IDEAS home Printed from https://ideas.repec.org/a/eee/ecomod/v328y2016icp108-118.html
   My bibliography  Save this article

How important are choice of model selection method and spatial autocorrelation of presence data for distribution modelling by MaxEnt?

Author

Listed:
  • Halvorsen, Rune
  • Mazzoni, Sabrina
  • Dirksen, John Wirkola
  • Næsset, Erik
  • Gobakken, Terje
  • Ohlson, Mikael

Abstract

In this paper we explore new options for model selection in the distribution modelling method MaxEnt, offered by the strict maximum likelihood explanation of the method. These options, which are collectively referred to as the ‘alternative MaxEnt procedure’ (aMp), imply manual forward stepwise selection of variables and an F-ratio test to compare nested models. We compared aMp models with models obtained by the default variable transformation and model selection procedures in the popular Maxent.jar software (‘default MaxEnt procedure’; dMp), which invokes ℓ1-regularisation. We used swamp-forest presence in SE Norway as the target for our modelling. Eleven terrain variables derived from a LiDAR-based digital elevation map, making up three groups of internally correlated variables, were used as predictors in the models. An independently collected presence/absence ‘test’ data set was used for evaluation of models. Although dMp models were much more complex than aMp models, with up to 240 variables derived from the original 11, compared to a maximum number of derived variables in aMp models of 14, no significant difference in performance between dMp and aMp models was found. This indicates that the regularisation procedure is not the main reason for the good performance of MaxEnt (as implemented in Maxent.jar) in comparative studies. Advantages of the more flexible aMp procedure, which produces simpler models, are discussed. Effects of spatial autocorrelation in the response variable on modelling results were addressed by obtaining parallel MaxEnt models for two response variables that differ in the number of presence observations: the centroid of the 121 swamp forests and the 7175 grid cells, each 5m×5m, in which swamp forest was recorded as present. Our results are not conclusive with respect to the effect of spatial autocorrelation in the response variable on the predictive performance of distribution models by MaxEnt.

Suggested Citation

  • Halvorsen, Rune & Mazzoni, Sabrina & Dirksen, John Wirkola & Næsset, Erik & Gobakken, Terje & Ohlson, Mikael, 2016. "How important are choice of model selection method and spatial autocorrelation of presence data for distribution modelling by MaxEnt?," Ecological Modelling, Elsevier, vol. 328(C), pages 108-118.
  • Handle: RePEc:eee:ecomod:v:328:y:2016:i:c:p:108-118
    DOI: 10.1016/j.ecolmodel.2016.02.021
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0304380016300503
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.ecolmodel.2016.02.021?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Santika, Truly & Hutchinson, Michael F., 2009. "The effect of species response form on species distribution model prediction and inference," Ecological Modelling, Elsevier, vol. 220(19), pages 2365-2379.
    2. Merckx, Bea & Steyaert, Maaike & Vanreusel, Ann & Vincx, Magda & Vanaverbeke, Jan, 2011. "Null models reveal preferential sampling, spatial autocorrelation and overfitting in habitat suitability modelling," Ecological Modelling, Elsevier, vol. 222(3), pages 588-597.
    3. Stokland, Jogeir N. & Halvorsen, Rune & Støa, Bente, 2011. "Species distribution modelling—Effect of design and sample size of pseudo-absence observations," Ecological Modelling, Elsevier, vol. 222(11), pages 1800-1809.
    4. Anderson, Robert P. & Gonzalez, Israel, 2011. "Species-specific tuning increases robustness to sampling bias in models of species distributions: An implementation with Maxent," Ecological Modelling, Elsevier, vol. 222(15), pages 2796-2811.
    5. Jesús Aguirre-Gutiérrez & Luísa G Carvalheiro & Chiara Polce & E Emiel van Loon & Niels Raes & Menno Reemer & Jacobus C Biesmeijer, 2013. "Fit-for-Purpose: Species Distribution Model Performance Depends on Evaluation Criteria – Dutch Hoverflies as a Case Study," PLOS ONE, Public Library of Science, vol. 8(5), pages 1-11, May.
    6. Ian W. Renner & David I. Warton, 2013. "Equivalence of MAXENT and Poisson Point Process Models for Species Distribution Modeling in Ecology," Biometrics, The International Biometric Society, vol. 69(1), pages 274-281, March.
    7. Austin, Mike, 2007. "Species distribution models and ecological theory: A critical assessment and some possible new approaches," Ecological Modelling, Elsevier, vol. 200(1), pages 1-19.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Wiltshire, Kathryn H & Tanner, Jason E, 2020. "Comparing maximum entropy modelling methods to inform aquaculture site selection for novel seaweed species," Ecological Modelling, Elsevier, vol. 429(C).
    2. Wei Xu & Yuqi Miao & Shuaimeng Zhu & Jimin Cheng & Jingwei Jin, 2023. "Modelling the Geographical Distribution Pattern of Apple Trees on the Loess Plateau, China," Agriculture, MDPI, vol. 13(2), pages 1-14, January.
    3. Fois, Mauro & Cuena-Lombraña, Alba & Fenu, Giuseppe & Bacchetta, Gianluigi, 2018. "Using species distribution models at local scale to guide the search of poorly known species: Review, methodological issues and future directions," Ecological Modelling, Elsevier, vol. 385(C), pages 124-132.
    4. Schratz, Patrick & Muenchow, Jannes & Iturritxa, Eugenia & Richter, Jakob & Brenning, Alexander, 2019. "Hyperparameter tuning and performance assessment of statistical and machine-learning algorithms using spatial data," Ecological Modelling, Elsevier, vol. 406(C), pages 109-120.
    5. Akpoti, Komlavi & Dossou-Yovo, Elliott R. & Zwart, Sander J. & Kiepe, Paul, 2021. "The potential for expansion of irrigated rice under alternate wetting and drying in Burkina Faso," Agricultural Water Management, Elsevier, vol. 247(C).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Wiltshire, Kathryn H & Tanner, Jason E, 2020. "Comparing maximum entropy modelling methods to inform aquaculture site selection for novel seaweed species," Ecological Modelling, Elsevier, vol. 429(C).
    2. Moreno-Amat, Elena & Mateo, Rubén G. & Nieto-Lugilde, Diego & Morueta-Holme, Naia & Svenning, Jens-Christian & García-Amorena, Ignacio, 2015. "Impact of model complexity on cross-temporal transferability in Maxent species distribution models: An assessment using paleobotanical data," Ecological Modelling, Elsevier, vol. 312(C), pages 308-317.
    3. Santiago José Elías Velazco & Franklin Galvão & Fabricio Villalobos & Paulo De Marco Júnior, 2017. "Using worldwide edaphic data to model plant species niches: An assessment at a continental extent," PLOS ONE, Public Library of Science, vol. 12(10), pages 1-24, October.
    4. Bell, David M. & Schlaepfer, Daniel R., 2016. "On the dangers of model complexity without ecological justification in species distribution modeling," Ecological Modelling, Elsevier, vol. 330(C), pages 50-59.
    5. Abel Chemura & Dumisani Kutywayo & Danisile Hikwa & Christoph Gornott, 2022. "Climate change and cocoyam (Colocasia esculenta (L.) Schott) production: assessing impacts and potential adaptation strategies in Zimbabwe," Mitigation and Adaptation Strategies for Global Change, Springer, vol. 27(6), pages 1-20, August.
    6. Leandro, Camila & Jay-Robert, Pierre & Mériguet, Bruno & Houard, Xavier & Renner, Ian W., 2020. "Is my sdm good enough? insights from a citizen science dataset in a point process modeling framework," Ecological Modelling, Elsevier, vol. 438(C).
    7. Barker, Justin R. & MacIsaac, Hugh J., 2022. "Species distribution models: Administrative boundary centroid occurrences require careful interpretation," Ecological Modelling, Elsevier, vol. 472(C).
    8. Holder, Anna M. & Markarian, Arev & Doyle, Jessie M. & Olson, John R., 2020. "Predicting geographic distributions of fishes in remote stream networks using maximum entropy modeling and landscape characterizations," Ecological Modelling, Elsevier, vol. 433(C).
    9. Schartel, Tyler E. & Cao, Yong, 2024. "Background selection complexity influences Maxent predictive performance in freshwater systems," Ecological Modelling, Elsevier, vol. 488(C).
    10. Ortner, Olivia & Wallentin, Gudrun, 2020. "Integration of landscape metric surfaces derived from vector data improves species distribution models," Ecological Modelling, Elsevier, vol. 431(C).
    11. Kuemmerlen, Mathias & Schmalz, Britta & Guse, Björn & Cai, Qinghua & Fohrer, Nicola & Jähnig, Sonja C., 2014. "Integrating catchment properties in small scale species distribution models of stream macroinvertebrates," Ecological Modelling, Elsevier, vol. 277(C), pages 77-86.
    12. Václavík, Tomáš & Meentemeyer, Ross K., 2009. "Invasive species distribution modeling (iSDM): Are absence data and dispersal constraints needed to predict actual distributions?," Ecological Modelling, Elsevier, vol. 220(23), pages 3248-3258.
    13. Muñoz-Mas, Rafael & Vezza, Paolo & Alcaraz-Hernández, Juan Diego & Martínez-Capel, Francisco, 2016. "Risk of invasion predicted with support vector machines: A case study on northern pike (Esox Lucius, L.) and bleak (Alburnus alburnus, L.)," Ecological Modelling, Elsevier, vol. 342(C), pages 123-134.
    14. Wolke Tobón-Niedfeldt & Alicia Mastretta-Yanes & Tania Urquiza-Haas & Bárbara Goettsch & Angela P. Cuervo-Robayo & Esmeralda Urquiza-Haas & M. Andrea Orjuela-R & Francisca Acevedo Gasman & Oswaldo Oli, 2022. "Incorporating evolutionary and threat processes into crop wild relatives conservation," Nature Communications, Nature, vol. 13(1), pages 1-18, December.
    15. Iturbide, Maialen & Bedia, Joaquín & Herrera, Sixto & del Hierro, Oscar & Pinto, Miriam & Gutiérrez, Jose Manuel, 2015. "A framework for species distribution modelling with improved pseudo-absence generation," Ecological Modelling, Elsevier, vol. 312(C), pages 166-174.
    16. Meineri, Eric & Dahlberg, C. Johan & Hylander, Kristoffer, 2015. "Using Gaussian Bayesian Networks to disentangle direct and indirect associations between landscape physiography, environmental variables and species distribution," Ecological Modelling, Elsevier, vol. 313(C), pages 127-136.
    17. Marmion, Mathieu & Luoto, Miska & Heikkinen, Risto K. & Thuiller, Wilfried, 2009. "The performance of state-of-the-art modelling techniques depends on geographical distribution of species," Ecological Modelling, Elsevier, vol. 220(24), pages 3512-3520.
    18. Kaiping Wang & Weiqi Wang & Niyi Zha & Yue Feng & Chenlan Qiu & Yunlu Zhang & Jia Ma & Rui Zhang, 2022. "Spatially Heterogeneity Response of Critical Ecosystem Service Capacity to Address Regional Development Risks to Rapid Urbanization: The Case of Beijing-Tianjin-Hebei Urban Agglomeration in China," Sustainability, MDPI, vol. 14(12), pages 1-21, June.
    19. Liang, Wanwan & Papeş, Monica & Tran, Liem & Grant, Jerome & Washington-Allen, Robert & Stewart, Scott & Wiggins, Gregory, 2018. "The effect of pseudo-absence selection method on transferability of species distribution models in the context of non-adaptive niche shift," Ecological Modelling, Elsevier, vol. 388(C), pages 1-9.
    20. Sellami, Mohamed Habib & Sifaoui, Mohamed Salah, 2008. "Modelling of heat and mass transfer inside a traditional oasis: Experimental validation," Ecological Modelling, Elsevier, vol. 210(1), pages 144-154.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:ecomod:v:328:y:2016:i:c:p:108-118. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/ecological-modelling .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.