The use of the GARP genetic algorithm and Internet grid computing in the Lifemapper world atlas of species biodiversity

Abstract

Lifemapper (http://www.lifemapper.org) is a predictive electronic atlas of the Earth's biological biodiversity. Using a screensaver version of the GARP genetic algorithm for modeling species distributions, Lifemapper harnesses vast computing resources through 'volunteers' PCs similar to SETI@home, to develop models of the distribution of the worlds fauna and flora. The Lifemapper project's primary goal is to provide an up to date and comprehensive database of species maps and prediction models (i.e. a fauna and flora of the world) using available data on species' locations. The models are developed using specimen data from distributed museum collections and an archive of geospatial environmental correlates. A central server maintains a dynamic archive of species maps and models for research, outreach to the general community, and feedback to museum data providers. This * Corresponding author

Predicting potential distribution of Tibetan spruce (Picea smithiana) in Qomolangma (Mount Everest) National Nature Preserve using maximum entropy niche-based model

“…A high value of the function indicates that the grid cell is predicted to have suitable conditions for that species (Phillips et al, 2005). Compared with other existing models, such as the bioclimatic prediction system (BIOCLIM) (Beaumont et al, 2005), domain model (DOMAIN) (Carpenter et al, 1993), genetic algorithm for rule-set prediction modeling system (GARP) (Stockwell et al, 2006;SanchezFlores, 2007) and multivariate adaptive regression splines (MARS) (Elith et al, 2006), Maxent has a number of features that make it very useful for modeling species distribution (Vidal-Garcia and Serio-Silva, 2010), including a deterministic frame work, hence, stability as well as the ability to run with presence-only point occurrences; high performance with few point localities; better computing efficiency enabling the use of large-scale high-resolution data layers; continuous output from least to most suitable conditions; and an ability to model complex responses to environmental variables (Phillips et al, 2005).…”

Assessment of climatically suitable area for Syrmaticus reevesii under climate change

“…Biotic factors are generally not included (Soberón & Nakamura 2009); instead, climatic variables are typically the environmental data used in ENMs to model species' climatic niches (Broennimann et al 2007), which represent the species' climatic requirements, and find climatically suitable areas (CSAs) in geographic space (Lee et al 2012). Several ENM algorithms that use machine learning and multivariate statistics have been developed, such as Maximum Entropy (Maxent; Phillips et al 2004), Ecological Niche Factor Analysis (ENFA; Hirzel et al 2001), and Genetic Algorithm for Ruleset Prediction (GARP; Stockwell et al 2006). Maxent is regarded as consistently competitive with the best performing methods (Elith et al 2006, Phillips & Dudik 2008).…”

Aplicación de algoritmos genéticos en problemas de Ingeniería

“…Otro ejemplo de predicción es la obtención de modelos para determinar la distribución de especies biológicas (flora y fauna) de una determinada región (Stockwell et al, 2008) a través de información suministrada en Internet. Los datos de las especies fueron obtenidos a partir de una red de información suministrada por los museos de todo el mundo.…”