scholarly journals Application of species distribution models to explain and predict the distribution, abundance and assemblage structure of nearshore temperate reef fishes

2015 ◽  
Vol 21 (12) ◽  
pp. 1428-1440 ◽  
Author(s):  
Mary Young ◽  
Mark H. Carr
Keyword(s):  
Species Distribution ◽  
Species Distribution Models ◽  
Reef Fishes ◽  
Assemblage Structure ◽  
Distribution Models ◽  
Temperate Reef

scholarly journals Conservation biogeography of lotic fishes in the Missouri and Colorado River basins

2019 ◽  
Author(s):  
◽  
Landon Lee Pierce
Keyword(s):  
Species Distribution ◽  
Fish Assemblage ◽  
Native Species ◽  
Species Distribution Models ◽  
Colorado River ◽  
River Basins ◽  
Assemblage Structure ◽  
Native Fish ◽  
Fish Assemblage Structure ◽  
Distribution Models

To improve our understanding of lotic fish ecology and improve conservation efforts, I 1) identified potentially ecologically important tributaries (PEITs) and evaluated their effects on fish assemble structure, 2) evaluated factors affecting spatial transferability of species distribution models (SDMs), and 3) evaluated the drivers of non-native fish establishment in the Missouri and Colorado River basins (MRB and CRB). The effects of PEIT likely vary among rivers as all Missouri River PEITs affected fish assemblage structure, but only half of upper Colorado River basin PEITs affected fish assemblage structure. Species distribution models transferred from the MRB to the CRB for 15 of 25 species, but transferability was not predictable based on species characteristics, re-enforcing the hypothesis that transferability is species-and contextspecific. Support for Human Activity, Biotic Resistance and Biotic Acceptance hypotheses as the drivers of non-native fish establishment varied by family, but these hypotheses rarely explained significant variability in the probability of non-native Salmonidae, Catostomidae, and Cyprinidae occurrence. These results may suggest that other factors (e.g., natural factors) drive non-native species distributions at the spatial (i.e., grain-stream segment; extents-physiographic divisions, and MRB and CRB combined) and taxonomic (i.e., family) scales considered in this study. This study aids conservations efforts by providing an efficient approach for identifying ecologically important tributaries and improving predictions of non-native species establishment.

scholarly journals Incorporating reef fish avoidance behavior improves accuracy of species distribution models

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e9246
Author(s):  
Kostantinos A. Stamoulis ◽  
Jade M.S. Delevaux ◽  
Ivor D. Williams ◽  
Alan M. Friedlander ◽  
Jake Reichard ◽  
...  
Keyword(s):  
Reef Fish ◽  
Species Distribution ◽  
Avoidance Behavior ◽  
Species Distribution Models ◽  
Fish Assemblages ◽  
Reef Fishes ◽  
Distribution Models ◽  
Approach Distance ◽  
Fish Avoidance ◽  
Habitat Variables

Species distribution models (SDMs) are used to interpret and map fish distributions based on habitat variables and other drivers. Reef fish avoidance behavior has been shown to vary in the presence of divers and is primarily driven by spearfishing pressure. Diver avoidance behavior or fish wariness may spatially influence counts and other descriptive measures of fish assemblages. Because fish assemblage metrics are response variables for SDMs, measures of fish wariness may be useful as predictors in SDMs of fishes targeted by spearfishing. We used a diver operated stereo-video system to conduct fish surveys and record minimum approach distance (MAD) of targeted reef fishes inside and outside of two marine reserves on the island of Oʻahu in the main Hawaiian Islands. By comparing MAD between sites and management types we tested the assumption that it provides a proxy for fish wariness related to spearfishing pressure. We then compared the accuracy of SDMs which included MAD as a predictor with SDMs that did not. Individual measures of MAD differed between sites though not management types. When included as a predictor, MAD averaged at the transect level greatly improved the accuracy of SDMs of targeted fish biomass.

scholarly journals A Robust Prediction Model for Species Distribution Using Bagging Ensembles with Deep Neural Networks

2021 ◽  
Vol 13 (8) ◽  
pp. 1495
Author(s):  
Jehyeok Rew ◽  
Yongjang Cho ◽  
Eenjun Hwang
Keyword(s):  
Neural Networks ◽  
Species Distribution ◽  
Best Practice ◽  
Deep Neural Networks ◽  
Species Distribution Models ◽  
Species Distribution Model ◽  
Environmental Data ◽  
Distribution Model ◽  
Distribution Models ◽  
Robust Prediction

Species distribution models have been used for various purposes, such as conserving species, discovering potential habitats, and obtaining evolutionary insights by predicting species occurrence. Many statistical and machine-learning-based approaches have been proposed to construct effective species distribution models, but with limited success due to spatial biases in presences and imbalanced presence-absences. We propose a novel species distribution model to address these problems based on bootstrap aggregating (bagging) ensembles of deep neural networks (DNNs). We first generate bootstraps considering presence-absence data on spatial balance to alleviate the bias problem. Then we construct DNNs using environmental data from presence and absence locations, and finally combine these into an ensemble model using three voting methods to improve prediction accuracy. Extensive experiments verified the proposed model’s effectiveness for species in South Korea using crowdsourced observations that have spatial biases. The proposed model achieved more accurate and robust prediction results than the current best practice models.

Sign in / Sign up

Export Citation Format

Share Document