Evaluation of the configuration of three algorithms to model the potential distribution of forest species
DOI:
https://doi.org/10.19136/era.a12n2.4127Keywords:
Random Forest, Maxent, generalized additive model, tuning, PinusAbstract
Potential distribution models are a useful tool to identify optimal environmental conditions for an organism to prevail. The objective of the study was to evaluate the parameter configuration of the Maxent, Random Forest and Generalized Additive Models (GAM) algorithms through the generation of distribution models of six forest species from Mexico. With presence records of six forest species, potential distribution models were adjusted with three algorithms, two configurations were used in their parameters (tuned and default), the models were evaluated through the area under the curve, to compare the tuned and default configuration. violin plots, plots of predicted fitness values with both configurations, and a fuzzy global matching analysis were performed. Sets of four, five, and six variables improved predictions. The best values in the regularization multiplier ranged between 0.1 and 0.4, the feature classes that best describe the potential distribution of the six species were linear, quadratic and product. Random Forest showed that with 750 and 1 000 trees and two variables in each division the fit of the models for the six species does not improve. The best smoothing values for the GAM algorithm ranged from 0.0001 for P. pseudostrobus to 1.5 for P. durangensis, however, no differences were found between fitting models with fine-tuned and default settings. The algorithms obtained good performance, however, the effect of parameter tuned on the predictive capacity was marginal and varied depending on the algorithm.
Downloads
References
Ávila Coriaz R, Villavicencio-García R, Ruiz-Corral JA (2018) Distribución potencial de Pinus herrerae Martínez en el occidente del estado de Jalisco. Revista Mexicana de Ciencias Forestales 5(24): 92-109. https://doi.org/10.29298/rmcf.v5i24.322.
Bodbyl-Roels S, Peterson AT, Xiao X (2011) Comparative analysis of remotely-sensed data products via ecological niche modeling of avian influenza case occurrences in Middle Eastern poultry. International Journal of Health Geographics 10(21): 1-12. https://doi.org/10.1186/1476-072X-10-21.
Breiman L (2001) Random Forests. Machine Learning 45: 5-32. https://doi.org/https://doi.org/10.1023/A:1010933404324.
Breiner FT, Nobis MP, Bergamini A, Guisan A (2018) Optimizing ensembles of small models for predicting the distribution of species with few occurrences. Methods in Ecology and Evolution 9(4): 802-808. https://doi.org/10.1111/2041-210X.12957.
Brun P, Thuiller W, Chauvier Y, Pellissier L, Wüest RO, Wang Z, Zimmermann NE (2020) Model complexity affects species distribution projections under climate change. Journal of Biogeography 47(1): 130-142. https://doi.org/10.1111/jbi.13734.
Cobos ME, Peterson AT, Barve N, and Osorio-Olvera L (2019a) Kuenm: An R package for detailed development of ecological niche models using Maxent. PeerJ 7: e6281. https://doi.org/10.7717/peerj.6281.
Cobos ME, Peterson AT, Osorio-Olvera L, Jiménez-García D (2019b) An exhaustive analysis of heuristic methods for variable selection in ecological niche modeling and species distribution modeling. Ecological Informatics 53: 100983. https://doi.org/10.1016/j.ecoinf.2019.100983.
Derville S, Torres LG, Iovan C, Garrigue C (2018) Finding the right fit: Comparative cetacean distribution models using multiple data sources and statistical approaches. Diversity and Distributions 24(11): 1657-1673. https://doi.org/10.1111/ddi.12782.
Fan JY, Zhao NX, Li M, Gao WF, Wang ML, Zhu GP (2018) What are the best predictors for invasive potential of weeds? Transferability evaluations of model predictions based on diverse environmental data sets for Flaveria bidentis. Weed Research 58(2): 141-149. https://doi.org/10.1111/wre.12292.
Fick SE, Hijmans RJ (2017) WorldClim 2: new 1-km spatial resolution climate surfaces for global land areas. International Journal of Climatology 37(12): 4302-4315. https://doi.org/10.1002/joc.5086.
Fournier A, Barbet-Massin M, Rome Q, Courchamp F (2017) Predicting species distribution combining multi-scale drivers. Global Ecology and Conservation 12: 215-226. https://doi.org/10.1016/j.gecco.2017.11.002.
García-Aranda MA, Méndez-González J, Hernández-Arizmendi JY (2018) Distribución potencial de Pinus cembroides, Pinus nelsonii y Pinus culminicola en el Noreste de México. Ecosistemas y Recursos Agropecuarios 5(13): 3-13. https://doi.org/10.19136/era.a5n13.1396.
Hallgren W, Santana F, Low-Choy S, Zhao Y, Mackey B (2019) Species distribution models can be highly sensitive to algorithm configuration. Ecological Modelling 408: 108719. https://doi.org/10.1016/j.ecolmodel.2019.108719.
Heikkinen RK, Marmion M, Luoto M (2012) Does the interpolation accuracy of species distribution models come at the expense of transferability? Ecography 35(3): 276-288. https://doi.org/10.1111/j.1600-0587.2011.06999.x.
Hengl T, Mendes de Jesus J, Heuvelink GBM, Ruiperez-Gonzalez M, Kilibarda M, Blagotić A, Kempen B (2017) SoilGrids250m: Global gridded soil information based on machine learning. In PLoS ONE 12(2): e0169748. https://doi.org/10.1371/journal.pone.0169748.
Jiménez SMÁ, Méndez GJ (2021) Distribución actual y potencial de Pinus engelmannii Carriére bajo escenarios de cambio climático. Madera y Bosques 27(3): e2732117. https://doi.org/10.21829/myb.2021.2732117.
Larsen K (2015) GAM: the Predictive Modeling Silver Bullet. MultiThreaded 1-27. Retrieved from https://multithreaded.stitchfix.com/blog/2015/07/30/gam/
Li Y, Li M, Li C, Liu Z (2020) Optimized maxent model predictions of climate change impacts on the suitable distribution of cunninghamia lanceolata in China. Forests 11(3): 1-25. https://doi.org/10.3390/f11030302.
Low BW, Zeng Y, Tan HH, Yeo DCJ (2020) Predictor complexity and feature selection affect Maxent model transferability: Evidence from global freshwater invasive species. Diversity and Distributions 27(3): 497-511. https://doi.org/10.1111/ddi.13211.
Manzanilla-Quiñones U, Aguirre-Calderón ÓA, Jiménez-Pérez J, Treviño-Garza EJ, Yerena-Yamallel JI (2019) Distribución actual y futura del bosque subalpino de Pinus hartwegii Lindl en el Eje Neovolcánico Transversal. Madera y Bosques 25(2): 1-16. https://doi.org/10.21829/myb.2019.2521804.
Martínez-Sifuentes AR, Villanueva-Díaz J, Manzanilla-Quiñones U, Becerra-López JL, Hernández-Herrera JA, Estrada-ávalos J, Velázquez-Pérez AH (2020) Spatial modeling of the ecological niche of pinus greggii engelm. (pinaceae): A species conservation proposal in mexico under climatic change scenarios. IForest 13(5): 426-434. https://doi.org/10.3832/ifor3491-013.
Méndez-Encina FM, Méndez-González J, Mendieta-Oviedo R, López-Díaz JÓM, Nájera-Luna JA (2021) Ecological niches and suitability areas of three host pine species of bark beetle dendroctonus mexicanus hopkins. Forests 12(4): 1-18. https://doi.org/10.3390/f12040385.
Merow C, Smit MJ, Silander JA (2013) A practical guide to MaxEnt for modeling species’ distributions: What it does, and why inputs and settings matter. Ecography 36(10): 1058-1069. https://doi.org/10.1111/j.1600-0587.2013.07872.x.
Montoya-Jiménez JC, Valdez-Lazalde JR, Ángeles-Pérez G, De los santos-Posadas HM, Cruz-Cárdenas G (2022) Predictive capacity of nine algorithms and an ensemble model to determine the geographic distribution of tree species. IForest 15(5): 363-371. https://doi.org/https://doi.org/10.3832/ifor4084-015.
Pecchi M, Marchi M, Moriondo M, Forzieri G, Ammoniaci M, Bernetti I, Chirici G (2020) Potential impact of climate change on the forest coverage and the spatial distribution of 19 key forest tree species in italy under RCP4.5 IPCC trajectory for 2050s. Forests 11(9): 1-19. https://doi.org/10.3390/F11090934.
Probst P, Wright MN, and Boulesteix AL (2019) Hyperparameters and tuning strategies for random forest. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 9(3): 1-15. https://doi.org/10.1002/widm.1301.
R Core Team (2024) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/. Fecha de consulta: 5 de mayo de 2023.
Schratz P, Muenchow J, Iturritxa E, Richter J, Brenning A (2019) Hyperparameter tuning and performance assessment of statistical and machine-learning algorithms using spatial data. Ecological Modelling 406(24): 109-120. https://doi.org/10.1016/j.ecolmodel.2019.06.002.
SEMARNAT (2010) Atlas Geográfico del Medio Ambiente y Recursos Naturales. Secretaría de Medio Ambiente y Recursos Naturales. https://biblioteca.semarnat.gob.mx/janium/Documentos/Ciga/Libros2011/CG006431.pdf. Fecha de consulta: 7 mayo de 2023.
Swets JA (1988) Measuring the accuracy of diagnostic information. Science 240(4857): 1285-1293. https://doi.org/10.1002/9781118341544.ch5.
Urbina-Cardona N, Blair ME, Londoño MC, Loyola R, Velásquez-Tibatá J, Morales-Devia H (2019) Species Distribution Modeling in Latin America: A 25-Year Retrospective Review. Tropical Conservation Science 12(1): 1-19. https://doi.org/10.1177/1940082919854058.
Valavi R, Elith J, Lahoz-Monfort JJ, Guillera-Arroita G (2021) Modelling species presence-only data with random forests. Ecography 44(12): 1731-1742. https://doi.org/10.1111/ecog.05615.
Vignali S, Barras AG, Arlettaz R, Braunisch V (2020) SDMtune: An R package to tune and evaluate species distribution models. Ecology and Evolution 10(20): 11488-11506. https://doi.org/10.1002/ece3.6786.
Visser H, De-Nijs T (2006) The map comparison kit. Environmental Modelling and Software 21(3): 346-358. https://doi.org/10.1016/j.envsoft.2004.11.013.
Wood SN (2017) Generalized Additive Models An Introduction with R. Chapman and Hall/CRC. New York, USA. 496p. https://doi.org/10.1201/9781315370279.
Wood SN (2021) Package mgcv. R package version 1.8-33. https://doi.org/10.1201/9781315370279.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Ecosistemas y Recursos Agropecuarios
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Aviso de copyright
Los autores que se envían a esta revista aceptan los siguientes términos:
una. Los autores conservan los derechos de autor y garantizan a la revista el derecho a ser la primera publicación del trabajo con una licencia de atribución de Creative Commons que permite a otros compartir el trabajo con un reconocimiento de la autoría del trabajo y la publicación inicial en esta revista.
B. Los autores pueden establecer acuerdos complementarios separados para la distribución no exclusiva de la versión del trabajo publicado en la revista (por ejemplo, en un repositorio institucional o publicarlo en un libro), con un reconocimiento de su publicación inicial en esta revista.
C. Se permite y se anima a los autores a difundir su trabajo electrónicamente (por ejemplo, en repositorios institucionales o en su propio sitio web) antes y durante el proceso de envío, ya que puede conducir a intercambios productivos, así como a una cita más temprana y más extensa del trabajo publicado. (Consulte El efecto del acceso abierto).
