Can multilayer perceptron ensembles model the ecological niche of freshwater fish species?

Muñoz‐Mas, Rafael; Martínez‐Capel, Francisco; Alcaraz‐Hernández, Juan Diego; Mouton, Ans

doi:10.1016/j.ecolmodel.2015.04.025

Cited by 17 publications

(16 citation statements)

References 62 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is suggested that these mechanisms may enhance opportunities for feeding in fine‐sediment dominated rivers that lack the hard substrates generally required for anchoring by filter feeders . Multiple organisms positioned adjacent or in the streamwise direction can exploit mutually generated hydrodynamic conditions, for example, to enhance their feeding rate by concentrating flows, or in the case of fish schooling by exploiting von Kármán trails generated by individuals upstream that can reduce the energy costs of swimming …”

Section: Exploitation Of Turbulent Flow Propertiesmentioning

confidence: 99%

Life in turbulent flows: interactions between hydrodynamics and aquatic organisms in rivers

et al. 2017

View full text Add to dashboard Cite

The turbulent properties of flow in rivers are of fundamental importance to aquatic organisms yet are rarely quantified during routine river habitat assessment surveys or the design of restoration schemes due to their complex nature. In this paper, we review the two-way interactions between aquatic biota and hydrodynamics in rivers, and key methodological approaches used in their quantification, to encourage more explicit consideration of the importance of turbulence in river science and management. We explore recent advances and issues relating to the study of these interactions in the field, laboratory and numerical modeling, the use of artificial and live biota, and different flow measurement technologies. We also review methods for the quantification of ecologically relevant turbulent flow properties, identifying key descriptors of the intensity, periodicity, orientation, and the scale of turbulent flow structures. Our analysis highlights not only the various ways in which plants and animals modify the flow field but also how this can deliver beneficial effects relating to solute exchange, food availability, oxygenation, waste removal, locomotion, and predator-prey interactions. It also demonstrates potential threats to growth and survival relating to turbulence, including injury, dislodgement, increased energy expenditure, mortality, and complex influences on predators and prey. We conclude by identifying some remaining barriers to the integration of turbulence into the science and practice of river assessment and restoration but also opportunities in the form of controlled laboratory experimentation, increasingly sophisticated flow sensors and imaging technologies, and numerical simulation of turbulence that could advance understanding in this complex field of research.There is considerable diversity in the research approaches applied to the study of interactions FIGURE 1 | Definition of Reynolds number and laminar and turbulent flow, with example Reynolds numbers for different types of organisms interacting with the flow. Advanced Reviewwires.wiley.com/water

show abstract

Section: Exploitation Of Turbulent Flow Propertiesmentioning

confidence: 99%

Life in turbulent flows: interactions between hydrodynamics and aquatic organisms in rivers

et al. 2017

View full text Add to dashboard Cite

show abstract

“…However, the main difficulty in addressing process-based models is the definition of the key physical and biological processes and the subsequent parameterization of these processes, which require a good understanding and monitoring of the studied system and adequately designed in situ and ex situ experiments (Ye et al, 2013). In this regard, statistical or data-driven mathematical models have been shown to be supportive tools to overtake the sizable requirements of process-based models (Muñoz-Mas, Lopez-Nicolas, Martínez-Capel, & Pulido-Velazquez, 2016) and to explore species' ecological requirements (Muñoz-Mas, Martínez-Capel, Alcaraz-Hernández, & Mouton, 2015). In this sense, statistical models have already proficiently complemented field and laboratory experiments (Fraaije et al, 2015;Glenz, Iorgulescu, Kienast, & Schlaepfer, 2008) as well as process-based vegetation models (Benjankar et al, 2014).…”

mentioning

confidence: 99%

Exploring the key drivers of riparian woodland successional pathways across three European river reaches

et al. 2017

Self Cite

View full text Add to dashboard Cite

International audienceClimate change and river regulation are negatively impacting riparian vegetation. To evaluate these impacts, process‐based models are preferred over data‐driven approaches. However, they require extensive knowledge about ecohydrological processes. To facilitate the implementation of such process‐based models, the key drivers of riparian woodland successional pathways across three river reaches, in Austria, Portugal, and Spain, were explored, employing two complementary approaches. The principal component analyses highlighted the importance of the physical gradients determining the placement of the succession phases within the riparian and floodplain zones. The generalized additive models revealed that the initial and pioneer succession phases, characteristic of the colonization stage, appeared in areas highly morphodynamic, close in height and distance to the water table, and with coarse substrate, whereas elder phases within the transitional and mature stages showed incremental differences, occupying less dynamic areas with finer substrate. The Austrian site fitted well the current successional theory (elder phases appearing sequentially further up and distant), but at the Portuguese site, the tolerance of the riparian species to drought and flash flood events governed their placement. Finally, at the Spanish site, the patchy distribution of the elder phases was the remnants of formative events that reshaped the river channel. These results highlight the complex relationships between flow regime, channel morphology, and riparian vegetation. The use of succession phases, which rely on the sequential evolution of riparian vegetation as a response to different drivers, may be potentially better reproducible, within numerical process‐based models, and transferable to other geographical regions

show abstract

“…Lambert, 1992;Liu & Chan, 2010) or ANN ensembles (e.g. Muñoz-Mas et al, 2015). Additionally, it was not possible to establish a clear relationship between the input variables and species density from PaD analysis (Fig.…”

Section: Discussionmentioning

confidence: 99%

Modelling critical factors affecting the distribution of the vulnerable endemic Eastern Iberian barbel (Luciobarbus guiraonis) in Mediterranean rivers

et al. 2015

Self Cite

View full text Add to dashboard Cite

Luciobarbus guiraonis (Eastern Iberian barbel) is an endemic fish species restricted to Spain, mainly distributed in the Júcar River Basin District. Its study is important because there is little knowledge about its biology and ecology. To improve the knowledge about the species distribution and habitat requirements, nonlinear modelling was carried out to predict the presence/absence and density of the Eastern Iberian barbel, based on 155 sampling sites distributed throughout the Júcar River Basin District (Eastern Iberian Peninsula). We used multilayer feed-forward artificial neural networks (ANN) to represent nonlinear relationships between L. guiraonis descriptors and variables regarding the physical habitat and biological components (macroinvertebrates, fish, riparian forest). The gradient descent algorithm was implemented to find the optimal model parameters; the importance of the ANN’s input variables was determined by the partial derivatives method. The predictive power of the model was evaluated with the Cohen’s kappa (k), the correctly classified instances (CCI), and the area under the curve (AUC) of the receiver operator characteristic (ROC) plots. The best model predicted presence/absence with a high performance (k= 0.66, CCI= 87% and AUC= 0.85); the prediction of density was moderate (CCI = 62%, AUC=0.71 and k= 0.43). The fundamental variables describing the presence/absence were; solar radiation (the highest contribution was observed between 2000 and 4200 WH/m2), drainage area (with the strongest influence between 3000 and 5.000 km2), and the proportion of exotic fish species (with relevant contribution between 50 and 100%). In the density model, the most important variables were the coefficient of variation of mean annual flows (relative importance of 50.5%) and the proportion of exotic fish species (24.4%). The models provide important information about the relation of L. guiraonis with biotic and abiotic variables, this new knowledge can help develop future studies and management plans for the conservation of this species in the Júcar River Basin District and, potentially, for the conservation of other endemic fish species of Barbus and Luciobarbus in Mediterranean rivers.

show abstract

Can multilayer perceptron ensembles model the ecological niche of freshwater fish species?

Cited by 17 publications

References 62 publications

Life in turbulent flows: interactions between hydrodynamics and aquatic organisms in rivers

Life in turbulent flows: interactions between hydrodynamics and aquatic organisms in rivers

Exploring the key drivers of riparian woodland successional pathways across three European river reaches

Modelling critical factors affecting the distribution of the vulnerable endemic Eastern Iberian barbel (Luciobarbus guiraonis) in Mediterranean rivers

Contact Info

Product

Resources

About