Habitat suitability for marine fishes using presence-only modelling and multibeam sonar

Monk, Jacquomo; Ierodiaconou, Daniel; Versace, Vincent L.; Bellgrove, Alecia; Harvey, Euan S.; Rattray, Alex; Laurenson, L.; Quinn, Gerry P.

doi:10.3354/meps08858

Cited by 76 publications

(81 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent works (MacLeod et al, 2008;Monk et al, 2010) focusing on the marine environment suggested differences between the presence-only models and presence/absence models could be less important. MacLeod et al (2008) suggested that the presenceonly models can perform almost as well as the presence-absence models and Monk et al (2010) encouraged the ongoing use of presence-only approaches.…”

Section: Introductionmentioning

confidence: 97%

“…Comparing both approaches in marine ecosystems is relevant since the use of presence-only models in the marine environment has increased markedly during the last few years (e.g., Bryan & Metaxas, 2007;Galparsoro et al 2009;Monk et al, 2010;Hermosilla et al, 2011;Reiss et al, 2011;Pierrat et al, 2012;Ross & Howell, 2013;Martín-García et al, 2013;García-Alegre et al, in press) although the reasons behind choosing this type of method and the consequences of not including the absences are not always clear (Dorazio, 2012;Monk, 2013;Yackulic et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparing species distribution models: a case study of four deep sea urchin species

et al. 2014

View full text Add to dashboard Cite

There is an increasing demand for biodiversity mapping to address new challenges in the management of marine ecosystems. Species distribution models are a key tool in supplying part of this information. However, the use of these models in the marine environment is still developing and the reasons for the underlying use of different methodological approaches are not always clear. In this work, we compared four different statistical techniques: the ecological niche factor analysis (ENFA), the MAXimun ENTropy algorithm (MAXENT), general additive Models (GAMs), and Random Forest. ENFA and MAXENT were applied using presence-only data whereas GAM and Random Forest used presenceabsence data. As a case study, we used four deep sea urchin species: Centrostephanus longispinus, Coelopleurus floridanus, Stylocidaris affinis, and Cidaris cidaris. The distribution of the studied sea urchins showed strong bathymetric segregation. Depth was the most important variable, followed by reflectivity and slope. The correlations between the predictive outputs of the models were similar between GAM, Random Forest and MAXENT, and lower for ENFA. Models using presence/absence data showed the highest scores in the four species, significantly outperforming ENFA in most of the cases, although differences with MAXENT were significant in only one species.

show abstract

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Comparing species distribution models: a case study of four deep sea urchin species

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Most available predictive applications of ML in marine fish ecology refer mainly to coral reef-associated assemblages in shallow waters (Pittman et al, 2007;Moore et al, 2009;Knudby et al, 2010a;Pittman and Brown, 2011). Such works on demersal fish in other ecosystem types are very scarce (Leathwick et al, 2006a;Monk et al, 2010;Compton et al, 2012;Bergström et al, 2013;Bucas et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Spatial prediction of demersal fish diversity in the Baltic Sea: comparison of machine learning and regression-based techniques

Smoliński

Radtke

2016

ICES Journal of Marine Science

View full text Add to dashboard Cite

Marine spatial planning (MSP) is considered a valuable tool in the ecosystem-based management of marine areas. Predictive modelling may be applied in the MSP framework to obtain spatially explicit information about biodiversity patterns. The growing number of statistical approaches used for this purpose implies the urgent need for comparisons between different predictive techniques. In this study, we evaluated the performance of selected machine learning and regression-based methods that were applied for modelling fish community indices. We hypothesized that habitat features can influence fish assemblage and investigated the effect of environmental gradients on demersal fish diversity (species richness and Shannon-Weaver Index). We used fish data from the Baltic International Trawl Surveys (2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010)(2011)(2012)(2013)(2014) and maps of six potential predictors: bottom salinity, depth, seabed slope, growth season bottom temperature, seabed sediments and annual mean bottom current velocity. We compared the performance of six alternative modelling approaches: generalized linear models, generalized additive models, multivariate adaptive regression splines, support vector machines, boosted regression trees and random forests. We applied repeated 10-fold cross-validation, using accuracy as the measure of model quality. Finally, we selected random forest as the best performing algorithm and implemented it for the spatial prediction of fish diversity from the Baltic Proper to the Kattegat. To obtain information on the data reliability and confidence of the developed models, which are essential for MSP, we estimated the uncertainty of predictions with standard deviation of predictions obtained from all the trees in the ensemble random forest method. We showed how state-of-the-art predictive techniques, based on easily available data and simple Geographic Information System tools, can be used to obtain reliable spatial information about fish diversity. Our comparative work highlighted the potential of machine learning method to reduce prediction error in modelling of demersal fish diversity in the framework of MSP.

show abstract

“…Similarly to empirical field experiments (Lirman 1999, Gratwicke & Speight 2005, species distribution models show that increased fish diversity or abundance can be associated with increased habitat complexity. Examples include the substratum rugosity of reefs (Friedlander & Parrish 1998, Pittman et al 2007, Pittman et al 2009, Monk et al 2010) and biogenic complexity in soft sediments, e.g. rock sole densities relative to worm tube densities and sediment bed-form structure (Stoner et al 2007).…”

Section: Introductionmentioning

confidence: 99%

Ontogenetic habitat associations of a demersal fish species, Pagrus auratus, identified using boosted regression trees

Compton¹,

Morrison²,

Leathwick³

et al. 2012

Mar. Ecol. Prog. Ser.

View full text Add to dashboard Cite

In coastal areas, the identification of habitat types critical to fish life history strategies can provide useful information for ecosystem-based management. Recent studies show that species distribution modelling can be a cost effective tool for describing fish habitat. However, few modelling studies have examined ontogenetic habitat associations. This is critical, as fish species often have different habitat preferences depending on their life stage. In this study, we used boosted regression trees (BRT) to describe ontogenetic habitat associations in snapper Pagrus auratus across the inner Hauraki Gulf of New Zealand. The BRT models identified that juvenile snapper were most frequently associated with slow orbital velocities and slow tidal current speeds, as well as biogenic sedimentary structures (area under the receiver operating curve or AUC, a measure of model performance, 0.79). In contrast, larger snapper were associated with faster tidal currents and faster orbital velocities (AUC 0.78). Juvenile and adult snapper were spatially separated; juvenile snapper occurred in waters close to shore, whereas large snapper occurred mainly in the channels between the islands and the waters around the islands. The successful discrimination of adult and juvenile habitat associations suggests that a modelling approach such as this could be useful for ecosystem-based management.

show abstract

Habitat suitability for marine fishes using presence-only modelling and multibeam sonar

Cited by 76 publications

References 87 publications

Comparing species distribution models: a case study of four deep sea urchin species

Comparing species distribution models: a case study of four deep sea urchin species

Spatial prediction of demersal fish diversity in the Baltic Sea: comparison of machine learning and regression-based techniques

Ontogenetic habitat associations of a demersal fish species, Pagrus auratus, identified using boosted regression trees

Contact Info

Product

Resources

About