A comparison of two sensitivity analysis techniques based on four bayesian models representing ecosystem services provision in the Argentine Pampas

Abstract Sensitivity analyses (SAs) identify how an output variable of a model is modified by changes in the input variables. These analyses are a good way for assessing the performance of probabilistic models, like Bayesian Networks (BN). However, there are several commonly used SAs in BN literature, and formal comparisons about their outcomes are scarce. We used four previously developed BNs which represent ecosystem services provision in Pampean agroecosystems (Argentina) in order to test two local sensitivity approaches widely used. These SAs were: 1) One-at-a-time, used in BNs but more commonly in linear modelling; and 2) Sensitivity to findings, specific to BN modelling. Results showed that both analyses provided an adequate overview of BN behaviour. Furthermore, analyses produced a similar influence ranking of input variables over each output variable. Even though their interchangeably application could be an alternative in our bayesian models, we believe that OAT is the suitable one to implement here because of its capacity to demonstrate the relation (positive or negative) between input and output variables. In summary, we provided insights about two sensitivity techniques in BNs based on a case study which may be useful for ecological modellers.

[1]  Daniel Zelterman,et al.  Bayesian Artificial Intelligence , 2005, Technometrics.

[2]  Wayne E. Thogmartin,et al.  Sensitivity analysis of North American bird population estimates , 2010 .

[3]  Niels Peek,et al.  Using sensitivity analysis for efficient quantification of a belief network , 1999, Artif. Intell. Medicine.

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

[5]  Mark E. Borsuk,et al.  A Bayesian network of eutrophication models for synthesis, prediction, and uncertainty analysis , 2004 .

[6]  D. Ferraro,et al.  Ecosystem Services Provided by Agroecosystems: A Qualitative and Quantitative Assessment of this Relationship in the Pampa Region, Argentina , 2014, Environmental Management.

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

[8]  P. Sedgwick.  Standardising outcome measures using z scores , 2014, BMJ : British Medical Journal.

[9]  A. Saltelli,et al.  The role of sensitivity analysis in ecological modelling , 2007 .

[10]  Yao Hu,et al.  Global sensitivity analysis for large-scale socio-hydrological models using Hadoop , 2015, Environ. Model. Softw..

[11]  Fundamental Processes in Ecology: An Earth Systems Approach , 2006 .

[12]  B. Burkhard,et al.  Ecosystem services–A tool for sustainable management of human–environment systems. Case study Finnish Forest Lapland , 2010 .

[13]  Anders L. Madsen,et al.  The Hugin Tool for Probabilistic Graphical Models , 2005, Int. J. Artif. Intell. Tools.

[14]  Kristian Kristensen,et al.  The use of a Bayesian network in the design of a decision support system for growing malting barley without use of pesticides , 2002 .

[15]  Charles M. Macal,et al.  Lessons from a comprehensive validation of an agent based-model: The experience of the Pampas Model of Argentinean agricultural systems , 2014 .

[16]  J. L. Puga,et al.  Las redes bayesianas como herramientas de modelado en psicología , 2007 .

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

[18]  Kerrie L. Mengersen,et al.  A proposed validation framework for expert elicited Bayesian Networks , 2013, Expert Syst. Appl..

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

[20]  Linda C. van der Gaag,et al.  Properties of Sensitivity Analysis of Bayesian Belief Networks , 2002, Annals of Mathematics and Artificial Intelligence.

[21]  Wiktor Frid,et al.  Identification of sensitivities in Bayesian networks , 2004, Eng. Appl. Artif. Intell..

[22]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[23]  D. Hamby.  A review of techniques for parameter sensitivity analysis of environmental models , 1994, Environmental monitoring and assessment.

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

[25]  Guillermo P Podesta,et al.  Sensitivity of CERES-Maize simulated yields to uncertainty in soil properties and daily solar radiation , 2007 .

[26]  Ann E. Nicholson,et al.  Structural Sensitivity for the Knowledge Engineering of Bayesian Networks , 2014, Probabilistic Graphical Models.

[27]  Edward J. Rykiel,et al.  Testing ecological models: the meaning of validation , 1996 .

[28]  Adrienne Grêt-Regamey,et al.  Spatially explicit avalanche risk assessment linking Bayesian networks to a GIS , 2006 .

[29]  Gianni Bellocchi,et al.  Comparison of sensitivity analysis techniques: A case study with the rice model WARM , 2010 .

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

[31]  Sylvain Payraudeau,et al.  Environmental impact assessment for a farming region: a review of methods , 2005 .

[32]  Analía Amandi,et al.  Evaluating Bayesian networks' precision for detecting students' learning styles , 2007, Comput. Educ..

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

[34]  Paola Annoni,et al.  Sixth International Conference on Sensitivity Analysis of Model Output How to avoid a perfunctory sensitivity analysis , 2010 .

[35]  Anthony J. Jakeman,et al.  A Bayesian network approach for assessing the sustainability of coastal lakes in New South Wales, Australia , 2007, Environ. Model. Softw..

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

[37]  Estevam R. Hruschka,et al.  Using Bayesian networks with rule extraction to infer the risk of weed infestation in a corn-crop , 2009, Eng. Appl. Artif. Intell..

[38]  Andrea Castelletti,et al.  Bayesian Networks and participatory modelling in water resource management , 2007, Environ. Model. Softw..

[39]  Forrest Stonedahl,et al.  The Complexities of Agent-Based Modeling Output Analysis , 2015, J. Artif. Soc. Soc. Simul..

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

[41]  Anthony J. Jakeman,et al.  Sensitivity analysis for assessing the behaviour of a landscape-based sediment source and transport model , 2003, Environ. Model. Softw..

[42]  V Stelzenmüller,et al.  Assessment of a Bayesian Belief Network-GIS framework as a practical tool to support marine planning. , 2010, Marine pollution bulletin.

[43]  Norman Abramson,et al.  Teoría de la Información y Codificación , 1981 .

[44]  Malka Gorfine,et al.  Sensitivity analysis for complex ecological models - A new approach , 2011, Environ. Model. Softw..

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

[46]  Adnan Darwiche,et al.  Sensitivity Analysis in Bayesian Networks: From Single to Multiple Parameters , 2004, UAI.