Species distribution modeling with scalability: The case study of P-GARP, a parallel genetic algorithm for rule-set production

Fabiana Santana, César Alberto Bravo Pariente, Antonio Mauro Saraiva

Research output: A Conference proceeding or a Chapter in BookConference contribution

1 Citation (Scopus)

Abstract

Species distribution modeling (SDM) calculates a species' probabilistic distribution by combining Environmental raster layers with species datasets. Such models can help to answer complex questions in Ecology/Biology/Health, e.g., by calculating impacts of climate changes in Biodiversity, or the potential for a disease spread (vectors' modeling). Machine learning is largely applied in SDM, being the Genetic Algorithm for Rule-set Production (GARP) one of the most reliable solutions. However, GARP's convergence needs to speedup under certain conditions (high resolution or number of layers), for which this paper proposes P-GARP, a parallel, scalable implementation of GARP. P-GARP was implemented onto a SGI Altix XE 1300 cluster with 2 quad-core processors/node. Preliminary results show an expressive 3.2/node speedup. Premature convergence is not observed in PGARP and its accuracy is very similar to GARP´s. Effective solutions to improve this speedup in even larger scale are proposed, along with a discussion about P-GARP correctness and efficiency.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017
Place of PublicationSan Diego, US
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages162-170
Number of pages9
Volume2017-January
ISBN (Electronic)9781538615621
ISBN (Print)9781538615638
DOIs
Publication statusPublished - 4 Aug 2017
Event18th IEEE International Conference on Information Reuse and Integration, IRI 2017 - San Diego, United States
Duration: 4 Aug 20176 Aug 2017

Publication series

NameProceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017
Volume2017-January

Conference

Conference18th IEEE International Conference on Information Reuse and Integration, IRI 2017
CountryUnited States
CitySan Diego
Period4/08/176/08/17

Fingerprint

Set theory
Parallel algorithms
Scalability
Genetic algorithms
Biodiversity
Ecology
Climate change
Learning systems
Genetic algorithm
Modeling
Health
Node

Cite this

Santana, F., Bravo Pariente, C. A., & Saraiva, A. M. (2017). Species distribution modeling with scalability: The case study of P-GARP, a parallel genetic algorithm for rule-set production. In Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017 (Vol. 2017-January, pp. 162-170). [8102933] (Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017; Vol. 2017-January). San Diego, US: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IRI.2017.93
Santana, Fabiana ; Bravo Pariente, César Alberto ; Saraiva, Antonio Mauro. / Species distribution modeling with scalability: The case study of P-GARP, a parallel genetic algorithm for rule-set production. Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017. Vol. 2017-January San Diego, US : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 162-170 (Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017).
@inproceedings{75e7d4a24a3648558c34b6fa585edf2b,
title = "Species distribution modeling with scalability: The case study of P-GARP, a parallel genetic algorithm for rule-set production",
abstract = "Species distribution modeling (SDM) calculates a species' probabilistic distribution by combining Environmental raster layers with species datasets. Such models can help to answer complex questions in Ecology/Biology/Health, e.g., by calculating impacts of climate changes in Biodiversity, or the potential for a disease spread (vectors' modeling). Machine learning is largely applied in SDM, being the Genetic Algorithm for Rule-set Production (GARP) one of the most reliable solutions. However, GARP's convergence needs to speedup under certain conditions (high resolution or number of layers), for which this paper proposes P-GARP, a parallel, scalable implementation of GARP. P-GARP was implemented onto a SGI Altix XE 1300 cluster with 2 quad-core processors/node. Preliminary results show an expressive 3.2/node speedup. Premature convergence is not observed in PGARP and its accuracy is very similar to GARP´s. Effective solutions to improve this speedup in even larger scale are proposed, along with a discussion about P-GARP correctness and efficiency.",
keywords = "Ecological niche modeling, GARP, Genetic algorithms, Parallel algorithms, PGARP, Species distribution modeling",
author = "Fabiana Santana and {Bravo Pariente}, {C{\'e}sar Alberto} and Saraiva, {Antonio Mauro}",
year = "2017",
month = "8",
day = "4",
doi = "10.1109/IRI.2017.93",
language = "English",
isbn = "9781538615638",
volume = "2017-January",
series = "Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "162--170",
booktitle = "Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017",
address = "United States",

}

Santana, F, Bravo Pariente, CA & Saraiva, AM 2017, Species distribution modeling with scalability: The case study of P-GARP, a parallel genetic algorithm for rule-set production. in Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017. vol. 2017-January, 8102933, Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017, vol. 2017-January, IEEE, Institute of Electrical and Electronics Engineers, San Diego, US, pp. 162-170, 18th IEEE International Conference on Information Reuse and Integration, IRI 2017, San Diego, United States, 4/08/17. https://doi.org/10.1109/IRI.2017.93

Species distribution modeling with scalability: The case study of P-GARP, a parallel genetic algorithm for rule-set production. / Santana, Fabiana; Bravo Pariente, César Alberto; Saraiva, Antonio Mauro.

Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017. Vol. 2017-January San Diego, US : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 162-170 8102933 (Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017; Vol. 2017-January).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Species distribution modeling with scalability: The case study of P-GARP, a parallel genetic algorithm for rule-set production

AU - Santana, Fabiana

AU - Bravo Pariente, César Alberto

AU - Saraiva, Antonio Mauro

PY - 2017/8/4

Y1 - 2017/8/4

N2 - Species distribution modeling (SDM) calculates a species' probabilistic distribution by combining Environmental raster layers with species datasets. Such models can help to answer complex questions in Ecology/Biology/Health, e.g., by calculating impacts of climate changes in Biodiversity, or the potential for a disease spread (vectors' modeling). Machine learning is largely applied in SDM, being the Genetic Algorithm for Rule-set Production (GARP) one of the most reliable solutions. However, GARP's convergence needs to speedup under certain conditions (high resolution or number of layers), for which this paper proposes P-GARP, a parallel, scalable implementation of GARP. P-GARP was implemented onto a SGI Altix XE 1300 cluster with 2 quad-core processors/node. Preliminary results show an expressive 3.2/node speedup. Premature convergence is not observed in PGARP and its accuracy is very similar to GARP´s. Effective solutions to improve this speedup in even larger scale are proposed, along with a discussion about P-GARP correctness and efficiency.

AB - Species distribution modeling (SDM) calculates a species' probabilistic distribution by combining Environmental raster layers with species datasets. Such models can help to answer complex questions in Ecology/Biology/Health, e.g., by calculating impacts of climate changes in Biodiversity, or the potential for a disease spread (vectors' modeling). Machine learning is largely applied in SDM, being the Genetic Algorithm for Rule-set Production (GARP) one of the most reliable solutions. However, GARP's convergence needs to speedup under certain conditions (high resolution or number of layers), for which this paper proposes P-GARP, a parallel, scalable implementation of GARP. P-GARP was implemented onto a SGI Altix XE 1300 cluster with 2 quad-core processors/node. Preliminary results show an expressive 3.2/node speedup. Premature convergence is not observed in PGARP and its accuracy is very similar to GARP´s. Effective solutions to improve this speedup in even larger scale are proposed, along with a discussion about P-GARP correctness and efficiency.

KW - Ecological niche modeling

KW - GARP

KW - Genetic algorithms

KW - Parallel algorithms

KW - PGARP

KW - Species distribution modeling

UR - http://www.scopus.com/inward/record.url?scp=85044212324&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/species-distribution-modeling-scalability-case-study-pgarp-parallel-genetic-algorithm-ruleset-produc

U2 - 10.1109/IRI.2017.93

DO - 10.1109/IRI.2017.93

M3 - Conference contribution

SN - 9781538615638

VL - 2017-January

T3 - Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017

SP - 162

EP - 170

BT - Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - San Diego, US

ER -

Santana F, Bravo Pariente CA, Saraiva AM. Species distribution modeling with scalability: The case study of P-GARP, a parallel genetic algorithm for rule-set production. In Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017. Vol. 2017-January. San Diego, US: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 162-170. 8102933. (Proceedings - 2017 IEEE International Conference on Information Reuse and Integration, IRI 2017). https://doi.org/10.1109/IRI.2017.93