Ecological uses for genetic algorithms: predicting fish distributions in complex physical habitats

D'Angelo, D. J.; Meyer, Judy L.; Howard, Leslie; Gregory, S.; Ashkenas, Linda R.

doi:10.1139/f95-782

Cited by 37 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1998), multivariate approaches based on linear or logistic regressions (Yu et al 1990; Lamouroux et al . 1999) , non‐linear techniques based on artificial intelligence (D’Angelo et al . 1995; Mastrorillo et al .…”

Section: Discussionmentioning

confidence: 99%

Fish habitat preferences in large streams of southern France

Lamouroux¹,

Capra²,

Pouilly³

et al. 1999

Freshwater Biology

153

186

View full text Add to dashboard Cite

1. Relationships between fish and their habitat over whole geographic regions, which are evident from studies of many streams and species, can improve understanding of lotic communities and provide reliable management tools. Nevertheless, most habitat preference studies have been based on single sites, and confined to small streams and to game species. 2. Regional habitat preference models, based on local velocity, depth and roughness, were developed for twenty‐four species and their size classes commonly found in large European streams. Fish surveys were conducted in six large streams in southern France over an 8‐year period. To limit the influences of habitat variables other than those studied, we estimated fish preferences within each survey and averaged this information across surveys. Preferences were fitted with confidence intervals and their sensitivity to field uncertainty was evaluated. 3. Most species and size classes had significant preferences for local habitat conditions which were consistent across the region. Habitat preferences predominant in the region overall were not always observed at any one site, but habitat conditions preferred on average in the region were never actually avoided locally. These results support the use of regional preference models for fish and the development of similar models for other lotic groups whose sensitivity to local habitat conditions has been reported elsewhere.

show abstract

Section: Discussionmentioning

confidence: 99%

Fish habitat preferences in large streams of southern France

Lamouroux¹,

Capra²,

Pouilly³

et al. 1999

Freshwater Biology

153

186

View full text Add to dashboard Cite

show abstract

“…Lek et al ., 1996; Mastrorillo et al ., 1997; Brosse & Lek, 2000; Olden & Jackson, 2001) and genetic algorithms (e.g. D'Angelo et al ., 1995) for modelling ecological data. It is believed that these alternative approaches can provide researchers with more flexible tools for modelling complex ecological relationships.…”

Section: Introductionmentioning

confidence: 99%

A comparison of statistical approaches for modelling fish species distributions

2002

View full text Add to dashboard Cite

SUMMARY 1. The prediction of species distributions is of primary importance in ecology and conservation biology. Statistical models play an important role in this regard; however, researchers have little guidance when choosing between competing methodologies because few comparative studies have been conducted. 2. We provide a comprehensive comparison of traditional and alternative techniques for predicting species distributions using logistic regression analysis, linear discriminant analysis, classification trees and artificial neural networks to model: (1) the presence/absence of 27 fish species as a function of habitat conditions in 286 temperate lakes located in south‐central Ontario, Canada and (2) simulated data sets exhibiting deterministic, linear and non‐linear species response curves. 3. Detailed evaluation of model predictive power showed that approaches produced species models that differed in overall correct classification, specificity (i.e. ability to correctly predict species absence) and sensitivity (i.e. ability to correctly predict speciespresence) and in terms of which of the study lakes they correctly classified. Onaverage, neural networks outperformed the other modelling approaches, although all approaches predicted species presence/absence with moderate to excellent success. 4. Based on simulated non‐linear data, classification trees and neural networks greatly outperformed traditional approaches, whereas all approaches exhibited similar correct classification rates when modelling simulated linear data. 5. Detailed evaluation of model explanatory insight showed that the relative importance of the habitat variables in the species models varied among the approaches, where habitat variable importance was similar among approaches for some species and very different for others. 6. In general, differences in predictive power (both correct classification rate and identity of the lakes correctly classified) among the approaches corresponded with differences in habitat variable importance, suggesting that non‐linear modelling approaches (i.e. classification trees and neural networks) are better able to capture and model complex, non‐linear patterns found in ecological data. The results from the comparisons using simulated data further support this notion. 7. By employing parallel modelling approaches with the same set of data and focusing on comparing multiple metrics of predictive performance, researchers can begin to choose predictive models that not only provide the greatest predictive power, but also best fit the proposed application.

show abstract

“…This technique has been used to identify current suitable habitat for specific taxa, model future species distributions including predicting invasive and rare species presence, and predict biodiversity of an area (Tan & Smeins 1996;Kampichler et al 2000;Cutler et al 2007;Olden et al 2008;. Common tools include Random Forest (Cutler et al 2007;Peters et al 2007), classification and decision trees (Ribic & Ainley 1997;Kobler & Adamic 2000;Bell 1999;Vayssièrs et al 2000;Debeljak et al 2001;Miller & Franklin 2002), neural networks (Mastrorillo et al 1997;Guégan et al 1998;Özesmi et al 2006;Brosse et al 2001;Thuiller 2003;Fielding 1999a;Dedecker et al 2004;Manel et al 2001;Segurado & Araújo 2004), genetic algorithms (D'Angelo et al 1995;Stockwell & Peters 1999;McKay 2001;Wiley et al 2003;Termansen et al 2006;Stockwell 1999;Peterson et al 2002), and Bayesian classifiers (Fischer 1990;Brzeziecki et al 1993;Guisan & Zimmermann 2000).…”

Section: Habitat Modeling and Species Distributionmentioning

confidence: 99%

Adoption of machine learning techniques in Ecology and Earth Science

Thessen

2016

Preprint

View full text Add to dashboard Cite

The natural sciences, such as ecology and earth science, study complex interactions between biotic and abiotic systems in order to infer understanding and make predictions. Machine-learning-based methods have an advantage over traditional statistical methods in studying these systems because the former do not impose unrealistic assumptions (such as linearity), are capable of inferring missing data, and can reduce long-term expert annotation burden. Thus, a wider adoption of machine learning methods in ecology and earth science has the potential to greatly accelerate the pace and quality of science. Despite these advantages, machine learning techniques have not had wide spread adoption in ecology and earth science. This is largely due to 1) a lack of communication and collaboration between the machine learning research community and natural scientists, 2) a lack of easily accessible tools and services, and 3) the requirement for a robust training and test data set. These impediments can be overcome through financial support for collaborative work and the development of tools and services facilitating ML use. Natural scientists who have not yet used machine learning methods can be introduced to these techniques through Random Forest, a method that is easy to implement and performs well. This manuscript will 1) briefly describe several popular ML methods and their application to ecology and earth science, 2) discuss why ML methods are underutilized in natural science, and 3) propose solutions for barriers preventing wider ML adoption.

show abstract

Ecological uses for genetic algorithms: predicting fish distributions in complex physical habitats

Cited by 37 publications

References 15 publications

Fish habitat preferences in large streams of southern France

Fish habitat preferences in large streams of southern France

A comparison of statistical approaches for modelling fish species distributions

Adoption of machine learning techniques in Ecology and Earth Science

Contact Info

Product

Resources

About