Random subset feature selection for ecological niche models of wildfire activity in Western North America
| Autor: | J. Tomasz Giermakowski, A. Michelle Lawing, Antonio Trabucco, Gail M. Drus, Maria D. Tchakerian, Robert N. Coulson, James L. Tracy |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0106 biological sciences
Ecological niche 010504 meteorology & atmospheric sciences Computer science business.industry Ecological Modeling Niche Feature selection Future climate Machine learning computer.software_genre 010603 evolutionary biology 01 natural sciences Variable (computer science) Feature (computer vision) Artificial intelligence business computer 0105 earth and related environmental sciences |
| Zdroj: | Ecological Modelling. 383:52-68 |
| ISSN: | 0304-3800 |
| DOI: | 10.1016/j.ecolmodel.2018.05.019 |
| Popis: | Variable selection in ecological niche modelling can influence model projections to a degree comparable to variations in future climate scenarios. Consequently, it is important to select feature (variable) subsets for optimizing model performance and characterizing variability. We utilize a novel random subset feature selection algorithm (RSFSA) for niche modelling to select an ensemble of optimally sized feature subsets of limited correlation (|r |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect