Development of a Habitat Suitability Index for the Noble Crayfish Astacus Astacus Using Fuzzy Modelling

Abstract

A Geographic Information System (GIS) and fuzzy modelling were used to develop a habitat suitability index for the noble crayfish, Astacus astacus. The model is based on crayfish distribution data for the federal state Hesse, Germany, which had been recorded between 1988 and 1996. It includes 185 sites with noble crayfish in 126 watercourses. Official data on the morphological quality of surface waters recorded between 1996 and 1998 by order of the Ministry of Hesse for Environment, Rural Areas and Consumers Protection was used to describe the habitat features. One third of the crayfish sites was selected by chance to determine habitat properties significantly associated with crayfish occurrence by means of the Kolmogorov-Smirnoff test and frequency analysis. Meaningless associations were excluded based on expert knowledge. Five parameters related to the structure of the riverbed and the bankside were incorporated in the fuzzy model. The model was complemented by a number of parameters known to exclude the occurrence of the noble crayfish (e.g. pipes, concrete embankments). Finally, a habitat suitability index for every stretch of water in Hesse was calculated. The predictive power of the fuzzy model was tested on the remaining distribution data set for Astacus astacus. The habitat suitability index differed slightly but significantly (p < 0.001) between sites with and sites without crayfish occurrence. Fuzzy modelling proved to be useful for assessing habitat suitability with respect to crayfish, though further improvements of the model appeared to be necessary for a more reliable prediction of noble crayfish sites. Key-words:Astacus astacus, fuzzy modelling, Germany, Geographic Information System (GIS), habitat suitability, stream structure, Water Framework Directive. DÉVELOPPEMENT D'UN INDICE DE QUALITÉ D'HABITAT POUR L'ÉCREVISSE NOBLE ASTACUS ASTACUS PAR MODÉLISATION FLOUE RÉSUMÉ

Modeling and predicting meat yield and growth performance using morphological features of narrow-clawed crayfish with machine learning techniques

“…There are many different ways in machine learning involving patterns in which relationships will be discovered, each of which determines the type of technique that can be used to make sense of the output from the data. The most commonly used machine learning methods in the literature are; artificial neural networks (Surayanarayana et al, 2008;Tirelli et al, 2011;Benzer et al, 2017), logistic regression (Benzer et al, 2017;Gültepe and Gültepe, 2020), fuzzy modeling (Zuther et al, 2005), genetic algorithms and programming (Luna et al, 2019), decision tree (Tirelli et al, 2011;Gültepe and Gültepe, 2020), Bayesian network approach (Lin et al, 2004;Hamilton et al, 2015;Trifonova et al, 2017), random forest (Gültepe and Gültepe, 2020;Adibi et al, 2020), support vector machine (Gültepe and Gültepe, 2020;Favaro et al, 2011). Regression-based modeling techniques are widely used to estimate species distribution.…”

Modeling and predicting meat yield and growth performance using morphological features of narrow-clawed crayfish with machine learning techniques

“…There are many different ways in machine learning involving patterns in which relationships will be discovered, each of which determines the type of technique that can be used to make sense of the output from the data. The most commonly used machine learning methods in the literature are; artificial neural networks [6–8], logistic regression [8–9], fuzzy modeling [10], genetic algorithms and programming [11], decision tree [7,9], Bayesian network approach [12–14], random forest [9,15], support vector machine [9,16]. Regression-based modeling techniques are widely used to estimate species distribution.…”

“…The most commonly used machine learning methods in the literature are; artificial neural networks [6][7][8], logistic regression [8][9], fuzzy modeling [10], genetic algorithms and programming [11],…”

GIS-based assessment of land suitability for alfalfa cultivation: a case study in the dry continental steppes of northern China

“…Fuzzy set methodology has the potential to provide better land evaluations than the commonly used discrete approaches because this approach can accommodate the effects of attribute values and properties that are close to category boundaries (Stoms et al, 2002). A number of fuzzy MCDA approaches that combine the advantages of these two methods have been developed for assessing land suitability (Ruger et al, 2005;Sicat et al, 2005;Zuther et al, 2005). In addition, Mendas & Delali (2012) developed a spatial decisionsupport system that enabled the preparation of agricultural land-use suitability maps by integrating GIS with the ELECTRE Tri multi-criterion analysis method.…”