Loading…
A comparison of artificial neural networks and random forests to predict native fish species richness in Mediterranean rivers
Machine learning (ML) techniques have become important to support decision making in management and conservation of freshwater aquatic ecosystems. Given the large number of ML techniques and to improve the understanding of ML utility in ecology, it is necessary to perform comparative studies of thes...
Saved in:
Published in: | Knowledge and management of aquatic ecosystems 2013-01 (409), p.7 |
---|---|
Main Authors: | , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Machine learning (ML) techniques have become important to support decision making in management and conservation of freshwater aquatic ecosystems. Given the large number of ML techniques and to improve the understanding of ML utility in ecology, it is necessary to perform comparative studies of these techniques as a preparatory analysis for future model applications. The objectives of this study were (i) to compare the reliability and ecological relevance of two predictive models for fish richness, based on the techniques of artificial neural networks (ANN) and random forests (RF) and (ii) to evaluate the conformity in terms of selected important variables between the two modelling approaches. The effectiveness of the models were evaluated using three performance metrics: the determination coefficient (R2), the mean squared error (MSE) and the adjusted determination coefficient (R2adj and both models were developed using a k-fold crossvalidation procedure. According to the results, both techniques had similar validation performance (R2 = 68% for RF and R2 = 66% for ANN). Although the two methods selected different subsets of input variables, both models demonstrated high ecological relevance for the conservation of native fish in the Mediterranean region. Moreover, this work shows how the use of different modelling methods can assist the critical analysis of predictions at a catchment scale.
Les techniques d’apprentissage automatique (ML) sont devenues importantes pour aider à la décision dans la gestion et la conservation des écosystèmes aquatiques d’eau douce. Étant donné le grand nombre de techniques ML pour améliorer la compréhension de l’utilité des ML en écologie, il est nécessaire de réaliser des études comparatives de ces techniques comme analyse préparatoire pour des applications de modèles futurs. Les objectifs de cette étude étaient : (i) de comparer la fiabilité et la pertinence écologique de deux modèles prédictifs pour la richesse de poisson, basé sur les techniques de réseaux de neurones artificiels (ANN) et les forêts aléatoires (RF) et (ii) d’évaluer la conformité en termes de sélection des variables importantes entre les deux approches de modélisation. L’efficacité des modèles a été évaluée au moyen de trois indicateurs de performance : le coefficient de détermination (R2), l’erreur quadratique moyenne (MSE) et le coefficient de détermination ajusté (R2adj et les deux modèles ont été développés en utilisant une procédure de validation cro |
---|---|
ISSN: | 1961-9502 1961-9502 |
DOI: | 10.1051/kmae/2013052 |