Access the full text.
Sign up today, get DeepDyve free for 14 days.
D. Rumelhart, Geoffrey Hinton, Ronald Williams (1986)
Learning representations by back-propagating errorsNature, 323
J. Lawton, G. Woodroffe (1991)
HABITAT AND THE DISTRIBUTION OF WATER VOLES: WHY ARE THERE GAPS IN A SPECIES' RANGE?Journal of Animal Ecology, 60
P. Brewin, S. Buckton, S. Ormerod (1998)
River habitat surveys and biodiversity in acid-sensitive riversAquatic Conservation-marine and Freshwater Ecosystems, 8
F. Spitz, S. Lek (1999)
Environmental impact prediction using neural network modelling. An example in wildlife damageJournal of Applied Ecology, 36
R. Green, G. Vascotto (1978)
A method for the analysis of environmental factors controlling patterns of species composition in aquatic communitiesWater Research, 12
W. Sutherland (1998)
The effect of local change in habitat quality on populations of migratory speciesJournal of Applied Ecology, 35
Boon Boon, Raven Raven (1998)
The application of classification and assessment methods to river management in the UK.Aquatic Conservation: Marine and Freshwater Ecosystems, 8
C. Chatfield (1995)
Model uncertainty, data mining and statistical inferenceJournal of The Royal Statistical Society Series A-statistics in Society, 158
Buckton Buckton, Brewin Brewin, Lewis Lewis, Stevens Stevens, Ormerod Ormerod (1998)
The distribution of dippers Cinclus cinclus in the acid‐sensitive region of upland Wales, 1984–1995.Freshwater Biology, 39
A. Davis, L. Jenkinson, J. Lawton, B. Shorrocks, S. Wood (1998)
Making mistakes when predicting shifts in species range in response to global warmingNature, 391
A. Suren, S. Ormerod (1998)
Aquatic bryophytes in Himalayan streams: testing a distribution model in a highly heterogeneous environmentFreshwater Biology, 40
A. Fielding, P. Haworth (1995)
Testing the Generality of Bird‐Habitat ModelsConservation Biology, 9
Malcolm Newson, D. Harper, C. Padmore, J. Kemp, B. Vogel (1998)
A cost-effective approach for linking habitats, flow types and species requirements
E. Peeters, J.J.P. Gardeniers (1998)
Logistic regression as a tool for defining habitat requirements of two common gammaridsFreshwater Biology, 39
N. Wahlberg, A. Moilanen, I. Hanski (1996)
Predicting the Occurrence of Endangered Species in Fragmented LandscapesScience, 273
M. Austin, Jacqui Meyers (1996)
Current approaches to modelling the environmental niche of eucalypts: implication for management of forest biodiversityForest Ecology and Management, 85
Buckton, Brewin, Lewis, Stevens, Ormerod (1998)
The distribution of dippers, Cinclus cinclus (L.), in the acid-sensitive region of Wales 1984–95Freshwater Biology, 39
M. Hill, R. Jongman, C. Braak, O. Tongeren (1987)
Data analysis in community and landscape ecologyJournal of Animal Science
S. Mastrorillo, S. Lek, F. Dauba, A. Belaud (1997)
The use of artificial neural networks to predict the presence of small‐bodied fish in a riverFreshwater Biology, 38
N. Leader-Williams, V. Heywood (1996)
Global Biodiversity AssessmentJournal of Animal Ecology, 65
A. Fielding, J. Bell (1997)
A review of methods for the assessment of prediction errors in conservation presence/absence modelsEnvironmental Conservation, 24
I. Jüttner, H. Rothfritz, S. Ormerod (1996)
Diatoms as indicators of river quality in the Nepalese Middle Hills with consideration of the effects of habitat‐specific samplingFreshwater Biology, 36
S. Manel, J. Dias, S. Ormerod (1999)
Comparing discriminant analysis, neural networks and logistic regression for predicting species distributions: a case study with a Himalayan river birdEcological Modelling, 120
T. Blackburn, K. Gaston (1998)
Some Methodological Issues in MacroecologyThe American Naturalist, 151
C. Bishop, C. Bishop, C. Bishop, V. Bishop, M. Bishop, M. Bishop, C. Bishop (1995)
Neural Network for Pattern Recognition
R. Green, P. Osborne, E. Sears (1994)
The distribution of Passerine birds in hedgerows during the breeding season in relation to characteristics of the hedgerow and adjacent farmlandJournal of Applied Ecology, 31
A. Strahler (1957)
Quantitative analysis of watershed geomorphologyEos, Transactions American Geophysical Union, 38
Baran Baran, Lek Lek, Delacoste Delacoste, Belaud Belaud (1996)
Stochastic models that predict trout population density or biomass on a mesohabitat scale.Hydrobiologia, 337
S. Lek, M. Delacoste, Philippe Baran, I. Dimopoulos, J. Lauga, S. Aulagnier (1996)
Application of neural networks to modelling nonlinear relationships in ecologyEcological Modelling, 90
M. Austin, A. Nicholls, M. Doherty, Jacqui Meyers (1994)
Determining species response functions to an environmental gradient by means of a β‐functionJournal of Vegetation Science, 5
S. Buckton, S. Ormerod (1997)
Use of a new standardized habitat survey for assessing the habitat preferences and distribution of upland river birdsBird Study, 44
S. Lek, A. Belaud, P. Baran, I. Dimopoulos, M. Delacoste (1996)
Role of some environmental variables in trout abundance models using neural networksAquatic Living Resources, 9
H. Neave, R. Cunningham, T. Norton, H. Nix (1996)
Biological inventory for conservation evaluation III. Relationships between birds, vegetation and environmental attributes in southern AustraliaForest Ecology and Management, 85
F. Goldsmith, P. Edwards, R. May, N. Webb (1995)
Large-Scale Ecology and Conservation Biology.Journal of Applied Ecology, 32
J. Hair (1972)
Multivariate data analysisInternational Statistical Review, 40
B. Ripley, N. Hjort (1996)
Pattern recognition and neural networks
M. Hunter (1995)
Fundamentals of Conservation Biology
P. Cheek, P. McCullagh, J. Nelder (1990)
Generalized Linear Models, 2nd Edn.Applied statistics, 39
P. Williams, C. Humphries, D. Vane-Wright, Kevin Gaston (1997)
Descriptive and predictive approaches to biodiversity measurement.Trends in ecology & evolution, 12 11
R. Collins, A. Jenkins (1996)
The impact of agricultural land use on stream chemistry in the Middle Hills of the Himalayas, NepalJournal of Hydrology, 185
P. Osborne, B. Tigar (1992)
Interpreting bird atlas data using logistic models: an example from Lesotho, Southern AfricaJournal of Applied Ecology, 29
K. Gaston, T. Blackburn (1999)
A critique for macroecologyOikos, 84
D. Pearson, S. Carroll (1998)
Global Patterns of Species Richness: Spatial Models for Conservation Planning Using Bioindicator and Precipitation DataConservation Biology, 12
C. Richards, L. Johnson, G. Host (1996)
Landscape-scale influences on stream habitats and biotaCanadian Journal of Fisheries and Aquatic Sciences, 53
M. Hill (1991)
Patterns of species distribution in Britain elucidated by canonical correspondence analysisJournal of Biogeography, 18
W. Venables, B. Ripley (1996)
Modern Applied Statistics with S-Plus.Biometrics, 52
S. Ormerod, S. Rundle, S. Wilkinson, G. Daly, K. Dale, I. Jűttner (1994)
Altitudinal trends in the diatoms, bryophytes, macroinvertebrates and fish of a Nepalese river systemFreshwater Biology, 32
W. Walley, Valentine Fontama (1998)
Neural network predictors of average score per taxon and number of families at unpolluted river sites in Great BritainWater Research, 32
K. Gaston, T. Blackburn (1995)
Mapping biodiversity using surrogates for species richness: macro-scales and New World birdsProceedings of the Royal Society of London. Series B: Biological Sciences, 262
D. Collett (1991)
Modelling Binary DataTechnometrics, 46
J. Guégan, S. Lek, T. Oberdorff (1998)
Energy availability and habitat heterogeneity predict global riverine fish diversityNature, 391
H. Birks, J. Line, S. Juggins, A. Stevenson, C. Braak (1990)
Diatoms and pH ReconstructionPhilosophical Transactions of the Royal Society B, 327
Summary 1. Current emphasis on species conservation requires the development of specific distribution models. Several modelling methods are available, but their performance has seldom been compared. We therefore used discriminant analysis, logistic regression and artificial neural networks with environmental data to predict the presence or absence of six river birds along 180 Himalayan streams. We applied each method to calibration sites and independent test sites. With logistic regression, we compared performance in predicting presence–absence using map‐derived predictors (river slope and altitude) as opposed to detailed data from a standardized river habitat survey (RHS). 2. Using the entire calibration data, overall success at predicting presence or absence was only slightly greater using artificial neural networks (89–100%) than either logistic regression (75–92%) or discriminant analysis (81–95%), and on this criterion all methods gave good performance. 3. When applied to independent test data, overall prediction success averaged 71–80%, with logistic regression marginally but significantly out‐performing the other methods. Encouragingly for researchers with limited data, model performance in jack‐knife tests faithfully represented performance in more rigorous validations where calibration (n = 119) and test sites (n = 61) were in separate geographical regions. 4. All three methods predicted true absences (83–92% success) better than true presences (31–44%). Results from logistic regression were the most variable across species, but positive prediction declined with increasing species rarity in each method. 5. Applications with logistic regression illustrated that significant habitat predictors varied between data sets within species. Hypotheses about causal effects by habitat structure on distribution were thus difficult to erect or test. Logistic regression also showed that detailed data from the river habitat survey substantially improved positive prediction by comparison with prediction using slope or altitude alone. 6. We conclude that discriminant analysis, logistic regression and artificial neural networks differ only marginally in performance when predicting species distributions. Model choice should therefore depend on the nature of the data, on the needs of any particular analysis, and on whether assumptions for each method are satisfied. All three methods share drawbacks due to systematic effects by species rarity on performance measures. They also share limitations due to the correlative nature of survey data often used for model development at the spatial scales required in macro‐ecology and conservation biology. Tests with independent data, using a wider range of performance measures than those used traditionally, will be important in examining models and testing hypotheses for such applications.
Journal of Applied Ecology – Wiley
Published: Oct 1, 1999
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.