summary
The variability in atmospheric CO2 is largely controlled by terrestrial carbon fluxes. These land–atmosphere fluxes are predictable for around 2 years, but the mechanisms providing the predictability are not well understood. By decomposing the predictability of carbon fluxes into individual contributors we were able to explain the spatial and seasonal patterns and the interannual variability of CO2 flux predictability.
Aaron Spring, István Dunkl, Hongmei Li, Victor Brovkin, and Tatiana Ilyina
Earth Syst. Dynam., 12, 1139–1167, https://doi.org/10.5194/esd-12-1139-2021, https://doi.org/10.5194/esd-12-1139-2021, 2021
Short summary
Short summary
Numerical carbon cycle prediction models usually do not start from observed carbon states due to sparse observations. Instead, only physical climate is reconstructed, assuming that the carbon cycle follows indirectly. Here, we test in an idealized framework how well this indirect and direct reconstruction with perfect observations works. We find that indirect reconstruction works quite well and that improvements from the direct method are limited, strengthening the current indirect use.
Peter Pfleiderer, Anna Merrifield, István Dunkl, Homer Durand, Enora Cariou, Julien Cattiaux, and Sebastian Sippel
EGUsphere, https://doi.org/10.5194/egusphere-2025-2397, https://doi.org/10.5194/egusphere-2025-2397, 2025
Short summary
Short summary
Due to changes in atmospheric circulation some regions are warming quicker than others. Statistical methods are used to estimate how much of the local summer temperature trends are due to circulation changes. We evaluate these methods by comparing their estimates to special simulations representing only temperature changes related to circulation changes. By applying the methods to observations of 1979–2023 we find that half of the warming over parts of Europe is related to circulation changes.
István Dunkl, Ana Bastos, and Tatiana Ilyina
Earth Syst. Dynam., 16, 151–167, https://doi.org/10.5194/esd-16-151-2025, https://doi.org/10.5194/esd-16-151-2025, 2025
Short summary
Short summary
While the El Niño–Southern Oscillation, a climate mode, has a similar impact on CO2 growth rates across Earth system models, there is significant uncertainty in the processes behind this relationship. We found a compensatory effect that masks differences in the sensitivity of carbon fluxes to climate anomalies and observed that the carbon fluxes contributing to global CO2 anomalies originate from different regions and are caused by different drivers.
Mareike Ließ and Ali Sakhaee
EGUsphere, https://doi.org/10.5194/egusphere-2023-2386, https://doi.org/10.5194/egusphere-2023-2386, 2023
Preprint archived
Short summary
Short summary
The CNN is a powerful algorithm to generate three-dimensional multivariate data products. Its high potential is demonstrated by generating a data product for the agricultural soil landscape of Germany. It comprises soil particle size fractions in a vertical resolution of one centimeter. Many soil functions and processes are controlled by the soil particle size distribution. The developed data product is of particular importance to model agricultural processes.
István Dunkl, Nicole Lovenduski, Alessio Collalti, Vivek K. Arora, Tatiana Ilyina, and Victor Brovkin
Biogeosciences, 20, 3523–3538, https://doi.org/10.5194/bg-20-3523-2023, https://doi.org/10.5194/bg-20-3523-2023, 2023
Short summary
Short summary
Despite differences in the reproduction of gross primary productivity (GPP) by Earth system models (ESMs), ESMs have similar predictability of the global carbon cycle. We found that, although GPP variability originates from different regions and is driven by different climatic variables across the ESMs, the ESMs rely on the same mechanisms to predict their own GPP. This shows that the predictability of the carbon cycle is limited by our understanding of variability rather than predictability.
Ali Sakhaee, Anika Gebauer, Mareike Ließ, and Axel Don
SOIL, 8, 587–604, https://doi.org/10.5194/soil-8-587-2022, https://doi.org/10.5194/soil-8-587-2022, 2022
Short summary
Short summary
As soil carbon has become a key component of climate-smart agriculture, the demand for high-resolution maps has increased drastically. Meanwhile, machine learning algorithms are becoming more widely used and are opening up new solutions in soil mapping. This paper shows which algorithms perform best, how soil inventory data can be most efficiently used for digital soil mapping, and the different available options and methods to derive high-resolution soil carbon data at the large regional scale.
Javier Reyes and Mareike Ließ
EGUsphere, https://doi.org/10.5194/egusphere-2022-273, https://doi.org/10.5194/egusphere-2022-273, 2022
Preprint archived
Short summary
Short summary
The use of soil Vis-NIR spectroscopy is a promising research field in the context of SOC monitoring. Predictive models were built on behalf of spectral laboratory and field measurements and thoroughly interpreted concerning spectral wavelength importance. The analysis disclosed the challenge of using soil spectroscopy for SOC monitoring. Shifts in wavelength importance were observed between spectrometers. Correction of spectral field data improved the predictive performance of the models.
István Dunkl, Aaron Spring, Pierre Friedlingstein, and Victor Brovkin
Earth Syst. Dynam., 12, 1413–1426, https://doi.org/10.5194/esd-12-1413-2021, https://doi.org/10.5194/esd-12-1413-2021, 2021
Short summary
Short summary
The variability in atmospheric CO2 is largely controlled by terrestrial carbon fluxes. These land–atmosphere fluxes are predictable for around 2 years, but the mechanisms providing the predictability are not well understood. By decomposing the predictability of carbon fluxes into individual contributors we were able to explain the spatial and seasonal patterns and the interannual variability of CO2 flux predictability.
Aaron Spring, István Dunkl, Hongmei Li, Victor Brovkin, and Tatiana Ilyina
Earth Syst. Dynam., 12, 1139–1167, https://doi.org/10.5194/esd-12-1139-2021, https://doi.org/10.5194/esd-12-1139-2021, 2021
Short summary
Short summary
Numerical carbon cycle prediction models usually do not start from observed carbon states due to sparse observations. Instead, only physical climate is reconstructed, assuming that the carbon cycle follows indirectly. Here, we test in an idealized framework how well this indirect and direct reconstruction with perfect observations works. We find that indirect reconstruction works quite well and that improvements from the direct method are limited, strengthening the current indirect use.
Cited articles
Adhikari, K., Kheir, R. B., Greve, M. B., Bøcher, P. K., Malone, B. P.,
Minasny, B., McBratney, A. B., and Greve, M. H.: High-resolution 3-D mapping
of soil texture in Denmark, Soil Sci. Soc. Am. J., 77,
860–876, https://doi.org/10.2136/sssaj2012.0275, 2013. a, b, c
Behrens, T., Zhu, A.-X., Schmidt, K., and Scholten, T.: Multi-scale digital
terrain analysis and feature selection for digital soil mapping, Geoderma,
155, 175–185, https://doi.org/10.1016/j.geoderma.2009.07.010, 2010. a, b
Behrens, T., Schmidt, K., Viscarra Rossel, R. A., Gries, P., Scholten, T., and
MacMillan, R. A.: Spatial modelling with Euclidean distance fields and
machine learning, Eur. J. Soil Sci., 69, 757–770, https://doi.org/10.1111/ejss.12687, 2018. a
Benjamini, Y. and Yekutieli, D.: The control of the false discovery rate in
multiple testing under dependency, Ann. Stat., 29, 1165–1188,
2001. a
Beven, K. J. and Kirkby, M. J.: A physically based, variable contributing area
model of basin hydrology, Hydrolog. Sci. J., 24, 43–69, https://doi.org/10.1080/02626667909491834, 1979. a
BGR: Geologische Karte der Bundesrepublik Deutschland 1 : 1.000.000 (GK1000
v4.0), Hannover, 2006. a
BGR: Bodenübersichtskarte 1 : 200.000 (BÜK200 v1.5), Hannover, 2012. a
BKG: GeoBasis-DE, 2012. a
Blanco, C. M. G., Gomez, V. M. B., Crespo, P., and Ließ, M.: Spatial
prediction of soil water retention in a Páramo landscape: Methodological
insight into machine learning using random forest, Geoderma, 316, 100–114, https://doi.org/10.1016/j.geoderma.2017.12.002,
2018. a
Blume, H.-P., Brümmer, G. W., Horn, R., Kandeler, E., Kögel-Knabner,
I., Kretzschmar, R., Stahr, K., and Wilke, B.-M.: Scheffer/schachtschabel:
Lehrbuch der bodenkunde, Springer-Verlag, https://doi.org/10.1007/978-3-662-49960-3, 2016. a
Bock, M., Böhner, J., Conrad, O., Köthe, R., and Ringeler, A.: XV.
Methods for creating Functional Soil Databases and applying Digital Soil
Mapping with SAGA GIS, JRC Scientific and technical Reports, Office for
Official Publications of the European Communities, Luxemburg, 2007. a
Böhner, J. and Antonić, O.: Land-surface parameters specific to
topo-climatology, Dev. Soil Sci., 33, 195–226, https://doi.org/10.1016/S0166-2481(08)00008-1, 2009. a, b
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001. a
Bulmer, C., Schmidt, M., Heung, B., Scarpone, C., Zhang, J., Filatow, D.,
Finvers, M., Berch, S., and Smith, S.: Improved soil mapping in British
Columbia, Canada, with legacy soil data and random forest, in: Digital Soil
Mapping Across Paradigms, Scales and Boundaries, edited by: Zhang, G.-L., Brus, D., Liu, F., Song, X.-D., and Lagacherie, P., 291–303, Springer, https://doi.org/10.1007/978-981-10-0415-5_24,
2016. a
Büttner, G., Feranec, J., Jaffrain, G., Mari, L., Maucha, G., and Soukup,
T.: The CORINE land cover 2000 project, EARSeL eProceedings, 3, 331–346,
2004. a
Carré, F., McBratney, A. B., and Minasny, B.: Estimation and potential
improvement of the quality of legacy soil samples for digital soil mapping,
Geoderma, 141, 1–14, https://doi.org/10.1016/j.geoderma.2007.01.018, 2007. a
Chandrashekar, G. and Sahin, F.: A survey on feature selection methods,
Comput. Electr. Eng., 40, 16–28, 2014. a
Charrad, M., Ghazzali, N., Boiteau, V., Niknafs, A., and Charrad, M. M.:
Package “NbClust”, J. Stat. Softw., 61, 1–36, https://doi.org/10.18637/jss.v061.i06, 2014. a
De Bruin, S. and Stein, A.: Soil-landscape modelling using fuzzy c-means
clustering of attribute data derived from a digital elevation model (DEM),
Geoderma, 83, 17–33, https://doi.org/10.1016/S0016-7061(97)00143-2, 1998. a
de Carvalho Junior, W., Lagacherie, P., da Silva Chagas, C., Calderano Filho,
B., and Bhering, S. B.: A regional-scale assessment of digital mapping of
soil attributes in a tropical hillslope environment, Geoderma, 232, 479–486, https://doi.org/10.1016/j.geoderma.2014.06.007,
2014. a, b
Deutscher Wetterdienst: Vieljährige Mittelwerte,
https://www.dwd.de/DE/leistungen/klimadatendeutschland (last access: 22 August 2022), 2020. a
Dunkl, I.: Data set: On the benefits of clustering approaches in digital soil mapping: an application example concerning soil texture regionalization, OSF Home [data set], https://doi.org/10.17605/OSF.IO/GMJTQ, 2022. a
Evans, J. S., Murphy, M. A., Holden, Z. A., and Cushman, S. A.: Modeling
species distribution and change using random forest, in: Predictive species
and habitat modeling in landscape ecology, edited by: Drew, C. A., Wiersma, Y. F., and Huettmann, F., 139–159, Springer, https://doi.org/10.1007/978-1-4419-7390-0_8, 2011. a
Friedrich, K.: Digitale Reliefgliederungsverfahren zur Ableitung bodenkundlich
relevanter Flächeneinheiten, Fachbereich Geowiss. d.
Johann-Wolfgang-Goethe-Univ., ISBN 9783922540557, 1996. a
Gobin, A., Campling, P., and Feyen, J.: Soil-landscape modelling to quantify
spatial variability of soil texture, Phys. Chem. Earth Pt.
B, 26, 41–45, https://doi.org/10.1016/S1464-1909(01)85012-7, 2001. a, b
Grunwald, S.: Multi-criteria characterization of recent digital soil mapping
and modeling approaches, Geoderma, 152, 195–207, https://doi.org/10.1016/j.geoderma.2009.06.003, 2009. a
Grunwald, S., Thompson, J., and Boettinger, J.: Digital soil mapping and
modeling at continental scales: Finding solutions for global issues, Soil Sci. Soc. Am. J., 75, 1201–1213, https://doi.org/10.2136/sssaj2011.0025, 2011. a, b
Hamza, M. and Larocque, D.: An empirical comparison of ensemble methods based
on classification trees, J. Stat. Comput. Sim.,
75, 629–643, https://doi.org/10.1023/A:1009841519580, 2005. a
He, H. and Garcia, E. A.: Learning from imbalanced data, IEEE T.
Knowl. Data En., 21, 1263–1284, https://doi.org/10.1109/TKDE.2008.239, 2008. a, b
Hengl, T., Nussbaum, M., Wright, M. N., Heuvelink, G. B., and Gräler, B.:
Random forest as a generic framework for predictive modeling of spatial and
spatio-temporal variables, PeerJ, 6, e5518, https://doi.org/10.7717/peerj.5518, 2018. a
Heung, B., Bulmer, C. E., and Schmidt, M. G.: Predictive soil parent material
mapping at a regional-scale: A Random Forest approach, Geoderma, 214,
141–154, https://doi.org/10.1016/j.geoderma.2013.09.016, 2014. a, b
Heung, B., Ho, H. C., Zhang, J., Knudby, A., Bulmer, C. E., and Schmidt, M. G.:
An overview and comparison of machine-learning techniques for classification
purposes in digital soil mapping, Geoderma, 265, 62–77, https://doi.org/10.1016/j.geoderma.2015.11.014, 2016. a, b
Kalambukattu, J. G., Kumar, S., and Raj, R. A.: Digital soil mapping in a
Himalayan watershed using remote sensing and terrain parameters employing
artificial neural network model, Environ. Earth Sci., 77, 203, https://doi.org/10.1007/s12665-018-7367-9, 2018. a
LAGB: Auszug aus der Bodenprofildatenbank (SABOP) mit Stand vom
12.05.2016, Landesamt für Geologie und Bergwesen Sachsen-Anhalt, 2018. a
Lê, S., Josse, J., and Husson, F.: FactoMineR: an R package for
multivariate analysis, J. Stat. Softw., 25, 1–18, https://doi.org/10.18637/jss.v025.i01, 2008. a
Ließ, M.: Sampling for regression-based digital soil mapping: closing the
gap between statistical desires and operational applicability, Spat.
Stat., 13, 106–122, https://doi.org/10.1016/j.spasta.2015.06.002, 2015. a
Ließ, M.: At the interface between domain knowledge and statistical
sampling theory: Conditional distribution based sampling for environmental
survey (CODIBAS), Catena, 187, 104423, https://doi.org/10.1016/j.catena.2019.104423, 2020. a, b, c
Linting, M., Meulman, J. J., Groenen, P. J., and van der Kooij, A. J.:
Nonlinear Principal Components Analysis: Introduction and Application,
Psychol. Methods, 12, 336–358, https://doi.org/10.1037/1082-989X.12.3.336, 2007. a
MacMillan, R., Jones, R. K., and McNabb, D. H.: Defining a hierarchy of
spatial entities for environmental analysis and modeling using digital
elevation models (DEMs), Computers, Environment and Urban Systems, 28,
175–200, https://doi.org/10.1016/S0198-9715(03)00019-X, 2004. a
Marchi, L. and Dalla Fontana, G.: GIS morphometric indicators for the analysis
of sediment dynamics in mountain basins, Environ. Geol., 48,
218–228, https://doi.org/10.1007/s00254-005-1292-4, 2005. a
McBratney, A. B., Odeh, I. O., Bishop, T. F., Dunbar, M. S., and Shatar, T. M.:
An overview of pedometric techniques for use in soil survey, Geoderma, 97,
293–327, https://doi.org/10.1016/S0016-7061(00)00043-4, 2000. a
McBratney, A. B., Santos, M. M., and Minasny, B.: On digital soil mapping,
Geoderma, 117, 3–52, https://doi.org/10.1016/S0016-7061(03)00223-4, 2003. a, b
Minasny, B. and McBratney, A. B.: Digital soil mapping: A brief history and
some lessons, Geoderma, 264, 301–311, https://doi.org/10.1016/j.geoderma.2015.07.017, 2016. a
Møller, A. B., Beucher, A. M., Pouladi, N., and Greve, M. H.: Oblique geographic coordinates as covariates for digital soil mapping, SOIL, 6, 269–289, https://doi.org/10.5194/soil-6-269-2020, 2020. a
Moore, I. D., Grayson, R., and Ladson, A.: Digital terrain modelling: a review
of hydrological, geomorphological, and biological applications, Hydrol.
Process., 5, 3–30, https://doi.org/10.1002/hyp.3360050103, 1991. a, b
Moore, I. D., Gessler, P., Nielsen, G., and Peterson, G.: Soil attribute
prediction using terrain analysis, Soil Sci. Soc. Am. J.,
57, 443–452, https://doi.org/10.2136/sssaj1993.03615995005700020026x, 1993. a, b
Moran, C. J. and Bui, E. N.: Spatial data mining for enhanced soil map
modelling, Int. J. Geogr. Inf. Sci., 16,
533–549, https://doi.org/10.1080/13658810210138715, 2002. a, b
Nussbaum, M., Spiess, K., Baltensweiler, A., Grob, U., Keller, A., Greiner, L., Schaepman, M. E., and Papritz, A.: Evaluation of digital soil mapping approaches with large sets of environmental covariates, SOIL, 4, 1–22, https://doi.org/10.5194/soil-4-1-2018, 2018. a
OpenStreetMap contributors: Planet dump,
https://planet.osm.org and
https://www.openstreetmap.org (last access: 20 February 2019), 2018. a
Padarian, J., Minasny, B., and McBratney, A. B.: Machine learning and soil sciences: a review aided by machine learning tools, SOIL, 6, 35–52, https://doi.org/10.5194/soil-6-35-2020, 2020. a
Park, S. and Vlek, P.: Environmental correlation of three-dimensional soil
spatial variability: a comparison of three adaptive techniques, Geoderma,
109, 117–140, https://doi.org/10.1016/S0016-7061(02)00146-5, 2002. a, b
Peel, M. C., Finlayson, B. L., and McMahon, T. A.: Updated world map of the Köppen-Geiger climate classification, Hydrol. Earth Syst. Sci., 11, 1633–1644, https://doi.org/10.5194/hess-11-1633-2007, 2007. a
R Core Team: R: A Language and Environment for Statistical Computing, R
Foundation for Statistical Computing, Vienna, Austria,
http://www.R-project.org/ (last access: 18 August 2022), 2018. a
Rossiter, D. G.: Past, present & future of information technology in
pedometrics, Geoderma, 324, 131–137, https://doi.org/10.1016/j.geoderma.2018.03.009, 2018. a
Schmidt, K., Behrens, T., and Scholten, T.: Instance selection and
classification tree analysis for large spatial datasets in digital soil
mapping, Geoderma, 146, 138–146, https://doi.org/10.1016/j.geoderma.2008.05.010,
2008. a
Schubert, E. and Zimek, A.: ELKI: A large open-source library for data
analysis-ELKI Release 0.7.5 “Heidelberg”, arXiv [preprint], https://doi.org/10.48550/arXiv.1902.03616,
2019. a
Scull, P., Franklin, J., Chadwick, O., and McArthur, D.: Predictive soil
mapping: a review, Prog. Phys. Geogr., 27, 171–197, https://doi.org/10.1191/0309133303pp366ra, 2003. a, b
Sharififar, A., Sarmadian, F., Malone, B. P., and Minasny, B.: Addressing the
issue of digital mapping of soil classes with imbalanced class observations,
Geoderma, 350, 84–92, https://doi.org/10.1016/j.geoderma.2019.05.016, 2019. a, b
Subburayalu, S. K. and Slater, B. K.: Soil series mapping by knowledge
discovery from an Ohio county soil map, Soil Sci. Soc. Am. J., 77, 1254–1268, https://doi.org/10.2136/sssaj2012.0321, 2013. a
Taghizadeh-Mehrjardi, R., Schmidt, K., Eftekhari, K., Behrens, T., Jamshidi,
M., Davatgar, N., Toomanian, N., and Scholten, T.: Synthetic resampling
strategies and machine learning for digital soil mapping in Iran, Eur.
J. Soil Sci., 71, 352–368, https://doi.org/10.1111/ejss.12893, 2019. a
TGL: TGL 24300 Aufnahme landwirtschaftlich genutzter Standorte.,
Fachbereichsstandards, Akademie der Landwirtschaftswissenschaften der DDR,
Berlin, 1985. a
Vaysse, K. and Lagacherie, P.: Evaluating digital soil mapping approaches for
mapping GlobalSoilMap soil properties from legacy data in
Languedoc-Roussillon (France), Geoderma Regional, 4, 20–30, https://doi.org/10.1016/j.geodrs.2014.11.003, 2015. a, b
Vaysse, K. and Lagacherie, P.: Using quantile regression forest to estimate
uncertainty of digital soil mapping products, Geoderma, 291, 55–64, https://doi.org/10.1016/j.geoderma.2016.12.017, 2017. a, b
Wang, L. and Liu, H.: An efficient method for identifying and filling surface
depressions in digital elevation models for hydrologic analysis and
modelling, Int. J. Geogr. Inf. Sci., 20,
193–213, https://doi.org/10.1080/13658810500433453, 2006. a
Were, K., Bui, D. T., Øystein B. Dick, and Singh, B. R.: A comparative
assessment of support vector regression, artificial neural networks, and
random forests for predicting and mapping soil organic carbon stocks across
an Afromontane landscape, Ecol. Indic., 52, 394–403,
https://doi.org/10.1016/j.ecolind.2014.12.028, 2015. a
Zacharias, S., Bogena, H., Samaniego, L., Mauder, M., Fuß, R., Pütz,
T., Frenzel, M., Schwank, M., Baessler, C., Butterbach-Bahl, K., Bens, O., Borg, E., Brauer, A., Dietrich, P., Hajnsek, I., Helle, G., Kiese, R., Kunstmann, H., Klotz, S., Munch, J. C., Papen, H., Priesack, E., Schmid, H. P., Steinbrecher, R., Rosenbaum, U., Teutsch, G., and Vereecken, H.: A
network of terrestrial environmental observatories in Germany, Vadose Zone
J., 10, 955–973, https://doi.org/10.2136/vzj2010.0139, 2011. a
Zevenbergen, L. W. and Thorne, C. R.: Quantitative analysis of land surface
topography, Earth Surf. Proc. Land., 12, 47–56, https://doi.org/10.1002/esp.3290120107, 1987. a
Zhao, Z., Chow, T. L., Rees, H. W., Yang, Q., Xing, Z., and Meng, F.-R.:
Predict soil texture distributions using an artificial neural network model,
Comput. Electron. Agr., 65, 36–48, https://doi.org/10.1016/j.compag.2008.07.008, 2009. a
Zhou, Y., Hartemink, A. E., Shi, Z., Liang, Z., and Lu, Y.: Land use and
climate change effects on soil organic carbon in North and Northeast China,
Sci. Total Environ., 647, 1230–1238, https://doi.org/10.1016/j.scitotenv.2018.08.016, 2019. a
Short summary
Digital soil mapping (DSM) allows us to regionalize soil properties by relating them to environmental covariates with the help of an empirical model. Legacy soil data provide a valuable basis to generate high-resolution soil maps with DSM. We studied the usefulness of data-clustering methods to tackle potential sampling bias in legacy soil data while applying DSM for soil texture regionalization. Clustering has proved to be useful in various steps of the DSM process.
Digital soil mapping (DSM) allows us to regionalize soil properties by relating them to...