Back to Search
Start Over
Tree-based ensembles unveil the microhabitat suitability for the invasive bleak (Alburnus alburnus L.) and pumpkinseed (Lepomis gibbosus L.): Introducing XGBoost to eco-informatics
- Source :
- RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia, instname
- Publication Year :
- 2019
- Publisher :
- Elsevier BV, 2019.
-
Abstract
- [EN] Random Forests (RFs) and Gradient Boosting Machines (GBMs) are popular approaches for habitat suitability modelling in environmental flow assessment. However, both present some limitations theoretically solved by alternative tree-based ensemble techniques (e.g. conditional RFs or oblique RFs). Among them, eXtreme Gradient Boosting machines (XGBoost) has proven to be another promising technique that mixes subroutines developed for RFs and GBMs. To inspect the capabilities of these alternative techniques, RFs and GBMs were compared with: conditional RFs, oblique RFs and XGBoost by modelling, at the micro-scale, the habitat suitability for the invasive bleak (Alburnus alburnus L.) and pumpkinseed (Lepomis gibbosus L). XGBoost outperformed the other approaches, particularly conditional and oblique RFs, although there were no statistical differences with standard RFs and GBMs. The partial dependence plots highlighted the lacustrine origins of pumpkinseed and the preference for lentic habitats of bleak. However, the latter depicted a larger tolerance for rapid microhabitats found in run-type river segments, which is likely to hinder the management of flow regimes to control its invasion. The difference in the computational burden and, especially, the characteristics of datasets on microhabitat use (low data prevalence and high overlapping between categories) led us to conclude that, in the short term, XGBoost is not destined to replace properly optimised RFs and GBMs in the process of habitat suitability modelling at the micro-scale.<br />This project had the support of Fundacion Biodiversidad, of Spanish Ministry for Ecological Transition. We want to thank the volunteering students of the Universitat Politecnica de Valencia, Marina de Miguel, Carlos A. Puig-Mengual, Cristina Barea, Rares Hugianu, and Pau Rodriguez. R. Munoz-Mas benefitted from a postdoctoral Juan de la Cierva fellowship from the Spanish Ministry of Science, Innovation and Universities (ref. FJCI-2016-30829). This research was supported by the Government of Catalonia (ref. 2017 SGR 548).
- Subjects :
- 0106 biological sciences
ZOOLOGIA
Conditional random forests
15.- Proteger, restaurar y promover la utilización sostenible de los ecosistemas terrestres, gestionar de manera sostenible los bosques, combatir la desertificación y detener y revertir la degradación de la tierra, y frenar la pérdida de diversidad biológica
010603 evolutionary biology
01 natural sciences
Lepomis
Gradient boosting machine
Statistics
Tree based
Extreme gradient boosting
SMOTE
TECNOLOGIA DEL MEDIO AMBIENTE
Ecology, Evolution, Behavior and Systematics
Ecology
biology
010604 marine biology & hydrobiology
Applied Mathematics
Ecological Modeling
EXtreme Gradient Boosting machine
Random forests
biology.organism_classification
Alburnus alburnus
Computer Science Applications
Random forest
Environmental flow
Oblique random forests
Computational Theory and Mathematics
Habitat
Modeling and Simulation
Gradient boosting
Subjects
Details
- ISSN :
- 15749541
- Volume :
- 53
- Database :
- OpenAIRE
- Journal :
- Ecological Informatics
- Accession number :
- edsair.doi.dedup.....030d8b2dc581fe1b9d1106947baa837f