Improving species distribution model quality with a parallel linear genetic programming-fuzzy algorithm.

Created by W.Langdon from gp-bibliography.bib Revision:1.3949

@PhdThesis{MichelJanMarinusBieleveldCorr16,
  author =       "Michel Jan Marinus Bieleveld",
  title =        "Improving species distribution model quality with a
                 parallel linear genetic programming-fuzzy algorithm.",
  titletranslation = "Melhorar a qualidade de modelo de distribui{\c
                 c}{\~a}o das esp{\'e}cies com um algoritmo paralelo de
                 programa{\c c}{\~a}o linear gen{\'e}tico-fuzzy.",
  school =       "Computer Engineering, Escola Politecnica",
  year =         "2016",
  type =         "Tese de Doutorado",
  address =      "Brazil",
  month =        "9 " # sep,
  keywords =     "genetic algorithms, genetic programming, applied and
                 specific algorithms, bioclimatologia, ecological niche
                 models, fuzzy logic, species distribution modelling",
  bibsource =    "OAI-PMH server at www.teses.usp.br",
  contributor =  "Antonio Mauro Saraiva",
  language =     "en",
  oai =          "oai:teses.usp.br:tde-26012017-113329",
  rights =       "Liberar o conte{\'u}do para acesso p{\'u}blico.",
  URL =          "http://www.teses.usp.br/teses/disponiveis/3/3141/tde-26012017-113329/",
  URL =          "http://www.teses.usp.br/teses/disponiveis/3/3141/tde-26012017-113329/en.php",
  URL =          "http://www.teses.usp.br/teses/disponiveis/3/3141/tde-26012017-113329/publico/MichelJanMarinusBieleveldCorr16.pdf",
  publisher =    "Biblioteca Digitais de Teses e Disserta{\c c}{\~o}es
                 da USP",
  size =         "142 pages",
  abstract =     "Biodiversity, the variety of life on the planet, is
                 declining due to climate change, population and species
                 interactions and as the result f demographic and
                 landscape dynamics. Integrated model-based assessments
                 play a key role in understanding and exploring these
                 complex dynamics and have proven use in conservation
                 planning. Model-based assessments using Species
                 Distribution Models constitute an efficient means of
                 translating limited point data to distribution
                 probability maps for current and future scenarios in
                 support of conservation decision making. The aims of
                 this doctoral study were to investigate; (1) the use of
                 a hybrid genetic programming to build high quality
                 models that handle noisy real-world presence and
                 absence data, (2) the extension of this solution to
                 exploit the parallelism inherent to genetic programming
                 for fast scenario based decision making tasks, and (3)
                 a conceptual framework to share models in the hope of
                 enabling research synthesis. Subsequent to this, the
                 quality of the method, evaluated with the true skill
                 statistic, was examined with two case studies. The
                 first with a dataset obtained by defining a virtual
                 species, and the second with data extracted from the
                 North American Breeding Bird Survey relating to
                 mourning dove (Zenaida macroura). In these studies, the
                 produced models effectively predicted the species
                 distribution up to 30percent of error rate both
                 presence and absence samples. The parallel
                 implementation based on a twenty-node c3.xlarge Amazon
                 EC2 StarCluster showed a linear speedup due to the
                 multiple-deme coarse-grained design. The hybrid fuzzy
                 genetic programming algorithm generated under certain
                 consitions during the case studies significantly better
                 transferable models.",
  abstract =     "Biodiversidade, a variedade de vida no planeta,
                 est{\'a} em decl{\'i}nio {\`a}s altera{\c c}{\~o}es
                 clim{\'a}ticas, mudan{\c c}as nas intera{\c c}{\~o}es
                 das popula{\c c}{\~o}es e esp{\'e}cies, bem como nas
                 altera{\c c}{\~o}es demogr{\'a}ficas e na din{\^a}mica
                 de paisagens. Avalia{\c c}{\~o}es integradas baseadas
                 em modelo desempenham um papel fundamental na
                 compreens{\~a}o e na explora{\c c}{\~a}o destas
                 din{\^a}micas complexas e tem o seu uso comprovado no
                 planejamento de conserva{\c c}{\~a}o da biodiversidade.
                 Os objetivos deste estudo de doutorado foram
                 investigar; (1) o uso de t{\'e}cnicas de programa{\c
                 c}{\~a}o gen{\'e}tica e fuzzy para construir modelos de
                 alta qualidade que lida com presen{\c c}a e
                 aus{\^e}ncia de dados ruidosos do mundo real, (2) a
                 extens{\~a}o desta solu{\c c}{\~a}o para explorar o
                 paralelismo inerente {\`a} programa{\c c}{\~a}o
                 gen{\'e}tica para acelerar tomadas de decis{\~a}o e (3)
                 um framework conceitual para compartilhar modelos, na
                 expectativa de permitir a s{\'i}ntese de pesquisa.
                 Subsequentemente, a qualidade do m{\'e}todo, avaliada
                 com a true skill statistic, foi examinado com dois
                 estudos de caso. O primeiro utilizou um conjunto de
                 dados fict{\'i}cios obtidos a partir da defini{\c
                 c}{\~a}o de uma esp{\'e}cie virtual, e o segundo
                 utilizou dados de uma esp{\'e}cie de pomba (Zenaida
                 macroura) obtidos do North American Breeding Bird
                 Survey. Nestes estudos, os modelos foram capazes de
                 predizer a distribui{\c c}{\~a}o das esp{\'e}cies
                 maneira correta mesmo utilizando bases de dados com
                 at{\'e} 30percent de erros nas amostras de presen{\c
                 c}a e de aus{\^e}ncia. A implementa{\c c}{\~a}o
                 paralela utilizando um cluster de vinte n{\'o}s
                 c3.xlarge Amazon EC2 StarCluster, mostrou uma
                 acelera{\c c}{\~a}o linear devido ao arquitetura de
                 m{\'u}ltiplos deme de granula{\c c}{\~a}o grossa. O
                 algoritmo de programa{\c c}{\~a}o gen{\'e}tica e fuzzy
                 gerada em determinadas condi{\c c}{\~o}es durante os
                 estudos de caso, foram significativamente melhores na
                 transfer{\^e}ncia do que os algoritmos do BIOMOD.",
}

Genetic Programming entries for Michel Jan Marinus Bieleveld

Citations