Spatial disaggregation of complex Soil Map Units at the regional scale based on soil-landscape relationships

Digital soil mapping is becoming a powerful tool to increase the spatial detail of soil information over large areas, which is essential to address agronomic and environmental issues. When it exists, information about soil is often sparse or available at a coarser resolution than required. The spatial distribution of soil at the regional scale is usually represented as a set of polygons defining Soil Map Units (SMUs), each including several Soil Type Units (STUs), which are not spatially delineated but semantically described in a database. Delineation of STUs within SMUs, i.e. spatial disaggregation of SMU, should improve the precision of soil information derived from legacy and ancillary data. The aim of this study was to predict STUs by spatially disaggregating SMUs through a decision-tree approach that considered expert knowledge about soil-landscape relationships embedded in soil databases. In a 27,376 km2 study area in north-western France (Brittany), 434 SMUs were delineated at 1:250,000 scale, and 320 STUs, their relative area in the SMUs, and their geomorphological and geological contexts were described. A calibration dataset of points was established using stratified random sampling (n = 352,188). To retrieve soil-landscape relationships, expert rules for soil distribution defined by soil surveyors and based on topography, parent material and waterlogging index were considered in order to allocate an STU to 83% of the calibration dataset. The calibration dataset and covariates (i.e. pedological, geological and terrain attributes; land use; airborne gamma-ray spectrometry) were then used to build and extrapolate the decision tree using the C.5 algorithm in DSMART software. Several iterations were performed, providing a probability of occurrence of each possible STU within the study area. External validation was performed by comparing predictions of the disaggregation procedure to available soil maps at scales of 1:25,000 or 1:50,000 and observed profiles. Overall accuracies ranged from 41 to 72%, depending on the validation method (per pixel vs. 3 × 3 windows of pixels, per STU vs. STU grouped by semantic proximity (n = 204)). Introducing expert rules based on soil-landscape relationships to allocate STUs to calibration samples enabled production of a soil map with clear spatial structures, yielding expected spatial patterns of soil organisation. Future work notably concerns estimating soil properties at multiple depths deriving from STU predictions, according to the GlobalSoilMap project.

[1]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[2]  Budiman Minasny,et al.  Mapping continuous depth functions of soil carbon storage and available water capacity , 2009 .

[3]  N. Odgers,et al.  Large-area spatial disaggregation of a mosaic of conventional soil maps: evaluation over Western Australia , 2015 .

[4]  Thomas F. A. Bishop,et al.  Pragmatic models for the prediction and digital mapping of soil properties in eastern Australia , 2015 .

[5]  K. Beven,et al.  A physically based, variable contributing area model of basin hydrology , 1979 .

[6]  J. Wilford,et al.  Application of airborne gamma-ray spectrometry in soil/regolith mapping and applied geomorphology , 1997 .

[7]  A spatial disaggregation procedure for precipitation , 2002 .

[8]  Mike Grundy,et al.  Soil and landscape grid of Australia. , 2015 .

[9]  Gerard B. M. Heuvelink,et al.  Do more detailed environmental covariates deliver more accurate soil maps , 2015 .

[10]  Sabine Grunwald,et al.  Multi-criteria characterization of recent digital soil mapping and modeling approaches , 2009 .

[11]  Marine Lacoste,et al.  Regional mapping of soil parent material by machine learning based on point data , 2011 .

[12]  A-Xing Zhu,et al.  The effects of DEM resolution and neighborhood size on digital soil survey , 2006 .

[13]  Wei Sun,et al.  Disaggregating and harmonising soil map units through resampled classification trees , 2014 .

[14]  Soil Map Density and a Nation’s Wealth and Income , 2008 .

[15]  Alfred E. Hartemink,et al.  Linking soils to ecosystem services — A global review , 2016 .

[16]  Philippe Lagacherie,et al.  Integrating pedological knowledge into digital soil mapping , 2007 .

[17]  Philippe Lagacherie,et al.  Addressing Geographical Data Errors in a Classification Tree for Soil Unit Prediction , 1997, Int. J. Geogr. Inf. Sci..

[18]  Alex. B. McBratney,et al.  Some considerations on methods for spatially aggregating and disaggregating soil information , 1998, Nutrient Cycling in Agroecosystems.

[19]  Thomas C. Edwards,et al.  Machine learning for predicting soil classes in three semi-arid landscapes , 2015 .

[20]  T. Mayr,et al.  On the application of Bayesian Networks in Digital Soil Mapping , 2015 .

[21]  H. Jenny,et al.  Factors of Soil Formation , 1941 .

[22]  Alex B. McBratney,et al.  Modelling soil attribute depth functions with equal-area quadratic smoothing splines , 1999 .

[23]  Philippe Lagacherie,et al.  Evaluating Digital Soil Mapping approaches for mapping GlobalSoilMap soil properties from legacy data in Languedoc-Roussillon (France) , 2015 .

[24]  P. Scull,et al.  The application of classification tree analysis to soil type prediction in a desert landscape , 2005 .

[25]  Dominique Arrouays,et al.  National versus global modelling the 3D distribution of soil organic carbon in mainland France , 2016 .

[26]  Emilie Bourget,et al.  Esquisse cartographique des pédopaysages de Bretagne par télédétection , 2007 .

[27]  Marine Lacoste,et al.  Extrapolation at regional scale of local soil knowledge using boosted classification trees: A two-step approach , 2012 .

[28]  Dominique Arrouays,et al.  Optimizing pedotransfer functions for estimating soil bulk density using boosted regression trees. , 2009 .

[29]  B. Schröder,et al.  Spatial disaggregation of complex soil map units: A decision-tree based approach in Bavarian forest soils , 2012 .

[30]  David Clifford,et al.  The Australian three-dimensional soil grid: Australia’s contribution to the GlobalSoilMap project , 2015 .

[31]  Reamonn Fealy,et al.  Are fine resolution digital elevation models always the best choice in digital soil mapping , 2013 .

[32]  Chris Moran,et al.  Disaggregation of polygons of surficial geology and soil maps using spatial modelling and legacy data , 2001 .

[33]  Z. Libohova,et al.  Harmonization of legacy soil maps in North America: Status, trends and implications for digital soil mapping efforts , 2012 .

[34]  Travis W. Nauman,et al.  Semi-automated disaggregation of conventional soil maps using knowledge driven data mining and classification trees , 2014 .

[35]  P.F.M. van Gaans,et al.  Continuous classification in soil survey: spatial correlation, confusion and boundaries , 1997 .

[36]  Christian Walter,et al.  Mapping waterlogging of soils using digital terrain models , 1995 .

[37]  B. Minasny,et al.  Digital Soil Map of the World , 2009, Science.

[38]  Wei Sun,et al.  Dsmart: An algorithm to spatially disaggregate soil map units , 2014 .

[39]  Philippe Lagacherie,et al.  GlobalSoilMap: Toward a Fine-Resolution Global Grid of Soil Properties , 2014 .

[40]  Budiman Minasny,et al.  On digital soil mapping , 2003 .

[41]  Jon Hempel,et al.  Challenges to Digital Soil Mapping , 2008 .

[42]  Julien Boé,et al.  Statistical and dynamical downscaling of the Seine basin climate for hydro‐meteorological studies , 2007 .

[43]  Margaret G. Schmidt,et al.  Predictive soil parent material mapping at a regional-scale: a Random Forest approach. , 2014 .