On the application of Bayesian Networks in Digital Soil Mapping

Abstract Two corresponding issues concerning Digital Soil Mapping are the demand for up-to-date, fine resolution soil data and the need to determine soil–landscape relationships. In this study, we propose a Bayesian Network framework as a suitable modelling approach to fulfil these requirements. Bayesian Networks are graphical probabilistic models in which predictions are obtained using prior probabilities derived from either measured data or expert opinion. They represent cause and effect relationships through connections in a network system. The advantage of the Bayesian Networks approach is that the models are easy to interpret and the uncertainty inherent in the relationships between variables can be expressed in terms of probability. In this study we will define the fundamentals of a Bayesian Network and the probability theory that underpins predictions. Then, using case studies, we demonstrate how they can be applied to predict soil properties (bulk density) and soil taxonomic class (associations).

[1]  Karl-Heinz Feger,et al.  Estimation of spatially distributed soil information: dealing with data shortages in the Western Bug Basin, Ukraine , 2012, Environmental Earth Sciences.

[2]  T. Mayr,et al.  Two Methods for Using Legacy Data in Digital Soil Mapping , 2010 .

[3]  A. Zhu,et al.  Entering the digital world (Pedometrics 2009) , 2012 .

[4]  Bronwyn Price,et al.  Using a Bayesian belief network to predict suitable habitat of an endangered mammal – The Julia Creek dunnart (Sminthopsis douglasi) , 2007 .

[5]  J. M. Bigham,et al.  Predicting bulk density of Ohio Soils from Morphology, Genetic Principles, and Laboratory Characterization Data , 2001 .

[6]  Stuart Green,et al.  Teagasc-EPA Soils and Subsoils mapping project: Final report V.1 , 2009 .

[7]  Ron Corstanje,et al.  Modelling soil bulk density at the landscape scale and its contributions to C stock uncertainty , 2012 .

[8]  L. Montanarella,et al.  Estimating forest soil bulk density using boosted regression modelling , 2010 .

[9]  V. I. Stewart,et al.  QUANTITATIVE PEDOLOGICAL STUDIES ON SOILS DERIVED FROM SILURIAN MUDSTONES: II. THE RELATIONSHIP BETWEEN STONE CONTENT AND THE APPARENT DENSITY OF THE FINE EARTH , 1970 .

[10]  Robert J. Lilieholm,et al.  Using Bayesian belief networks to identify potential compatibilities and conflicts between development and landscape conservation , 2011 .

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

[12]  R. J. Pike,et al.  Automated classifications of topography from DEMs by an unsupervised nested-means algorithm and a three-part geometric signature , 2007 .

[13]  Henry Tirri,et al.  B-Course: A Web-Based Tool for Bayesian and Causal Data Analysis , 2002, Int. J. Artif. Intell. Tools.

[14]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[15]  Wales,et al.  Soil classification for England and Wales : (higher categories) , 1980 .

[16]  Budiman Minasny,et al.  Building and testing conceptual and empirical models for predicting soil bulk density , 2007 .

[17]  Sabine Grunwald,et al.  Inferences from fluctuations in the local variogram about the assumption of stationarity in the variance , 2008 .

[18]  A. McBratney,et al.  A soil science renaissance , 2008 .

[19]  大西 仁,et al.  Pearl, J. (1988, second printing 1991). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan-Kaufmann. , 1994 .

[20]  Robert J. Hickey,et al.  Knowledge Based Soil Attribute Mapping In GIS: The Expector Method , 2002, Trans. GIS.

[21]  M. Degroot.  A Bayesian view of assessing uncertainty and comparing expert opinion , 1988 .

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

[23]  Laurence Smith,et al.  The role of expert opinion in environmental modelling , 2012, Environ. Model. Softw..

[24]  H. Elsenbeer,et al.  Soil organic carbon concentrations and stocks on Barro Colorado Island — Digital soil mapping using Random Forests analysis , 2008 .

[25]  Ron Kohavi,et al.  Supervised and Unsupervised Discretization of Continuous Features , 1995, ICML.

[26]  B. Marcot,et al.  Guidelines for developing and updating Bayesian belief networks applied to ecological modeling and conservation , 2006 .

[27]  Concha Bielza,et al.  Comparison of Bayesian networks and artificial neural networks for quality detection in a machining process , 2009, Expert Syst. Appl..

[28]  Elisabeth N. Bui,et al.  Extracting soil-landscape rules from previous soil surveys , 1999 .

[29]  Prakash P. Shenoy,et al.  A causal mapping approach to constructing Bayesian networks , 2004, Decis. Support Syst..

[30]  Rafael Rumí,et al.  Bayesian networks in environmental modelling , 2011, Environ. Model. Softw..

[31]  Eugene Charniak,et al.  Bayesian Networks without Tears , 1991, AI Mag..

[32]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[33]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[34]  Peter Finke,et al.  On digital soil assessment with models and the Pedometrics agenda , 2012 .

[35]  A. McBratney,et al.  Application of fuzzy sets in soil science: fuzzy logic, fuzzy measurements and fuzzy decisions , 1997 .

[36]  K. R. Hayes,et al.  How believable is your BBN , 2009 .

[37]  Liangxiao Jiang,et al.  Learning Tree Augmented Naive Bayes for Ranking , 2005, DASFAA.

[38]  W. Rawls.  Estimating soil bulk density from particle size analysis and organic matter content. , 1983 .

[39]  Alexander J. Hartemink,et al.  Learning Non-Stationary Dynamic Bayesian Networks , 2010, J. Mach. Learn. Res..

[40]  M. Aitkenhead,et al.  Predicting land cover using GIS, Bayesian and evolutionary algorithm methods. , 2009, Journal of environmental management.

[41]  Fan-Rui Meng,et al.  Using artificial neural network models to produce soil organic carbon content distribution maps across landscapes , 2010 .

[42]  Serena H. Chen,et al.  Good practice in Bayesian network modelling , 2012, Environ. Model. Softw..

[43]  Stephen H. Hallett,et al.  Environmental Information Systems Developments for Planning Sustainable Land Use , 1996, Int. J. Geogr. Inf. Sci..

[44]  Anthony J. Jakeman,et al.  Ten iterative steps in development and evaluation of environmental models , 2006, Environ. Model. Softw..

[45]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[46]  Markus Reichstein,et al.  Modeling the vertical soil organic matter profile using Bayesian parameter estimation , 2012 .

[47]  Laura Uusitalo,et al.  Advantages and challenges of Bayesian networks in environmental modelling , 2007 .

[48]  M. Perry,et al.  The generation of monthly gridded datasets for a range of climatic variables over the UK , 2005 .

[49]  Usama M. Fayyad,et al.  Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning , 1993, IJCAI.

[50]  Richard Dikau,et al.  Landform classification of New Mexico by computer , 1991 .

[51]  J. Cain.  Planning improvements in natural resource management. Guidelines for using Bayesian networks to support the planning and management of development programmes in the water sector and beyond , 2001 .

[52]  Elisabeth N. Bui,et al.  Spatial data mining for enhanced soil map modelling , 2002, Int. J. Geogr. Inf. Sci..

[53]  R. Hill,et al.  The UK Land Cover Map 2000: Construction of a Parcel-Based Vector Map from Satellite Images , 2002 .

[54]  Simon E. Cook,et al.  A Rule-based System to Map Soil Properties , 1996 .

[55]  M. Galdos,et al.  Near infrared spectroscopy for soil bulk density assessment , 2009 .

[56]  Luca Montanarella,et al.  Digital soil assessments: Beyond DSM , 2007 .

[57]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[58]  Finn Verner Jensen,et al.  Introduction to Bayesian Networks , 2008, Innovations in Bayesian Networks.

[59]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

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

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

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

[63]  T. Bayes.  An essay towards solving a problem in the doctrine of chances , 2003 .

[64]  A. Skidmore,et al.  An Operational GIS Expert System for Mapping Forest Soils , 1996 .

[65]  C. Kucharik,et al.  Developing models to predict soil bulk density in southern Wisconsin using soil chemical properties , 2008 .

[66]  W. Towers,et al.  The Risk of Peat Erosion from Climate Change: Land Management Combinations—An Assessment with Bayesian Belief Networks , 2010 .

[67]  J. Hannam,et al.  Empirically‐derived pedotransfer functions for predicting bulk density in European soils , 2012 .

[68]  M. Wiesmeier,et al.  Digital mapping of soil organic matter stocks using Random Forest modeling in a semi-arid steppe ecosystem , 2011, Plant and Soil.

[69]  Harry Zhang,et al.  The Optimality of Naive Bayes , 2004, FLAIRS.

[70]  B. Marcot,et al.  Bayesian belief networks: applications in ecology and natural resource management , 2006 .

[71]  Paul L. G. Vlek,et al.  Artificial Neural Network Estimation of Saturated Hydraulic Conductivity , 2007 .

[72]  Nir Friedman,et al.  Discretizing Continuous Attributes While Learning Bayesian Networks , 1996, ICML.

[73]  J. Deckers,et al.  World Reference Base for Soil Resources , 1998 .

[74]  A. Astover,et al.  Modelling soil organic carbon concentration of mineral soils in arable land using legacy soil data , 2011 .

[75]  Wisdom M. Dlamini,et al.  A Bayesian belief network analysis of factors influencing wildfire occurrence in Swaziland , 2010, Environ. Model. Softw..

[76]  Dominique Arrouays,et al.  Extrapolating regional soil landscapes from an existing soil map: Sampling intensity, validation procedures, and integration of spatial context , 2008 .

[77]  Anthony J. Jakeman,et al.  Selecting among five common modelling approaches for integrated environmental assessment and management , 2013, Environ. Model. Softw..

[78]  Kerrie Mengersen,et al.  Integrating Bayesian networks and geographic information systems: Good practice examples , 2012, Integrated environmental assessment and management.

[79]  W. Towers,et al.  Risk of erosion in peat soils – an investigation using Bayesian belief networks , 2011 .