How good are Bayesian belief networks for environmental management? A test with data from an agricultural river catchment

1. The ecological health of rivers worldwide continues to decline despite increasing effort and investment in river science and management. Bayesian belief networks (BBNs) are increasingly being used as a mechanism for decision-making in river management because they provide a simple visual framework to explore different management scenarios for the multiple stressors that impact rivers. However, most applications of BBN modelling to resource management use expert knowledge and/or limited real data, and fail to accurately assess the ability of the model to make predictions. 2. We developed a BBN to model ecological condition in a New Zealand river using field/GIS data (from multiple rivers), rather than expert opinion, and assessed its predictive ability on an independent dataset. The developed BBN performed moderately better than a number of other modelling techniques (e.g., artificial neural networks, classification trees, random forest, logistic regression), although model construction was more time3consuming. Thus the predictive ability of BBNs is (in this case at least) on a par with other modelling methods but the approach is distinctly better for its ability to visually present the data linkages, issues and potential outcomes of management options in real time. 3. The BBN suggested management of habitat quality, su ch as riparian planting, along with the current management focus on limiting nutrient leaching from agricultural land may be most effective in improving ecological condition. 4. BBNs can be a powerful and accurate method of effectively portraying the multiple interacting drivers of environmental condition in an easily understood manner. However, most BBN applications fail to appropriately test the model fit prior to use. We believe this lack of testing may seriously undermine their long-term effectiveness in resource management, and recommend that BBNs should be used in conjunction with some measure of uncertainty about model predictions. We have demonstrated this for a BBN of ecological condition in a New Zealand river, shown that model fit is better than that for other modelling techniques, and that improving habitat would be equally effective to reducing nutrients to improve ecological condition.

[1]  Stephen T. Buckland,et al.  The role of simulation in modelling spatially correlated data , 1998 .

[2]  David R. B. Stockwell,et al.  ANNA: A new prediction method for bioassessment programs , 2005 .

[3]  I. Fuller,et al.  Resetting the river template: the potential for climate‐related extreme floods to transform river geomorphology and ecology , 2015 .

[4]  Ton H. Snelder,et al.  MULTISCALE RIVER ENVIRONMENT CLASSIFICATION FOR WATER RESOURCES MANAGEMENT 1 , 2002 .

[5]  R. Death,et al.  Predictive modelling and spatial mapping of freshwater fish and decapod assemblages using GIS and neural networks , 2004 .

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

[7]  A. Louise Heathwaite,et al.  Why is achieving good ecological outcomes in rivers so difficult , 2012 .

[8]  Melissa Clark,et al.  Diffuse contributions dominate over point sources of soluble nutrients in two sub-catchments of the Manawatu River, New Zealand , 2012 .

[9]  K. Hughey,et al.  The Use of an Ecologic Classification to Improve Water Resource Planning in New Zealand , 2005, Environmental management.

[10]  R. Davies‐Colley,et al.  Planted Riparian Buffer Zones in New Zealand: Do They Live Up to Expectations? , 2003 .

[11]  David J. Hand,et al.  Construction and Assessment of Classification Rules , 1997 .

[12]  J. Allan.  Landscapes and Riverscapes: The Influence of Land Use on Stream Ecosystems , 2004 .

[13]  Chuong B Do,et al.  What is the expectation maximization algorithm? , 2008, Nature Biotechnology.

[14]  Á. Borja,et al.  The European Water Framework Directive at the age of 10: a critical review of the achievements with recommendations for the future. , 2010, The Science of the total environment.

[15]  B. Marcot,et al.  Using Bayesian belief networks to evaluate fish and wildlife population viability under land management alternatives from an environmental impact statement , 2001 .

[16]  G. De’ath,et al.  CLASSIFICATION AND REGRESSION TREES: A POWERFUL YET SIMPLE TECHNIQUE FOR ECOLOGICAL DATA ANALYSIS , 2000 .

[17]  Rosa F. Ropero,et al.  Regression using hybrid Bayesian networks: Modelling landscape-socioeconomy relationships , 2014, Environ. Model. Softw..

[18]  M. Palmer,et al.  Frontiers inEcology and the Environment Climate change and the world ’ s river basins : anticipating management options , 2007 .

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

[20]  Andrew J. Boulton,et al.  An overview of river health assessment: philosophies, practice, problems and prognosis , 1999 .

[21]  N. Poff,et al.  Ecological responses to altered flow regimes: a literature review to inform the science and management of environmental flows , 2010 .

[22]  Olivier Pourret,et al.  Bayesian networks : a practical guide to applications , 2008 .

[23]  Julian D Olden,et al.  Machine Learning Methods Without Tears: A Primer for Ecologists , 2008, The Quarterly Review of Biology.

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

[25]  D. Faith,et al.  Monitoring Ecological Impacts: Concepts and Practice in Flowing Waters , 2002 .

[26]  P. McIntyre,et al.  Global threats to human water security and river biodiversity , 2010, Nature.

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

[28]  R. Death,et al.  A review of the consequences of decreased flow for instream habitat and macroinvertebrates , 2007, Journal of the North American Benthological Society.

[29]  M. Acreman,et al.  Environmental flows and the European Water Framework Directive. , 2010 .

[30]  R. Death,et al.  Invertebrate community structure in streams of the Manawatu–Wanganui region, New Zealand: the roles of catchment versus reach scale influences , 2004 .

[31]  B. Downes.  Back to the future: little‐used tools and principles of scientific inference can help disentangle effects of multiple stressors on freshwater ecosystems , 2010 .

[32]  A. Townsend Peterson,et al.  Novel methods improve prediction of species' distributions from occurrence data , 2006 .

[33]  T. Reynoldson,et al.  The Reference Condition: A Comparison of Multimetric and Multivariate Approaches to Assess Water-Quality Impairment Using Benthic Macroinvertebrates , 1997, Journal of the North American Benthological Society.

[34]  J. Olden,et al.  Conservation biogeography of freshwater fishes: recent progress and future challenges , 2010 .

[35]  Julian D Olden,et al.  Rediscovering the species in community-wide predictive modeling. , 2006, Ecological applications : a publication of the Ecological Society of America.

[36]  Bruce G. Marcot,et al.  Metrics for evaluating performance and uncertainty of Bayesian network models , 2012 .

[37]  S. Cessie,et al.  Ridge Estimators in Logistic Regression , 1992 .

[38]  Boris Schröder,et al.  Are habitat models transferable in space and time , 2000 .

[39]  W. S. Fisher,et al.  Making Waves with the Clean Water Act , 2008, Science.

[40]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[41]  C. Townsend,et al.  Subsidy-stress and multiple-stressor effects along gradients of deposited fine sediment and dissolved nutrients in a regional set of streams and rivers , 2011 .

[42]  J. David Allan,et al.  Investigating the relationships between environmental stressors and stream condition using Bayesian belief networks , 2012 .

[43]  W. L. Chadderton,et al.  Dispersal, disturbance and the contrasting biogeographies of New Zealand’s diadromous and non‐diadromous fish species , 2008 .

[44]  R. Naiman,et al.  Freshwater biodiversity: importance, threats, status and conservation challenges , 2006, Biological reviews of the Cambridge Philosophical Society.

[45]  K. Burnham,et al.  Model selection: An integral part of inference , 1997 .

[46]  John R. Leathwick,et al.  Quantifying relationships between land-use gradients and structural and functional indicators of stream ecological integrity , 2012 .

[47]  M. Boyce,et al.  Evaluating resource selection functions , 2002 .

[48]  Oswaldo Morales-Nápoles,et al.  A continuous Bayesian network for earth dams' risk assessment: methodology and quantification , 2014 .

[49]  Ton H. Snelder,et al.  Is the River Environment Classification an improved landscape-scale classification of rivers? , 2004, Journal of the North American Benthological Society.

[50]  Ben Stewart-Koster,et al.  Understanding multiple ecological responses to anthropogenic disturbance: rivers and potential flow regime change. , 2012, Ecological applications : a publication of the Ecological Society of America.

[51]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[52]  Guy Woodward,et al.  Biomonitoring of Human Impacts in Freshwater Ecosystems: The Good, the Bad and the Ugly , 2011 .

[53]  P. Verdonschot,et al.  Chapter Three - From Natural to Degraded Rivers and Back Again: A Test of Restoration Ecology Theory and Practice , 2011 .

[54]  Stephen James Ormerod,et al.  Multiple stressors in freshwater ecosystems , 2010 .

[55]  S. Carpenter,et al.  NONPOINT POLLUTION OF SURFACE WATERS WITH PHOSPHORUS AND NITROGEN , 1998 .

[56]  Kevin B. Korb,et al.  Parameterisation and evaluation of a Bayesian network for use in an ecological risk assessment , 2007, Environ. Model. Softw..

[57]  Peter Davies,et al.  The Sustainable Rivers Audit: assessing river ecosystem health in the Murray Darling Basin, Australia , 2010 .

[58]  R. Death,et al.  Measuring stream macroinvertebrate responses to gradients of vegetation cover: when is enough enough? , 2009 .

[59]  C. Townsend,et al.  Multiple stressors in agricultural streams: interactions among sediment addition, nutrient enrichment and water abstraction , 2010 .

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

[61]  C. Townsend,et al.  Multiple Stressors in Agricultural Streams: A Mesocosm Study of Interactions among Raised Water Temperature, Sediment Addition and Nutrient Enrichment , 2012, PloS one.