Application of Probabilistic Neural Networks to microhabitat suitability modelling for adult brown trout (Salmo trutta L.) in Iberian rivers

Muñoz‐Mas, Rafael; Martínez‐Capel, Francisco; Garófano‐Gómez, Virginia; Mouton, Ans

doi:10.1016/j.envsoft.2014.05.003

Cited by 21 publications

(16 citation statements)

References 79 publications

(93 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diaz et al, 2004;Costello, 2009) whereby distinct geological, geomorphological and eco-hydraulic regions are interpreted to formulate physical habitat models which can be used to model spatial distributions of benthic biology (e.g. Ryan et al, 2007;Muñoz-Mas et al, 2014;Frieden et al, 2014), and fluid stresses exerted on the bed. An increasingly common means to map benthic habitats in shallow water is through use of swath sonar data (e.g.…”

Section: Characterizing Benthic Substrates Through Sidescan Texture Amentioning

confidence: 99%

Shallow water benthic imaging and substrate characterization using recreational-grade sidescan-sonar

Buscombe

2017

Environmental Modelling & Software

View full text Add to dashboard Cite

In recent years, lightweight, inexpensive, vessel-mounted 'recreational grade' sonar systems have rapidly grown in popularity among aquatic scientists, for swath imaging of benthic substrates. To promote an ongoing 'democratization' of acoustical imaging of shallow water environments, methods to carry out geometric and radiometric correction and georectification of sonar echograms are presented, based on simplified models for sonar-target geometry and acoustic backscattering and attenuation in shallow water. Procedures are described for automated removal of the acoustic shadows, identification of bed-water interface for situations when the water is too turbid or turbulent for reliable depth echosounding, and for automated bed substrate classification based on singlebeam full-waveform analysis. These methods are encoded in an open-source and freely-available software package, which should further facilitate use of recreational-grade sidescan sonar, in a fully automated and objective manner. The sequential correction, mapping, and analysis steps are demonstrated using a data set from a shallow freshwater environment.

show abstract

Section: Characterizing Benthic Substrates Through Sidescan Texture Amentioning

confidence: 99%

Shallow water benthic imaging and substrate characterization using recreational-grade sidescan-sonar

Buscombe

2017

Environmental Modelling & Software

View full text Add to dashboard Cite

show abstract

“…A process of spatial explicit validation (e.g. Muñoz-Mas et al, 2014a) or a transferability test (e.g. Thomas & Bovee, 1993) should be followed in that case.…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, some concerns should be raised because changes in natural flow regimes are occurring in a disorderly manner, and hydrological alteration is among the main anthropogenic threats to conservation of Neotropical fish species in lotic systems (Barletta et al, 2010 (Bowen et al, 2001;Armstrong et al, 2001;Martínez-Capel et al, 2009Muñoz-Mas et al, 2014a).…”

Section: Introductionmentioning

confidence: 99%

“…The habitat suitability models at microhabitat scale range from simple habitat suitability index (HSI) and bivariate polynomial functions (Lambert & Hanson, 1989) to more complex fuzzy rule base models (Jorde et al, 2001;Mouton et al, 2008), such as multilayer perceptron ensembles (Muñoz-Mas et al, 2014a) or probabilistic neural networks (Muñoz-Mas et al, 2014b). The mesohabitat scale areas usually classified as riffles, runs or pools (Angermeier & Schlosser, 1989) that exhibit important differences among them related to water velocity, channel morphology and type of substrate.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of the physical habitat simulation for fish species to assess environmental flows in an Atlantic Forest Stream in South-eastern Brazil

et al. 2015

View full text Add to dashboard Cite

The physical habitat simulation sub-routine of the Instream Flow Incremental Methodology (IFIM) uses hydraulic modeling and suitability indices of target fish species to predict how differences in-stream flows affect the microhabitat occupation by fish species. This habitat modelling approach was adopted to assess the ecological effects of running flows on three neotropical fish species of different orders (Bryconamericus ornaticeps, Ancistrus multispinis and Geophagus brasiliensis).The study encompassed two reaches of an Atlantic Forest stream in Southeastern Brazil where topographic and hydraulic (depth, velocity and type of substrate) characteristics were measured to implement one-dimensional hydraulic simulation. Sub aquatic observation of fish was performed to collect data on microhabitat use and these data were used to develop habitat suitability curves that were used in the habitat simulation to obtain the habitat suitability index (HSI) and weighted usable area (WUA) versus flow curves. Upon these curves minimum and optimum environmental flows for the target fish species were proposed. Bryconamericus ornaticeps and A. multispinis selected microhabitats around 0.6 m depth, whereas G. brasiliensis showed a wider suitable range (0.35-0.9 m). All the three species were mainly observed in microhabitat with low flow velocity (0.1 m/s). Bryconamericus ornaticeps selected more frequently coarse substrate (e.g. boulders) but it appeared also over sandy substrate, whereas A. multispinis and G. brasiliensis selected preferably boulders. The range of 0.65-0.85 m 3 /s was found as the optimum to meet the needs of the three fish species. Our results agree with the necessary objective information to perform grounded management actions in the frame of a management program aiming at ecosystem conservation. Thereby it can be considered a successful pilot study in environmental flow assessment in an Atlantic Forest stream of Brazil.A sub-rotina simulação de habitat físico da metodologia incremental -IFIM usa variáveis hidráulicas e os índices de aptidão das espécies alvo para predizer como diferentes vazões afetam a ocupação de microhabitat por espécies de peixes. Esta abordagem de simulação de hábitat foi adotada para avaliar os efeitos ecológicos sobre três espécies de peixes tropicais de diferentes ordens (Bryconamericus ornaticeps, Ancistrus multispinis e Geophagus brasiliensis) em dois trechos de um riacho de Mata Atlântica do sudeste do Brasil, durante a estação chuvosa de 2013 e a estação seca de 2014. Características topográficas e hidráulicas (profundidade, velocidade e tipo de substrato) foram mensuradas para implementação da simulação de habitat em uma dimensão; observações subaquáticas dos peixes foram realizadas para avaliação do uso do microhabitat. As curvas de aptidão de habitat de cada variável hidráulica foram utilizadas na simulação de habitat para obtenção das curvas de aptidão composta (HSI) e a área útil ponderada (WUA) versus fluxo, e propor vazões ambientais mínimas e ideais para as espécies de peix...

show abstract

“…To better understand the relationship between environmental variables and species occurrence, various SDMs have been developed and used in stream ecology; some notable examples, from previous work, include the generalized linear model (GLM) [10], the generalized additive model (GAM) [10,11], the random forest model (RF) [12,13], the support vector machine (SVM) [12], the Fuzzy model [14,15], the artificial neural network model (ANN) [10,12], and a model based on probabilistic neural networks (PNN) [16]. However, no consensus has been reached on an optimal model that is applicable in all relevant situations and suitable for all species since each SDM has its own unique structure and merit [17].…”

Section: Introductionmentioning

confidence: 99%

Uncertainty in Various Habitat Suitability Models and Its Impact on Habitat Suitability Estimates for Fish

Lin

2015

Water

View full text Add to dashboard Cite

Species distribution models (SDMs) are extensively used to project habitat suitability of species in stream ecological studies. Owing to complex sources of uncertainty, such models may yield projections with varying degrees of uncertainty. To better understand projected spatial distributions and the variability between habitat suitability projections, this study uses five SDMs that are based on the outputs of a two-dimensional hydraulic model to project the suitability of habitats and to evaluate the degree of variability originating from both differing model types and the split-sample procedure. The habitat suitability index (HSI) of each species is based on two stream flow variables, including current velocity (V), water depth (D), as well as the heterogeneity of these flow conditions as quantified by the information entropy of V and D. The six SDM approaches used to project fish abundance, as represented by HSI, included two stochastic models: the generalized linear model (GLM) and the generalized additive model (GAM); as well as three machine learning models: the support vector machine (SVM), random forest (RF) and the artificial neural network (ANN), and an ensemble model (where the latter is the average of the preceding five models). The target species Sicyopterus japonicas was found to prefer habitats with high current velocities. The relationship between mesohabitat diversity and fish abundance was indicated by the trends in information entropy and weighted usable area (WUA) over the study area. This study proposes a method for quantifying habitat suitability, and for assessing the uncertainties in HSI and WUA that are OPEN ACCESSWater 2015, 7 4089 introduced by the various SDMs and samples. This study also demonstrated both the merits of the ensemble modeling approach and the necessity of addressing model uncertainty.

show abstract

Application of Probabilistic Neural Networks to microhabitat suitability modelling for adult brown trout (Salmo trutta L.) in Iberian rivers

Abstract: ElsevierMuñoz Mas, R.; Martinez-Capel, F.; Garófano-Gómez, V.; Mouton, A. (2014)

Cited by 21 publications

References 79 publications

Shallow water benthic imaging and substrate characterization using recreational-grade sidescan-sonar

Shallow water benthic imaging and substrate characterization using recreational-grade sidescan-sonar

Application of the physical habitat simulation for fish species to assess environmental flows in an Atlantic Forest Stream in South-eastern Brazil

Uncertainty in Various Habitat Suitability Models and Its Impact on Habitat Suitability Estimates for Fish

Contact Info

Product

Resources

About