Skip to main content
SpringerLink
Log in

Simplicity, Model Fit, Complexity and Uncertainty in Spatial Prediction Models Applied Over Time: We Are Quite Sure, Aren’t We?

  • Chapter
  • First Online:
Predictive Species and Habitat Modeling in Landscape Ecology

Abstract

There is a strong need to assess impacts on wildlife and their habitats before they occur, and to act proactively to avoid “costs” (e.g., loss of species, wilderness, ecological ­services, human lives or money; see Nielsen et al. 2008 for an applied example). Although the concept of being proactive has been known for decades, the global climate change discussion has brought these concepts to the forefront. Proactive action also has use in impact studies of stochastic catastrophes such as floods or hurricanes. Simulations and predictions across time can help to mitigate or even resolve current problems (Fig. 10.1). Such techniques are widely used to assess risks and they have evolved into industrial standards elsewhere, such as in operations research (Fuller et al. 2008), within the pharmaceutical, insurance, and car industries, and in public health (Herrick et al. in press). Weather forecasts have already shown the value and power of such models, ­driving many day-to-day decisions.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 249.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  • Allouche O, Tsoar A, Kadmon R (2006) Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS). J Appl Ecol 3:1223–1232.

    Article  Google Scholar 

  • Anderson DR, Cooch EG, Gutierrez RJ, Krebs CJ, Lindberg MS, Pollock KH, Ribic CA, Shenck TM (2003) Rigorous science: suggestions on how to raise the bar. Wildl Soc Bull 31:296–305.

    Google Scholar 

  • Araújo MB, Guisan A (2006) Five (or so) challenges for species distribution modelling. J Biogeogr 33:1677–1688.

    Article  Google Scholar 

  • Araújo MB, New M (2007) Ensemble forecasting of species distributions. Trends Ecol Evol 22:42–47.

    Article  PubMed  Google Scholar 

  • Austin MP (2002) Spatial prediction of species distribution: an interface between ecological ­theory and statistical modelling. Ecol Model 157:101–118.

    Article  Google Scholar 

  • Betts MG, Ganio L, Huso M, Som N, Huettmann F, Bowman J, Wintle BA (2009) Comment on “Methods to account for spatial autocorrelation in the analysis of species distributional data: a review”. Ecography 32:374–378.

    Article  Google Scholar 

  • Booms T, Huettmann F, Schempf P (2009) Gyrfalcon nest distribution in Alaska based on a predictive GIS model. Polar Biol 33:1601–1612.

    Google Scholar 

  • Boyce MS, Vernier PR, Nielsen SE, Schmiegelow FKA (2002) Evaluating resource selection functions. Ecol Model 157:281–300.

    Article  Google Scholar 

  • Braun CE (2005) Techniques for wildlife investigations and management. The Wildlife Society (TWS), Bethesda, MD.

    Google Scholar 

  • Breiman L (2001a) Statistical modelling: the two cultures. Stat Sci 16:199–231.

    Article  Google Scholar 

  • Breiman L (2001b) Random forests. Mach Learn 45:5–32.

    Article  Google Scholar 

  • Burnham KP, Anderson DR (2002) Model selection and multimodel inference: a practical information-theoretic approach. 2nd edition. Springer, New York.

    Google Scholar 

  • Chapin FS, Kofinas GP, Folke C (eds) (2010) Principles of ecosystem stewardship: resilience-based natural resource management in a changing world. Springer, New York.

    Google Scholar 

  • Chen D, Stow DA, Gong P (2004) Examining the effect of spatial resolution and texture window size on classification accuracy: an urban environment case. Int J Rem Sens 25:2177–2192.

    Article  Google Scholar 

  • Craig E, Huettmann F (2008) Using “blackbox” algorithms such as TreeNet and Random Forests for data-mining and for finding meaningful patterns, relationships and outliers in complex ecological data: an overview, an example using golden eagle satellite data and an outlook for a promising future. In: Wang H (ed) Intelligent data analysis: developing new methodologies through pattern discovery and recovery. IGI Global, Hershey, PA.

    Google Scholar 

  • Cushman S (2010) Space and time in ecology: noise or fundamental driver? In: Cushman S, Huettmann, F (eds) Spatial complexity, informatics and wildlife conservation. Springer, Tokyo.

    Chapter  Google Scholar 

  • Cushman S, Huettmann F (2010) Spatial complexity, informatics and wildlife conservation. Springer, Tokyo.

    Book  Google Scholar 

  • Efron B, Tibshirani RJ (1998) An Introduction to the bootstrap. Chapman & Hall, New York.

    Google Scholar 

  • Elith J, Graham CH, Anderson RP, Dudík M, Ferrier S, Guisan A, Hijmans RJ, Huettmann F, Leathwick JR, Lehmann A, Li J, Lohmann LG, Loiselle BA, Manion G, Moritz C, Nakamura M, Nakazawa Y, Overton JMcC, Peterson AT, Philips SJ, Richardson K, Scachetti-Pereira R, Schapire RE, Soberón J, Williams S, Wisz MS, Zimmerman NE (2006) Novel methods improve prediction of species’ distributions from occurrence data. Ecography 29:129–151.

    Article  Google Scholar 

  • Engler R, Guisan A, Rechsteiner L (2004) An improved approach for predicting the distribution of rare and endangered species from occurrence and pseudo-absence data. J Appl Ecol 41:263–274.

    Article  Google Scholar 

  • Euskirchen ES, McGuire AD, Kicklighter DW, Zhuang Q, Clein JS, Dargaville RJ, Dyek G, Kimball JS, McDonald KC, Mellioz JM, Romanovsky VE, Smith NV (2006) Importance of recent shifts in soil thermal dynamics on growing season length, productivity, and carbon Sequestration in terrestrial high-latitude ecosystems. Global Change Biol 12:1–20.

    Article  Google Scholar 

  • Euskirchen ES, McGuire AD, Chapin III FS, Yi S, Thompson CC (2009) Changes in vegetation in northern Alaska under scenarios of climate change, 2003–2100: implications for climate feedbacks. Ecol Appl 19:1022–1043.

    Article  CAS  PubMed  Google Scholar 

  • Fielding AH, Bell JF (1997) A review of methods for the assessment of prediction errors in ­conservation presence/absence models. Environ Conserv 24:38–49.

    Article  Google Scholar 

  • Fisher RA (1930) Inverse probability. Proc. Cambridge PhD.

    Google Scholar 

  • Foley JA, DeFries R, Asner GP, Barford C, Bonan G, Carpenter SR, Chapin FS, Coe MT, Daily GC, Gibbs HK, Helkowski JH, Holloway T, Howard EA, Kucharik CJ, Monfreda C, Patz JA, Prentice IC, Ramankutty N, Snyder PK (2005) Global consequences of land use. Science 306:570–572.

    Article  Google Scholar 

  • Fuller T, Morton DP, Sarkar S (2008) Incorporating uncertainty about species’ potential distributions under climate change into the selection of conservation areas with a case study from the Arctic Coastal Plain of Alaska. Biol Conserv 41:1547–1559.

    Google Scholar 

  • Gottschalk TK, Huettmann F, Ehlers M (2005) Thirty years of analysing and modelling avian habitat relationships using satellite imagery data: a review. Int J Rem Sens 26:2631–2656.

    Article  Google Scholar 

  • Gottschalk TK, Dittrich R, Diekötter T, Sheridan P, Wolters V, Ekschmitt K (2010) Modelling land-use sustainability using farmland birds as indicators. Ecol Indic 10:15–23.

    Article  Google Scholar 

  • Graeber R (2005) Towards a biodiversity assessment of the Pacific Rim: predictive large-scale GIS-modelling of Brown Bear distribution (Canada, Alaska, Russian Far East And Japan) in estuaries using compiled coastal data. MSc thesis, University of Hannover, Germany.

    Google Scholar 

  • Guisan A, Thuiller W (2005) Predicting species distribution: offering more than simple habitat models. Ecol Lett 8:993–1009.

    Article  Google Scholar 

  • Guisan A, Zimmermann NE, Elith J, Graham CH, Phillips S, Peterson AT (2007) What matters for predicting the occurrences of trees: techniques, data or species’ characteristics? Ecol Monogr 77:615–630.

    Article  Google Scholar 

  • Hegel T, Cushman SA, Evans J, Huettmann F (2010) Current state of the art for statistical ­modelling of species distributions. In: Cushman S, Huettmann F (eds) Spatial complexity, informatics and wildlife conservation. Springer, Tokyo.

    Google Scholar 

  • Herrick K, Huettmann F, Runstadler J, Chernetsov N, Antonov A, Valchuk O, Gerasimov Y, Matsyna E, Matsyna A, Markovets M, Druzyaka A, Saito K (in press) Predictive RISK modeling of avian influenza in the Pacific Rim and beyond. In: Kremers H (ed) RISK modeling proceedings, CODATA Berlin Germany.

    Google Scholar 

  • Hickerson MJ, Carstens BC, Cavender-Bares J, Crandall KA, Graham CH, Johnson JB, Rissler L, Victriano PF, Yoder AD (2009) Phylogeogaphy’s Past, present, and future: 10 years after Avise, 2000. Mol Phylogenetics Evol 54:291–301.

    Article  Google Scholar 

  • Hirzel A, Helfer V, Metral F (2001) Assessing habitat-suitability models with a virtual species. Ecol Model 145:111–121.

    Article  Google Scholar 

  • Hirzel AH, Hauser J, Chessel D, Perrin N (2002) Ecological-niche factor analysis: how to ­compute habitat-suitability maps without absence data? Ecology 83:2027–2036.

    Article  Google Scholar 

  • Hirzel AH, Le Lay G, Helfer V, Randin C, Guisan A (2006) Evaluating the ability of habitat ­suitability models to predict species presences. Ecol Model 199:142–152.

    Article  Google Scholar 

  • Huettmann F (2007a) Modern adaptive management: adding digital opportunities towards a ­sustainable world with new values. Forum Public Policy 3:337–342.

    Google Scholar 

  • Huettmann F (2007b) Constraints, suggested solutions and an outlook towards a new digital culture for the oceans and beyond: experiences from five predictive GIS models that contribute to global management, conservation and study of marine wildlife and habitat. In: Vanden Berghe E, Appeltans W, Costello MJ, Pissierssens P (eds) Proceedings of ocean biodiversity informatics: an international conference on marine biodiversity data management. Hamburg, Germany, 29 November–1 December, 2004. IOC Workshop Report, 202, VLIZ Special Publication 37.

    Google Scholar 

  • Huettmann F (2009) The global need for, and appreciation of, high-quality metadata in biodiversity work. In: Spehn E, Koerner C (eds) Data mining for global trends in mountain biodiversity. CRC Press, Taylor & Francis, Boca Roton, FL.

    Google Scholar 

  • Huettmann F, Franklin SE, Stenhouse GB (2005) Predictive spatial modeling of landscape change in the Foothills Model Forest. Forest Chron 81:1–13.

    Google Scholar 

  • Hunter CM, Caswell H, Runge MC, Amstrup SC, Regehr EV, Stirling I (2007) Polar bears in the Southern Beaufort Sea II: demography and population growth in relation to sea ice conditions. Administrative report, USGS Alaska Science Center, Anchorage, AK.

    Google Scholar 

  • Koerner C, Paulsen D (2004) A world-wide study of high altitude treeline temperatures. J Biogeogr 31:713–732.

    Article  Google Scholar 

  • Larson MA, Thompson FR, Millspaugh JJ, Dijak WD, Shifley SR (2004) Linking population viability, habitat suitability, and landscape simulation models for conservation planning. Ecol Model 180:103–118.

    Article  Google Scholar 

  • Lawler JJ, White D, Neilson RP, Blaustein AR (2006) Predicting climate-induced range shifts: model differences and model reliability. Glob Chang Biol 12:1568–1584.

    Article  Google Scholar 

  • Lawler JJ, Shafer SL, White D, Kareiva P, Maurer EP, Blaustein AR, Bartlein PJ (2009) Projected climate-induced faunal change in the western hemisphere. Ecology 90:588–597.

    Article  PubMed  Google Scholar 

  • Lemoine N, Bauer HG, Peintinger M, Boehning-Gaese K (2007) Effects of climate and land-use change on species abundance in a central European bird community. Conserv Biol 21:495–503.

    Article  PubMed  Google Scholar 

  • Lozier JD, Aniello P, Hickerson MJ (2009) Predicting the distribution of Sasquatch in western North America: anything goes with ecological niche modeling. J Biogeogr 36:1623–1627

    Article  Google Scholar 

  • Magness D (2009) An assessment of the U.S. Wildlife Refuge System management in times of climate change. PhD thesis, University of Alaska, Fairbanks, AK.

    Google Scholar 

  • Magness D, Morton JM, Huettmann F (2010) How spatial information contributes to the management and conservation of animals and habitats. In: Cushman S, Huettmann F (eds) Spatial complexity, informatics and wildlife conservation. Springer Tokyo, Japan.

    Google Scholar 

  • Manel S, Dias JM, Ormerod SJ (1999) Comparing discriminant analysis, neural networks and logistic regression for predicting species’ distributions: a case study with a Himalayan river bird. Ecol Model 120:337–347.

    Article  Google Scholar 

  • Manel S, Williams HC, Ormerod SJ (2001) Evaluating presence-absence models in ecology: the need to account for prevalence. J Appl Ecol 38:921–931.

    Article  Google Scholar 

  • Manly FJ, McDonald LL, Thomas DL, McDonald LT, Erickson WP (2002) Resource selection by animals. Kluwer Academic Publishers, Dordrecht NL.

    Google Scholar 

  • Marmion M, Parviainen M, Luoto M, Heikkinen RK, Thuiller W (2009) Evaluation of consensus methods in predictive species distribution modeling. Divers Distrib 15:59–69.

    Article  Google Scholar 

  • Martínez-Meyer, E, Peterson AT, Hargrove WW (2004) Ecological niches as stable distributional constraints on mammal species, with implications for Pleistocene extinctions and climate change projections for biodiversity. Glob Ecol Biogeogr 13:305–314.

    Article  Google Scholar 

  • Martínez-Meyer E, Peterson AT (2006) Conservatism of ecological niche characteristics in North American plant species over the Pleistocene-to-recent transition. J Biogeogr 33:1779–1789.

    Article  Google Scholar 

  • Murray K, Conner MM (2009) Methods to quantify variable importance. Implications for the analysis of noisy ecological data. Ecology 90:348–355.

    Article  PubMed  Google Scholar 

  • Myers JC (1997) Geostatistical error management: quantifying uncertainty for environmental mapping. Van Nostrand Reinhold, New York.

    Google Scholar 

  • Nielsen SE, Stenhouse GB, Beyer HL, Huettmann F, Boyce MS (2008) Can natural disturbance-based forestry rescue a declining population of grizzly bears? Biol Conserv 141:2193–2207.

    Article  Google Scholar 

  • Nogués-Bravo D, Rodríguez J, Hortal J, Batra P, Araújo M (2008) Climate change, humans, and the extinction of the woolly mammoth. PLoS Biol 6:e79.

    Article  PubMed  Google Scholar 

  • O’Connor, R (2000) Why ecology lags behind biology. The Scientist 14:35.

    Google Scholar 

  • Ohse B, Huettmann F, Ickert-Bond S., Juday G (2009) Modeling the distribution of white spruce (Picea glauca) for Alaska with high accuracy: an open access role-model for predicting tree species in last remaining wilderness areas. Polar Biol 32:1717–1724.

    Article  Google Scholar 

  • Onyeahialam A, Huettmann F, Bertazzon S (2005) Modeling sage grouse: Progressive computational methods for linking a complex set of local biodiversity and habitat data towards global conservation statements and decision support systems. Lecture Notes in Computer Science (LNCS) 3482, International Conference on Computational Science and its Applications (ICCSA) Proceedings Part III:152–161.

    Google Scholar 

  • Oppel S, Strobel C, Huettmann F (2009) Alternative methods to quantify variable importance in ­ecology. Technical Report Number 65, Department of Statistics, University of Munich, Germany.

    Google Scholar 

  • Pearce J, Ferrier S (2000a) Evaluating the predictive performance of habitat models developed using logistic regression. Ecol Model 133:225–245.

    Article  Google Scholar 

  • Pearce J, Ferrier S (2000b) An evaluation of alternative algorithms for fitting species distribution models using logistic regression. Ecol Model 128:127–147.

    Article  Google Scholar 

  • Peterson AT (2001) Predicting species’ geographic distributions based on ecological niche ­modeling. Condor 103:599–605.

    Article  Google Scholar 

  • Pineiro G, Perelman S, Guerschman JP, Parelo JM (2008) How to evaluate models: observed vs. predicted or predicted vs. observed ? Ecol Model 216:316–322.

    Article  Google Scholar 

  • Prasad AM, Iverson LR, Liaw A (2006) Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9:181–199.

    Article  Google Scholar 

  • Rickleffs RE, Miller GL (1999) Ecology, 4th edition, Freeman & Co Publishers, New York.

    Google Scholar 

  • Ritter J (2007) Species distribution models for Denali National Park and Preserve, Alaska. M.S. thesis, University of Alaska-Fairbanks, AK.

    Google Scholar 

  • Thomas L (1997) Retrospective power analysis. Conserv Biol 11:276–280.

    Article  Google Scholar 

  • Van Horne B (1983) Density as a misleading indicator of habitat quality. J Wildl Manage 47:893–901.

    Article  Google Scholar 

  • Wickert C (2007) Breeding White Storks (Ciconia ciconia) in former East Prussia: comparing predicted relative occurrences across scales and time using a stochastic gradient boosting method (TreeNet), GIS and public data. M.Sc. Thesis, University of Potsdam, Germany.

    Google Scholar 

  • Wickham JD, Rhitters KH (1995) Sensitivity of landscape metrics to pixel size. Int J Rem Sens 16:3585–3594.

    Article  Google Scholar 

  • Wiens JJ, Graham CH (2005) Niche conservatism: integrating evolution, ecology, and conservation biology. Ann Rev Ecol Evol System 36:519–539.

    Article  Google Scholar 

  • Wittingham MJ, Stephens PA, Bradbury RB, Freckleton RP (2006) Why do we still use stepwise modeling in ecology and behaviour? J Anim Ecol 75:1182–1189.

    Article  Google Scholar 

  • Worm B, Myers R (2003) Meta-analysis of cod-shrimp interactions reveals top-down control in oceanic food webs. Ecology 84:162–173.

    Article  Google Scholar 

  • Yen P, Huettmann F, Cooke F (2004) Modelling abundance and distribution of Marbled Murrelets (Brachyramphus marmoratus) using GIS, marine data and advanced multivariate statistics. Ecol Model 171:395–413.

    Article  Google Scholar 

  • Ziv Y (1998) The effect of habitat heterogeneity on species diversity patterns: a community-level approach using an object-oriented landscape simulation model (SHALOM). Ecol Model 111:135–170.

    Article  Google Scholar 

Download references

Acknowledgments

We appreciate the initial discussion (and idea) for this MS with T. Edwards. Additional help came from our colleagues A. Drew, Y. Wiersma, students in the EWHALE lab and co-workers world-wide. The important work by the R. O’Connor (quantitative ornithologist; deceased) and B. Ripley (S-Plus and R) and L. Breiman (machine learning modeler; deceased) cannot be emphasized highly enough. We greatly value the software support and kind cooperation with Salford Systems, Dan Steinberg and his team. Comments from Y. Wiersma and two anonymous reviewers helped to significantly improve the manuscript. This is EWHALE lab publication #95.

Author information

Authors and Affiliations

  1. EWHALE lab, Institute of Arctic Biology, Biology and Wildlife Department, University of Alaska, Fairbanks, AK, 99775, USA

    Falk Huettmann

Authors
  1. Falk Huettmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thomas Gottschalk
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Falk Huettmann .

Editor information

Editors and Affiliations

  1. Dept. Zoology, Biodiversity & Spatial Information Ctr., North Carolina State University, Raleigh, 27695, North Carolina, USA

    C. Ashton Drew

  2. Dept. Biology, Memorial University of Newfoundland, St. John's, A1B 3X9, Newfoundland and Labrador, Canada

    Yolanda F. Wiersma

  3. Inst. Arctic Biology, Dept. Biology & Wildlife, University of Alaska, Fairbanks, 99775, Alaska, USA

    Falk Huettmann

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer Science+BUsiness Media, LLC

About this chapter

Cite this chapter

Huettmann, F., Gottschalk, T. (2011). Simplicity, Model Fit, Complexity and Uncertainty in Spatial Prediction Models Applied Over Time: We Are Quite Sure, Aren’t We?. In: Drew, C., Wiersma, Y., Huettmann, F. (eds) Predictive Species and Habitat Modeling in Landscape Ecology. Springer, New York, NY. https://doi.org/10.1007/978-1-4419-7390-0_10

Download citation

Publish with us

Policies and ethics

Search

Navigation