Analysis of algorithms for building a joint model for modeling Amazonian species
DOI:
https://doi.org/10.5902/1980509886428Keywords:
Consensus model for modeling, Ecological niche, Potential species distribution, Forest species, Climate changeAbstract
In order to monitor biodiversity changes in relation to climate change, different ecological niche models (ENMs) are employed. The selection of the most suitable model for a species may be constrained by various factors, such as data availability and resolution. The objective of the study was to analyze 13 algorithms and determine a consensus model to simulate the potential distribution of five deforestation-targeted species in the Amazon: Aspidosperma desmanthum, Cariniana micranta, Clarisia racemosa, Couratari oblongifolia, and Vouchysia guianensis. To construct the ENMs, bioclimatic and soil variables were used. The information for each species was individually modeled using the 13 algorithms, and subsequently, the average of each algorithm for all species was calculated. The performance was assessed based on metrics such as Area Under the Curve, True Skill Statistics, and Sorensen Index. Based on the results, it was observed that there is no ideal algorithm for all species. Therefore, a consensus model was proposed using the Random Forest, Boosted Regression Trees, Support Vector Machine, Bayesian Gaussian Process, and Maximum Entropy Default algorithms, as they demonstrated better performance on average. It is concluded that it is important to consider the specific characteristics of each species and the individuality of the dataset.
Downloads
References
ALLOUCHE, O.; TSOAR, A.; STEINITZ, O.; ROTEM, D.; KADMON, R. A comparative evaluation of presence-only methods for modelling species distribution. Diversity and Distributions, v. 13, pp. 397-405, 2007. DOI: 10.1111/j.1472-4642.2007.00346.x. DOI: https://doi.org/10.1111/j.1472-4642.2007.00346.x
AMIRI, M.; POURGHASEMI, H. R.; GHANBARIAN, G. A.; AFZALI, S. F. Assessment of the importance of gully erosion effective factors using Boruta algorithm and its spatial modeling and mapping using three machine learning algorithms. Geoderma, v. 340, pp. 55-69, 2019. DOI: 10.1016/j.geoderma.2018.12.042. DOI: https://doi.org/10.1016/j.geoderma.2018.12.042
ANDRADE, A. F. A.; VELAZCO, S. J. E.; MARCO JÚNIOR, P. D. ENMTLM: An R package for a straightforward construction of complex ecological niche models. Environmental Modelling & Software, v. 125, p. 104615, 2020. DOI: 10.1016/j.envsoft.2019.104615. DOI: https://doi.org/10.1016/j.envsoft.2019.104615
CRIA - Centro de Referência e Informação Ambiental. Specieslink - simple search, 2023. Available in: https://specieslink.net/search/. Accessed in: 2 April 2023.
ELITH, J.; GRAHAM, C. H.; ANDERSON, R. P.; DURÍK, M.; FERRIER, S.; GUISAN, A.; HIJMANS, R.; HUETTMANN, F.; LEATHWICK, J. R.; LEHMANN, A.; LI, J.; LOHMANN, L. G.; LOISELLE, B. A.; MANION, G.; MORIZ, C.; NAKAMURA, M.; NAKAZAWA, Y.; OVERTON, J. M.C.,; TOWNSEND, P.; PHILLIPS, S.; RICHARDSON, K.; SCACHETTI-PEREIRA, R.; SCHAPIRE, R. E.; SOBERÓN, J.; WILLIAM, S.; WISZ, M. S.; NIKLAUS, E. Z. Novel methods improve prediction of species distributions from occurrence data. Ecography, v. 29, pp. 129-151, 2006. DOI: 10.1111/j.2006.0906- 7590.04596.x. DOI: https://doi.org/10.1111/j.2006.0906-7590.04596.x
ELITH, J.; LEATHWICK, J. R.; HASTIE, T. A working guide to boosted regression trees. Journal of Animal Ecology, v. 77, pp. 802-813, 2008. DOI: 10.1111/j.1365-2656.2008.01390.x. DOI: https://doi.org/10.1111/j.1365-2656.2008.01390.x
ESTEVO, C. A.; NAGY-REIS, M. B.; NICHOLS, J. D. When habitat matters: Habitat preferences can modulate co-occurrence patterns of similar sympatric species. Plos One, v. 12, 2017. DOI: 10.1371/journal.pone.0179489. DOI: https://doi.org/10.1371/journal.pone.0179489
FAO; IIASA. Harmonized World Soil Database Version 2.0. Rome and Laxenburg. 2023. 69 p. Available in: https://www.fao.org/documents/card/en/c/cc3823en. Accessed: 30 Mar. 2023.
FICK, S. E.; HIJMANS, R. J. WordClim 2: new 1-km spatial resolution climate surfaces for global land areas. International Journal of Climatology, v. 37, n. 12, pp. 4302-4315, 2017. DOI: 10.1002/joc.5086. DOI: https://doi.org/10.1002/joc.5086
FIELDING, A. H.; BELL, J. F. A Review of Methods for the Assessment of Prediction Errors in Conservation Presence/Absence Models. Environmental Conservation, v. 24, pp. 38-49, 1997. DOI: 10.1017/S0376892997000088. DOI: https://doi.org/10.1017/S0376892997000088
FIRPO, M. A. F.; GUIMARÃES, B. S.; DANTAS, L. G.; DA SILVA, M. G. B.; ALVEZ, L. M.; CHADWICK, R.; LLOPART, M. P.; DE OLIVEIRA, G. S. Assessment of CPIP6 models performance in simulating present day climate in Brazil. Frontiers in Climate, v. 4, 2022. DOI: 10.3389/fclim.2022.948499. DOI: https://doi.org/10.3389/fclim.2022.948499
FOIS, M.; FENU, G.; LOMBRAÑA, A. C.; COGONI, D.; BACCHETTA, G. A practical method to speed up the discovery of unknown populations using Species Distribution Models. Journal for Nature Conservation, v. 24, pp. 42-48, 2015. DOI: 10.1016/j.jnc.2015.02.001. DOI: https://doi.org/10.1016/j.jnc.2015.02.001
GBIF. The Global Biodiversity Information Facility, 2023. Available in: https://www.gbif.org/pt/occurrence/search. Accessed in: April 05, 2023.
GOLDING, N.; PURSE, B. V. Fast and flexible Baysian species distribution modelling usind Gaussian processes. Methods in Ecology and Evolution, v. 7, pp. 598-608, 2016. DOI: doi.org/10.1111/2041-210X.12523. DOI: https://doi.org/10.1111/2041-210X.12523
GUO, Y.; LI, X.; ZHAO, Z.; NAWAZ, Z. Predicting the impacts of climate change, soils and vegetation types on the geographic distribution of Polyporus umbellatus in China. Science of the total environment, v. 648, p. 1-11, 2019. DOI: 10.1016/j.scitotenv.2018.07.465. DOI: https://doi.org/10.1016/j.scitotenv.2018.07.465
INGRAM, M.; VUKCEVIC, F.; GOLDING, N. Multi-output Gaussian processes for species distribution modelling. Methods in Ecology and Evolution, v. 11, pp. 1587-1598, 2020. DOI: 10.1111/2041-210X.13496. DOI: https://doi.org/10.1111/2041-210X.13496
KONOWALIK, K., NOSOL, A. Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage. Sci Rep, v. 11, 2021. DOI: 10.1038/s41598-020-80062-1. DOI: https://doi.org/10.1038/s41598-020-80062-1
LANDA, M. L. N.; CASTRO, J. C. M.; MONTERRUBIO-RICO, T. C.; LARA-CABRERA, S. I.; PIETRO-TORRES, D. A. Predicting co-distribution patterns of parrots and woody plants under global changes: The case of the Lilac-crowned Amazon and Neotropical dry forests. Journal for Nature Conservation, v. 71, 2023. DOI: https://doi.org/10.1016/j.jnc.2022.126323
LEROY, B. DELSOL, R.; HUGUENY, B.; MEYNARD, C. N.; BARHOUMI, C.; MASSIN, M. B.; BELLARD, C. Without quality presence-absence data, discrimination metrics such as TSS can be misleading measures of model performance. Journal of Biogeography, v. 45, n. 9, p. 1994-2002, 2018. DOI: 10.1111/jbi.13402. DOI: https://doi.org/10.1111/jbi.13402
LEYS, C.; KLEIN, O.; DOMINICY, Y.; LEY, C. Detecting multivariate outliers: Use a robust variant of the Mahalanobis distance. Journal of Experimental Social Psychology, v. 74, p. 150-156, 2018. DOI: 10.1016/j.jesp.2017.09.011. DOI: https://doi.org/10.1016/j.jesp.2017.09.011
LOBO, J.; JIMÉNEZ-VALVERDE.; HORTAL, J. The uncertain nature of absences and their importance in species distribution modelling, Ecography, v. 33, pp. 103-114, 2010. DOI: 10.1111/j.1600-0587.2009.06039.x. DOI: https://doi.org/10.1111/j.1600-0587.2009.06039.x
MA, Y.; YOU, X. A sustainable conservation strategy of wildlife in urban ecosystems: Case of Gallinua chloropus in Beijing-Tianjin-Hebei region. Ecological Informatics, v. 68, 2022. DOI: 10.1016/j.ecoinf.2022.101571. DOI: https://doi.org/10.1016/j.ecoinf.2022.101571
MAITNER, B. S.; BOYLE, B.; CASLER, N.; CONDIT, R.; DONOGHUE, J.; DURÁN, S. M.; GUADERRAMA, D.; HINCHLIFF, C. E.; JORGENSEN, P. M.; KRAFT, N. J. B.; MCGILL, B.; MEROW, C.; MORUETA-HOLME, N.; PEET, R. K.; SANDEL, B.; SCHILDHAUER, M.; SMITH, S. A.; SVENNING, J. C.; THIERS, B.; VIOLLE, C.; WISER, S.; ENQUIST, B. The BIEN R package: A tool to access the Botanical Information and Ecology Network (BIEN) database. Methods in ecology and Evolution, v. 9, pp. 373-379, 2018. DOI: 10.1111/2041-210X.12861. DOI: https://doi.org/10.1111/2041-210X.12861
MI, C.; HUETTMANN, F.; GUO, Y.; HAN, X.; WEN, L. Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence. PeerJ, v. 5, 2017. DOI: 10.7717/peerj.2849. DOI: https://doi.org/10.7717/peerj.2849
MONTEVERDE, C.; DE SALES, F.; JONES, C. Evaluation of the CMIP6 Performance in Simulating Precipitation in the Amazon River Basin. Climate, v. 10, 2022. DOI: 10.3390/cli10080122. DOI: https://doi.org/10.3390/cli10080122
MOTTA, A. Z.; BRAGA, S. R.; DA SILVA, N. D. M.; CHRISTOFARO, C. Avaliação do desempenho de modelos de distribuição potencial da espécie Wunderlichia azulenzis. In: Anais do XVIII Simpósio Brasileiro de Sensoriamento Remoto, 2017, São Paulo. Anais [...]. São Paulo: INPE Santos, 2017.
MUGO, R.; SAITOH, S. I.; IGARASHI, H.; TOYODA, T.; MASUDA, S.; AWAJI, T.; ISHIKAWA, Y. Identification of skipjack tuna (Katsuwonus pelamis) pelagic hotspots applying a satellite remote sensing-driven analysis of ecological niche factors: A short-term run. PLoS One, v.15, 2020. DOI 10.1371/journal.pone.0237742. DOI: https://doi.org/10.1371/journal.pone.0237742
NDAO, B.; LEROUX, L.; HEMA, A.; DIOUF, A. A.; BÉGUÉ, A.; SAMBOU, B. Tree species diversity analysis using species distribution models: A Faidherbia albida parkland case study in Senegal. Ecological Indicators, v. 144, 2022. DOI: https://doi.org/10.1016/j.ecolind.2022.109443
QIAO, H.; SOBERÓN, J.; PETERSON, A. T. No silver bullets in correlative ecological niche modelling: insights from testing among many potential algorithms for niche estimation. Methods in Ecology and Evolution, v. 6, n. 10, pp. 11126-1136, 2015. DOI: 10.1111/2041-210X.12397. DOI: https://doi.org/10.1111/2041-210X.12397
REMYA, K.; RAMACHANDRAN, A.; JAYAKUMAR, S. Predicting the current and future suitable habitat distribution of Myristica dactyloides Gaertn. Using Maxent model in the Eastern Ghats, India. Ecological Engineering, v. 82, pp. 184-188, 2015. DOI: 10.1016/j.ecoleng.2015.04.053. DOI: https://doi.org/10.1016/j.ecoleng.2015.04.053
SENAY, S. D.; WORNER, S. P.; IKEDA, T. Novel Three-Step Pseudo-Absence Selection Technique for Improved Species Distribution Modelling. Plos ONE, v. 8, 2013. DOI 10.1371/journal.pone.0071218. DOI: https://doi.org/10.1371/journal.pone.0071218
THUILLER, W.; GUÉGUEN, M.; RENAUD, J.; KARGE, D. N.; ZIMMERMANN, N. E. Uncertainty in ensembles of global biodiversity scenarios. Nature Communication, v. 10, 2019. DOI: 10.1038/s41467-019-09519-w. DOI: https://doi.org/10.1038/s41467-019-09519-w
ZHAO, Z.; GUO, Y.; WEI, H.; RAN, Q.; GU, W. Predictions of the Potential Geographical Distribution and Quality of Gynostemma pentaphyllum Base on the Fuzzy Matter Element Model in China. Sustainability, v. 9, 2017. DOI: 10.3390/su9071114. DOI: https://doi.org/10.3390/su9071114
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ciência Florestal
This work is licensed under a Creative Commons Attribution 4.0 International License.
A revista CIÊNCIA FLORESTAL reserva-se o direito de realizar, nos originais, alterações de ordens normativas, ortográficas e gramaticais, com vistas a manter o padrão escolar da língua, mas respeitando o estilo dos autores. As provas finais podem ou não ser enviadas aos autores.
