Improve performance and robustness of knowledge-based FUZZY LOGIC habitat models

Abstract Previous criticisms of knowledge-based fuzzy logic modelling have identified some of its limitations and revealed weaknesses regarding the development of fuzzy sets, the integration of expert knowledge, and the outcomes of different defuzzification processes. We show here how expert disagreement and fuzzy logic mechanisms associated with the rule development and combinations can positively or adversely affect model performance and the interpretation of results. We highlight how expert disagreement can induce uncertainty into model outputs when defining fuzzy sets and selecting a defuzzification method. We present a framework to account for sources of error and bias and improve the performance and robustness of knowledge-based fuzzy logic models. We recommend to 1) provide clear/unambiguous instructions on model development, processes and objectives, including the definition of input variables and fuzzy sets, 2) incorporate the disagreement among experts into the analysis, 3) increase the use of short rules and the OR operator to reduce complexity, and 4) improve model performance and robustness by using narrow fuzzy sets for extreme values of input variables to expand the universe of discourse adequately. Our framework is focused on fuzzy logic models but can be applied to all knowledge-based models that require expert judgment, including expert systems, decision trees and (fuzzy) Bayesian inference systems.

[1]  Jianwen Chen,et al.  Dealing with Uncertainty: A Survey of Theories and Practices , 2013, IEEE Transactions on Knowledge and Data Engineering.

[2]  M. Reed.  Stakeholder participation for environmental management: A literature review , 2008 .

[3]  B. Baets,et al.  Fuzzy rule-based macroinvertebrate habitat suitability models for running waters , 2006 .

[4]  R. G. Randall,et al.  Effects of low-head barriers on stream fishes: taxonomic affiliations and morphological correlates of sensitive species , 2006 .

[5]  Michael H. Huesemann,et al.  The inherent biases in environmental research and their effects on public policy , 2002 .

[6]  Guillermo A. Mendoza,et al.  Multi-criteria decision analysis in natural resource management: A critical review of methods and new modelling paradigms , 2006 .

[7]  Ying Bai,et al.  Fundamentals of Fuzzy Logic Control — Fuzzy Sets, Fuzzy Rules and Defuzzifications , 2006 .

[8]  Mark A. Burgman,et al.  Toward rigorous use of expert knowledge in ecological research , 2013 .

[9]  Jane M. Booker,et al.  Eliciting and analyzing expert judgement - a practical guide , 2001, ASA-SIAM series on statistics and applied probability.

[10]  A. St‐Hilaire,et al.  Assessment of Atlantic salmon (Salmo salar) habitat quality and its uncertainty using a multiple-expert fuzzy model applied to the Romaine River (Canada) , 2013 .

[11]  W. Aspinall.  A route to more tractable expert advice , 2010, Nature.

[12]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[13]  A. Salski,et al.  Fuzzy knowledge-based models in ecological research , 1992 .

[14]  A. Stamou,et al.  Evaluating the performance of habitat models for predicting the environmental flow requirements of benthic macroinvertebrates , 2018 .

[15]  David N. Ford,et al.  Expert knowledge elicitation to improve mental and formal models , 1997 .

[16]  Vincent C. Yen,et al.  Rule selections in fuzzy expert systems , 1999 .

[17]  Erik Lebret,et al.  The use of expert elicitation in environmental health impact assessment: a seven step procedure , 2010, Environmental health : a global access science source.

[18]  C. Wolter,et al.  Differences among Expert Judgments of Fish Habitat Suitability and Implications for River Management , 2017 .

[19]  A. St‐Hilaire,et al.  Inclusion of water temperature in a fuzzy logic Atlantic salmon (Salmo salar) parr habitat model. , 2020, Journal of thermal biology.

[20]  B. Baets,et al.  Effect of model formulation on the optimization of a genetic Takagi–Sugeno fuzzy system for fish habitat suitability evaluation , 2011 .

[21]  Bernard De Baets,et al.  Knowledge-based versus data-driven fuzzy habitat suitability models for river management , 2009, Environ. Model. Softw..

[22]  Ebrahim H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Hum. Comput. Stud..

[23]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[24]  A. P. Rotshtein,et al.  Influence of Defuzzification Methods on the Rate of Tuning a Fuzzy Model , 2002 .

[25]  Matthias Schneider,et al.  Fuzzy based Models for the Evaluation of Fish Habitat Quality and Instream Flow Assessment , 2001 .

[26]  Harpreet Singh,et al.  Real-Life Applications of Fuzzy Logic , 2013, Adv. Fuzzy Syst..

[27]  A. St‐Hilaire,et al.  Influences of Experts' Personal Experiences in Fuzzy Logic Modeling of Atlantic Salmon Habitat , 2015 .

[28]  Lotfi A. Zadeh,et al.  Is there a need for fuzzy logic? , 2008, NAFIPS 2008 - 2008 Annual Meeting of the North American Fuzzy Information Processing Society.

[29]  B. Ataie‐Ashtiani,et al.  Efficient fuzzy Bayesian inference algorithms for incorporating expert knowledge in parameter estimation , 2016 .

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

[31]  D. Lindenmayer,et al.  The nature and role of experiential knowledge for environmental conservation , 2006, Environmental Conservation.

[32]  Oļegs Užga-Rebrovs,et al.  Comparative Analysis of Fuzzy Set Defuzzification Methods in the Context of Ecological Risk Assessment , 2017 .

[33]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[34]  Enrique H. Ruspini,et al.  Similarity and Implication between Fuzzy Sets , 2012, Combining Experimentation and Theory.

[35]  S. Pal,et al.  Fuzzy Logic and Approximate Reasoning: An Overview , 1991 .

[36]  Mark A. Burgman,et al.  Expert Status and Performance , 2011, PloS one.

[37]  T. Runkler,et al.  A set of axioms for defuzzification strategies towards a theory of rational defuzzification operators , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[38]  Efficiency of coupled invasive weed optimization-adaptive neuro fuzzy inference system method to assess physical habitats in streams , 2021 .

[39]  Matthias Schneider,et al.  Optimisation of a fuzzy physical habitat model for spawning European grayling ( Thymallus thymallus L.) in the Aare river (Thun, Switzerland) , 2008 .

[40]  A. Salski,et al.  A fuzzy knowledge-based model of population dynamics of the Yellow-necked mouse (Apodemus flavicollis) in a beech forest , 1998 .

[41]  E. H. Mamdani,et al.  Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis , 1976, IEEE Transactions on Computers.

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

[43]  Peter Goethals,et al.  Fuzzy knowledge-based models for prediction of Asellus and Gammarus in watercourses in Flanders (Belgium) , 2006 .

[44]  André St-Hilaire,et al.  Regularized Bayesian quantile regression , 2018, Commun. Stat. Simul. Comput..

[45]  R. Muñoz‐Mas,et al.  Generalized additive and fuzzy models in environmental flow assessment: A comparison employing the West Balkan trout ( Salmo farioides ; Karaman, 1938) , 2016 .

[46]  Behrouz Ahmadi-Nedushan,et al.  Instream flow determination using a multiple input fuzzy-based rule system: a case study , 2008 .