Selecting thresholds of occurrence in the prediction of species distributions
Open accessAbstract
Transforming the results of species distribution modelling from probabilities of or suitabilities for species occurrence to presences/absences needs a specific threshold. Even though there are many approaches to determining thresholds, there is no comparative study. In this paper, twelve approaches were compared using two species in Europe and artificial neural networks, and the modelling results were assessed using four indices: sensitivity, specificity, overall prediction success and Cohen's kappa statistic. The results show that prevalence approach, average predicted probability/suitability approach, and three sensitivity‐specificity‐combined approaches, including sensitivity‐specificity sum maximization approach, sensitivity‐specificity equality approach and the approach based on the shortest distance to the top‐left corner (0,1) in ROC plot, are the good ones. The commonly used kappa maximization approach is not as good as the afore‐mentioned ones, and the fixed threshold approach is the worst one. We also recommend using datasets with prevalence of 50% to build models if possible since most optimization criteria might be satisfied or nearly satisfied at the same time, and therefore it's easier to find optimal thresholds in this situation.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The mean model TSS threshold maximizes specificity and sensitivity of the ROC curve and is particularly effective in presence-only data.
“This threshold consisted of the mean model TSS criteria of model evaluation, also named ' maximum test sensitivity and speci fi city ' logistic threshold, which maximizes the speci fi city and sensitivity of the receiver operating curve ( i.e. , the ROC curve), and is particularly effective in presence-only data (Liu et al., 2005).”
From Projecting future climate change impacts on the distribution of the ‘Octopus vulgaris species complex’ (2022) · cites this paper as Liu et al., 2005
The Index describes a threshold that maximizes the sum of sensitivity and specificity and identifies its corresponding point on the ROC curve. The cited paper does not call it a mean model TSS or “maximum test sensitivity and specificity” logistic threshold, and its discussion of occupied and unoccupied sites does not establish that it is particularly effective for presence-only data. (LLM, conf=0.87)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Predictive habitat distribution models in ecology
Guisan, A., & Zimmermann, N. E. (2000) · Ecological Modelling · doi:10.1016/s0304-3800(00)00354-9 · Cited by 7,359 · see citing works
A review of methods for the assessment of prediction errors in conservation presence/absence models
FIELDING, A. H., & BELL, J. F. (1997) · Environmental Conservation · doi:10.1017/s0376892997000088 · Cited by 6,956 · see citing works
Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine
ZWEIG, M. H., & Campbell, G. (1993) · Clinical Chemistry · doi:10.1093/clinchem/39.4.561 · Cited by 6,528 · see citing works
Basic principles of ROC analysis
Metz, C. E. (1978) · Seminars in Nuclear Medicine · doi:10.1016/s0001-2998(78)80014-2 · Cited by 6,058 · see citing works
Guisan, A., Edwards, T. C., & Hastie, T. (2002) · Ecological Modelling · doi:10.1016/s0304-3800(02)00204-1 · Cited by 2,356 · see citing works
Evaluating the predictive performance of habitat models developed using logistic regression
Pearce, J., & Ferrier, S. (2000) · Ecological Modelling · doi:10.1016/s0304-3800(00)00322-7 · Cited by 2,004 · see citing works
Austin, M. P. (2002) · Ecological Modelling · doi:10.1016/s0304-3800(02)00205-3 · Cited by 1,810 · see citing works
Evaluating presence–absence models in ecology: the need to account for prevalence
Manel, S., Williams, H. C., & Ormerod, S. J. (2001) · Journal of Applied Ecology · doi:10.1046/j.1365-2664.2001.00647.x · Cited by 1,759 · see citing works
Effects of sample size on accuracy of species distribution models
Stockwell, D. R. B., & Peterson, A. T. (2002) · Ecological Modelling · doi:10.1016/s0304-3800(01)00388-x · Cited by 1,237 · see citing works
GLM versus CCA spatial modeling of plant species distribution
Guisan, A., WEISS, S. B., & Weiss, A. D. (1999) · Plant Ecology · doi:10.1023/a:1009841519580 · Cited by 865 · see citing works
Pearson, R. G., Dawson, T. P., & Liu, C. (2004) · Ecography · doi:10.1111/j.0906-7590.2004.03740.x · Cited by 610 · see citing works
Self-citationModelling landscape‐scale habitat use using GIS and remote sensing: a case study with great bustards
Osborne, P. E., Alonso, J. C., & Bryant, R. G. (2001) · Journal of Applied Ecology · doi:10.1046/j.1365-2664.2001.00604.x · Cited by 564 · see citing works
SPECIES: A Spatial Evaluation of Climate Impact on the Envelope of Species
Pearson, R. G., Dawson, T. P., Berry, P. M., & Harrison, P. A. (2002) · Ecological Modelling · doi:10.1016/s0304-3800(02)00056-x · Cited by 474 · see citing works
Self-citationComparing five modelling techniques for predicting forest characteristics
Moisen, G. G., & Frescino, T. S. (2002) · Ecological Modelling · doi:10.1016/s0304-3800(02)00197-7 · Cited by 460 · see citing works
Manel, S., Dias, J.-M., & Ormerod, S. J. (1999) · Ecological Modelling · doi:10.1016/s0304-3800(99)00113-1 · Cited by 435 · see citing works
Huntley, B. J., Berry, P. M., Crämer, W., & McDonald, A. P. (1995) · Journal of Biogeography · doi:10.2307/2845830 · Cited by 405 · see citing works
Self-citationTesting the Generality of Bird‐Habitat Models
Fielding, A. H., & Haworth, P. F. (1995) · Conservation Biology · doi:10.1046/j.1523-1739.1995.09061466.x · Cited by 349 · see citing works
Berry, P. M., Dawson, T. P., Harrison, P. A., & Pearson, R. G. (2002) · Global Ecology and Biogeography · doi:10.1111/j.1466-8238.2002.00304.x · Cited by 336 · see citing works
Self-citationBoosting and Rocchio applied to text filtering
Schapire, R. E., Singer, Y., & Singhal, A. (1998) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/290941.290996 · Cited by 302 · see citing works
Predicting the potential distribution of plant species in an alpine environment
Guisan, A., Theurillat, J., & Kienast, F. (1998) · Journal of Vegetation Science · doi:10.2307/3237224 · Cited by 298 · see citing works
An artificial neural network approach to spatial habitat modelling with interspecific interaction
Özesmi, S. L., & Özesmi, U. (1999) · Ecological Modelling · doi:10.1016/s0304-3800(98)00149-5 · Cited by 290 · see citing works
Logit Models from Economics and Other Fields
Cramer, J. S. (2003) · Cambridge University Press eBooks · doi:10.1017/cbo9780511615412 · Cited by 288 · see citing works
A Comparison of C/B Ratios from Studies Using Receiver Operating Characteristic Curve Analysis
Cantor, S. B., Sun, C. C., Tortolero‐Luna, G., Richards-Kortum, R. R., & Follen, M. M. (1999) · Journal of Clinical Epidemiology · doi:10.1016/s0895-4356(99)00075-x · Cited by 218 · see citing works
Collingham, Y. C., Wadsworth, R. A., Huntley, B. J., et al. (2000) · Journal of Applied Ecology · doi:10.1046/j.1365-2664.2000.00556.x · Cited by 216 · see citing works
Equilibrium modeling of alpine plant distribution: how far can we go?
Guisan, A., & Theurillat, J. (2000) · Phytocoenologia · doi:10.1127/phyto/30/2000/353 · Cited by 174 · see citing works
Robertson, M. P., Caithness, N., & Villet, M. H. (2001) · Diversity and Distributions · doi:10.1046/j.1472-4642.2001.00094.x · Cited by 164 · see citing works
Brosse, S., Guégan, J., Tourenq, J.-N., & Lek, S. (1999) · Ecological Modelling · doi:10.1016/s0304-3800(99)00110-6 · Cited by 138 · see citing works
Hilbert, D. (2001) · Ecological Modelling · doi:10.1016/s0304-3800(01)00323-4 · Cited by 127 · see citing works
Robertson, M. P., Peter, C. I., Villet, M. H., & Ripley, B. S. (2003) · Ecological Modelling · doi:10.1016/s0304-3800(03)00028-0 · Cited by 120 · see citing works
GIS modeling of submerged macrophyte distribution using Generalized Additive Models
Lehmann, A. (1998) · Plant Ecology · doi:10.1023/a:1009754417131 · Cited by 109 · see citing works
Using habitat models to map diversity: pan‐African species richness of ticks (Acari: Ixodida)
Cumming, G. S. (2000) · Journal of Biogeography · doi:10.1046/j.1365-2699.2000.00419.x · Cited by 108 · see citing works
Species presence in fragmented landscapes: modelling of species requirements at the national level
Bailey, S. A., Haines-Young, R. H., & Watkins, C. (2002) · Biological Conservation · doi:10.1016/s0006-3207(02)00119-2 · Cited by 106 · see citing works
D'Heygere, T., Goethals, P. L. M., & Pauw, N. D. (2003) · Ecological Modelling · doi:10.1016/s0304-3800(02)00260-0 · Cited by 101 · see citing works
Statewide modeling of bobcat, Lynx rufus, habitat in Illinois, USA
Woolf, A., Nielsen, C. K., Weber, T. C., et al. (2002) · Biological Conservation · doi:10.1016/s0006-3207(01)00164-1 · Cited by 83 · see citing works
A Species‐Specific Approach to Modeling Biological Communities and Its Potential for Conservation
Olden, J. D. (2003) · Conservation Biology · doi:10.1046/j.1523-1739.2003.01280.x · Cited by 81 · see citing works
Use of artificial neural networks
Pu, H., & Hung, Y. (1995) · Environmental Management and Health · doi:10.1108/09566169510085126 · Cited by 57 · see citing works
Luck, G. (2002) · Biological Conservation · doi:10.1016/s0006-3207(01)00223-3 · Cited by 48 · see citing works
Berg, Å., Gärdenfors, U., & von Proschwitz, T. (2004) · Ecography · doi:10.1111/j.0906-7590.2004.03553.x · Cited by 45 · see citing works
Using Information Extraction to Aid the Discovery of Prediction Rules from Text
Mooney, U. Y. N. A. R. J. (2000) · Cited by 42 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- Berry, P. M. et al. 2001. Impacts on terrestrial environ- ments. Á/ In: Harrison, P. A., Berry, P. M. and Dawson, T. P. (eds), Climate change and nature conservation in the Britain and Ireland: modelling natural resource responses to climate change (the MONARCH project). UKCIP Tech. Rep., pp. 43 Á/150.
- Olden, J. D. and Jackson, D. A. 2001. Fish-habitat relationships in lakes: gaining predictive and explanatory insight by using artificial neural networks. Á/ Trans. Am. Fish. Soc. 130: 878 Á/ 897.
Cited by
Sorted by citations
Novel methods improve prediction of species’ distributions from occurrence data
Elith*, J., H. Graham*, C., P. Anderson, R., Dudík, M., Ferrier, S., Guisan, A., J. Hijmans, R., Huettmann, F., R. Leathwick, J., Lehmann, A., et al. (2006) · Ecography · doi:10.1111/j.2006.0906-7590.04596.x · Cited by 9,088 · see citing works
AUC: A misleading measure of the performance of predictive distribution models
Lobo, J. M., Jiménez‐Valverde, A., & Real, R. (2008) · Global Ecology and Biogeography · doi:10.1111/j.1466-8238.2007.00358.x · Cited by 3,499 · see citing works
Environmental controls on the distribution of wildfire at multiple spatial scales
Parisien, M.-A., & Moritz, M. A. (2009) · Ecological Monographs · doi:10.1890/07-1289.1 · Cited by 383 · see citing works
A checklist for maximizing reproducibility of ecological niche models
Feng, X., Park, D. S., Walker, C., Peterson, A. T., Merow, C., & Papeş, M. (2019) · Nature Ecology & Evolution · doi:10.1038/s41559-019-0972-5 · Cited by 323 · see citing works
The spatially varying influence of humans on fire probability in North America
Parisien, M.-A., Miller, C., Parks, S. A., DeLancey, E. R., Robinne, F.-N., & Flannigan, M. D. (2016) · Environmental Research Letters · doi:10.1088/1748-9326/11/7/075005 · Cited by 166 · see citing works
Invasive alien pests threaten the carbon stored in Europe’s forests
Seidl, R., Klonner, G., Rammer, W., Essl, F., Moreno, A., Neumann, M., & Dullinger, S. (2018) · Nature Communications · doi:10.1038/s41467-018-04096-w · Cited by 153 · see citing works
Kantar, M. B., Sosa, C. C., Khoury, C. K., Castañeda-Álvarez, N. P., Achicanoy, H. A., Bernau, V., Kane, N. C., Marek, L., Seiler, G., & Rieseberg, L. H. (2015) · Frontiers in Plant Science · doi:10.3389/fpls.2015.00841 · Cited by 76 · see citing works
New perspectives on the ecology of early domestic fowl: An interdisciplinary approach
Pitt, J., Gillingham, P. K., Maltby, M., & Stewart, J. R. (2016) · Journal of Archaeological Science · doi:10.1016/j.jas.2016.08.004 · Cited by 31 · see citing works
Borges, F. O., Guerreiro, M., Santos, C. P., Paula, J. R., & Rosa, R. (2022) · Frontiers in Marine Science · doi:10.3389/fmars.2022.1018766 · Cited by 28 · see citing works
“, the ROC curve), and is particularly effective in presence-only data (Liu et al., 2005).”
BackgroundYousefi, M., Naderloo, R., & Keikhosravi, A. (2022) · Global Ecology and Conservation · doi:10.1016/j.gecco.2022.e02266 · Cited by 19 · see citing works
- Authors
- Liu, C., Berry, P. M., Dawson, T. P., & Pearson, R. G.
- Affiliations
- University of New England (US)
- University of Oxford (GB)
- Venue
- Ecography
- Publisher
- Wiley
- Published
- 2005-06
- Volume
- 28
- Issue
- 3
- Pages
- 385-393
- ISSN
- 0906-7590 (ISSN-L)
- 1600-0587
- OpenAlex
- W2079018504
- Cited by
- 2,701
- References
- 40
- Citations by year
- 2026: 133 · 2025: 175 · 2024: 166 · 2023: 145 · 2022: 163 · 2021: 180 · 2020: 142 · 2019: 168 · 2018: 169 · 2017: 151 · 2016: 140 · 2015: 137 · 2014: 146 · 2013: 166 · 2012: 157
- FWCI
- 21.33
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Ecography (publishedVersion)
- ePrints Soton (University of Southampton) (submittedVersion)
- UCL Discovery (University College London) (submittedVersion)
- RUNE (Research UNE) (submittedVersion)
- Funders
- Ministry of Agriculture, Forestry and Fisheries
- Topics
- Physical Sciences › Environmental Science › Ecological Modeling › Species Distribution and Climate Change
- Physical Sciences › Environmental Science › Nature and Landscape Conservation › Ecology and Vegetation Dynamics Studies
- Physical Sciences › Environmental Science › Ecology › Wildlife Ecology and Conservation
- Keywords
- species distribution modeling, presence-absence prediction, prevalence, sensitivity and specificity, Cohen's kappa, ROC curve, artificial neural networks, model evaluation, threshold selection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
