Graduation Semester and Year
2020
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Quantitative Biology
Department
Biology
First Advisor
James P Grover
Abstract
The field of species distribution modeling has expanded rapidly over the past two decades along with increasing computing capability and the introduction of novel analytical techniques. SDMs relate species occurrence to environmental data and are a valuable tool in helping researchers understand species-environment relationships and make projections about future distributions. Model reliability has been shown to be highly dependent upon a range of factors, including statistical techniques, predictor variables, species prevalence, and choice metrics used to assess model accuracy. SDMs developed from ensembles of different models have been shown to improve reliability. Here I develop an ensemble modelling approach for freshwater fish using both statistical and algorithmic techniques and a comprehensive, continental scale dataset. I also evaluate the influence of prevalence and model technique on the most used performance metrics. The results of this ensemble model are then combined into a community consensus model, which is used to identify environmental factors that broadly underly freshwater fish distribution across multiple species. The community consensus model also highlights predictors that are important for rare or specialized species. Lastly, I evaluate the ability of the community consensus model to correctly identify species niche predictors through the use of simulated, virtual species. The results of this dissertation indicate that SDM accuracy should be evaluated using several metrics, and that species prevalence should be considered when selecting both model technique and performance metric. A consensus model can perform as well or even better than individual models and can be used to identify environmental predictors that influence freshwater fish as a group. The consensus approach also highlights predictors that are important for rare species. Finally, the results of a carefully developed community consensus modeling approach are consistent with mechanistic knowledge and are not simply “black boxes”.
Keywords
Species distribution model, Machine learning, Prevalence, Freshwater fish, Consensus model, Ensemble model
Disciplines
Biology | Life Sciences
License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Walsh, Melissa Jean, "Ensemble and Consensus Species Distribution Modeling Approaches Applied to Freshwater Fish" (2020). Biology Dissertations. 181.
https://mavmatrix.uta.edu/biology_dissertations/181
Comments
Degree granted by The University of Texas at Arlington