Abstract
The study of links between bird species richness and forest fragmentation contributes to a better understanding of landscape biodiversity. Difficulties arise from the necessity to deal with multiple non-linear relationships between the involved variables. Neural network models provide an interesting solution thanks to their internal set of non-linear neuron-like components. Their ability is well established for prediction, but their complex structure limits the understanding of underlying processes. To open the ‘black box’ and get a more transparent ‘glass box’ model, we selected a simple neural network (2 inputs, 1 hidden layer with 3 neurons and 1 output neuron), that improves the prediction of birds species richness (lower root mean square error) compared to linear, log-linear and logistic models, and simple enough to analyze its internal components and identify patterns in the data. The first hidden neuron provided a sigmoid relationship related to the forest area, the second was like a Boolean operator separating two groups according to the distance to the nearest source forest larger than 100 ha, and the third acted on the smallest isolated woodlots. We revealed a group of isolated woodlots with a higher species richness than less isolated woodlots for a given forest area. This result, unexpected according to the literature, was not obvious in the raw data, and could be explained by a regional differentiation in fragmentation history. Our neural network showed its ability to improve prediction accuracy in respect to other models, to remain ecologically understandable and to give new insights into data exploration.
Similar content being viewed by others
References
G. Balent B. Courtiade (1992) ArticleTitleModelling bird communities/landscape patterns relationships in a rural area of South-Western France Landscape Ecol. 6 195–211
G. Balent M. Génard F. Lescourret (1988) ArticleTitleAnalyse des patrons de répartition des oiseaux nicheurs en Midi-Pyrénées Acta Oeco/Oeco Gen 9 247–263
J. Bascompte R.V. Sole (1996) ArticleTitleHabitat fragmentation and extinction thresholds in spatially explicit models J. Anim. Ecol. 65 465–473
P.E. Bellamy S.A. Hinsley I. Newton (1996) ArticleTitleFactors influencing bird species numbers in small woods in south- east England J. Appl. Ecol. 33 249–262
Bishop C. 1995. Neural Networks for Pattern Recognition. Oxford University Press, 504pp.
S. Brosse J.-F. Guegan J.-N. Tourenq S. Lek (1999) ArticleTitleThe use of artificial neural networks to assess fish abundance and spatial occupancy in the littoral zone of a mesotrophic lake Ecol. Model. 120 299–311 Occurrence Handle10.1016/S0304-3800(99)00110-6
J.R. Brown N.D. Macleod (1996) ArticleTitleIntegrating ecology into natural resource management policy Environ. Manage 20 289–296 Occurrence Handle10.1007/BF01203838 Occurrence Handle8661605
F. Canters (1997) ArticleTitleEvaluating the uncertainty of area estimates derived from fuzzy land-cover classification Photogram. Eng. Remote Sens. 63 403–414
M. Deconchat G. Balent (1996) ArticleTitleBiodiversité et forêt dans un paysage agricole: Etude bibliographique Etudes et Recherches sur les Systémes Agraires et le Développement 29 15–36
M. Deconchat G. Balent (2001) ArticleTitleVegetation and bird community dynamics in fragmented coppice forests Forestry 74 105–118 Occurrence Handle10.1093/forestry/74.2.105
H. Demuth M. Beale (1998) Neural Network Toolbox User’s Guide The MathWorks, Inc. Natick, Massachussets
R. Ejrnaes E. Aude B. Nygaard B. Munier (2002) ArticleTitlePrediction of habitat quality using ordination and neural networks Ecol. Appl. 12 1180–1187
L. Fahrig (2003) ArticleTitleEffects of habitat fragmentation on biodiversity Ann. Rev. Ecol. Evol. Syst. 34 487–515 Occurrence Handle10.1146/annurev.ecolsys.34.011802.132419
A.H. Fielding J.F. Bell (1997) ArticleTitleA review of methods for the assessment of prediction errors in conservation presence/absence models Environ. Conserv. 24 38–49 Occurrence Handle10.1017/S0376892997000088
C.H. Flather (1996) ArticleTitleFitting species-accumulation functions and assessing regional land use impacts on avian diversity J. Biogeogr. 23 155–168 Occurrence Handle10.1046/j.1365-2699.1996.00980.x
N. Gilbert K. Troitzsch (1999) Simulation for the social scientist Open University press London, UK 273
F.B. Golley (1989) ArticleTitleLandscape ecology and biological conservation (Editor’s comment) Landscape Ecol. 2 201–202 Occurrence Handle10.1007/BF00137150
S.L. Granhlom (1983) ArticleTitleBias in density estimates due to movement of birds Condor 85 243–248
J.-P. Guyon F. Bessiére O. Faignaert J.-C. Bois (1996) ArticleTitleEvolution des formations boisées sur le territoire de deux communes du canton d’Aurignac (Haute Garonne) de 1942 á 1992 Etudes et Recherches sur les Systémes Agraires et le Développement 29 139–152
Y. Haila A.O. Nicholls I.K. Hanski S. Raivio (1996) ArticleTitleStochasticity in bird habitat selection: Year-to-year changes in territory locations in a boreal forest bird assemblage Oikos 76 536–552
D.W. Hilbert B. Ostendorf (2001) ArticleTitleThe utility of artificial neural networks for modelling the distribution of vegetation in pastpresent and future climates Ecol. Model. 146 311–327 Occurrence Handle10.1016/S0304-3800(01)00323-4
Hilborn R. and Mangel M. 1997. The Ecological Detective–Confronting Models with Data. Princeton University Press, 320 pp.
S.A. Hinsley P.E. Bellamy B. Enoksson G. Fry L. Gabrielsen D. Mccollin A. Schotman (1998) ArticleTitleGeographical and land-use influences on bird species richness in small woods in agricultural landscapes Global Ecol. Biogeogr. Lett. 7 125–135
J. Hof C.H. Flather (1996) ArticleTitleAccounting for connectivity and spatial correlation in the optimal placement of wildlife habitat Ecol. Model. 88 143–155 Occurrence Handle10.1016/0304-3800(95)00082-8
R.L. Hutto S.M. Pletschet P. Hendricks (1986) ArticleTitleA fixed-radius point count method for nonbreeding and breeding season use Auk 103 593–602
Icaran C. 1995. Biodiversité et boisement des terres agricoles. Mesures et hiérarchisation de variables influençant l’avifaune de fragments forestiers dans le Sud-Ouest de la France. Master of Science Institut Agronomique Méditerranéen Saragosse, 187pp
G. Jansson P.K. Angelstam (1999) ArticleTitleThreshold levels of habitat composition for the presence of the long-tailed tit (aegithalos caudatus) in a boreal landscape Landscape Ecol. 14 283–290 Occurrence Handle10.1023/A:1008085902053
J. Joachim J.-F. Bousquet C. Faure (1997) Atlas des oiseaux nicheurs de Midi-Pyrénées Années 1985 á 1989 AROMP Toulouse (France) 262
J. Joachim J. Lauga (1996) ArticleTitleLe pinson des arbres (Fringilla coelebs L.), espèce modèle pour l’étude de la fragmentation des paysages forestiers du sud-ouest de la France Etudes et Recherches sur les Systèmes Agraires et le Développement 29 53–66
J. Jokimaki E. Huhta (1996) ArticleTitleEffects of landscape matrix and habitat structure on a bird community in northern Finland: A multi-scale approach Ornis Fennica 73 97–113
S.E. Jorgensen (1999) ArticleTitleState-of-the-art of ecological modelling with emphasis on development of structural dynamic models Ecol. Model. 120 75–96 Occurrence Handle10.1016/S0304-3800(99)00093-9
R. Kohavi (1995) ArticleTitleThe power of decision tables Mach. Learn. Ecml-95 912 174–189
S. Lek M. Delacoste P. Baran I. Dimopoulos J. Lauga S. Aulagnier (1996) ArticleTitleApplication of neural networks to modelling nonlinear relationships in ecology Ecol. Model. 90 39–52 Occurrence Handle10.1016/0304-3800(95)00142-5
S. Lek J.F. Guegan (1999) ArticleTitleArtificial neural networks as a tool in ecological modelling, an introduction Ecol. Model. 120 65–73 Occurrence Handle10.1016/S0304-3800(99)00092-7
F. Lescourret M. Genard (1994) ArticleTitleHabitatLandscape and Bird Composition in Mountain Forest Fragments J. Environ. Manage. 40 317–328 Occurrence Handle10.1006/jema.1994.1025
J.G. Liu P.S. Ashton (1999) ArticleTitleSimulating effects of landscape context and timber harvest on tree species diversity Ecol. Appl. 9 186–201
J.F. Lynch D.F. Whigham (1984) ArticleTitleEffects of forest fragmentation on breeding bird communities in MarylandUSA Biol. Conserv. 28 287–324 Occurrence Handle10.1016/0006-3207(84)90039-9
S. Manel J.-M. Dias S.J. Ormerod (1999) ArticleTitleComparing discriminant analysis, neural networks and logistic regression for predicting species distributions: a case study with a Himalayan river bird Ecol. Model. 120 337–347 Occurrence Handle10.1016/S0304-3800(99)00113-1
J. Munoz A.M. Felicisimo (2004) ArticleTitleComparison of statistical methods commonly used in predictive modelling J. Veg. Sci. 15 285–292
J.D. Olden D.A. Jackson (2002) ArticleTitleIlluminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks Ecol. Model. 154 135–150 Occurrence Handle10.1016/S0304-3800(02)00064-9
J.D. Olden M.K. Joy R.G. Death (2004) ArticleTitleAn accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data Ecol. Model 178 389–397 Occurrence Handle10.1016/j.ecolmodel.2004.03.013
P. Opdam (1990) Understanding the ecology of populations in fragmented landscapes Trans. IUGB Congress Trondheim 373–380
P. Opdam G. Rijsdijk F. Hustings (1985) ArticleTitleBird communities in small woods in an agricultural landscape: effects of area and isolation Biol. Conserv. 34 333–352 Occurrence Handle10.1016/0006-3207(85)90039-4
P. Opdam R.C. Apeldoorn ParticleVan A. Schotman J. Kalkhoven (1993) Population responses to landscape fragmentation C.C. Vos P. Opdam (Eds) Landscape Ecology of a Stressed Environment Chapman and Hall London 147–171
P. Opdam D. Dorp ParticleVan C.J.F. ter Braak (1984) ArticleTitleThe effect of isolation on the number of woodland birds of small woods in the Netherlands J. Biogeogr. 11 473–478
I. Rivals L. Personnaz (1999) ArticleTitleOn Cross-Validation for Model Selection Neural Comput. 11 863–870 Occurrence Handle10.1162/089976699300016476 Occurrence Handle10226186
D.E. Rumelhart G.E. Hinton R.J. Williams (1986) ArticleTitleLearning representations by back-propagation error Nature 323 533–536 Occurrence Handle10.1038/323533a0
Sarle W. 2002. What are cross-validation and bootstrapping?. http://www.faqs.org/faqs/ai-faq/neural-nets/part3/section-12.html.
D.A. Saunders R.J. Hobbs C.R. Margules (1991) ArticleTitleBiological consequences of ecosystem fragmentation: a review Conserv. Biol. 5 18–32 Occurrence Handle10.1111/j.1523-1739.1991.tb00384.x
I. Seginer T. Boulard B.J. Bailey (1994) ArticleTitleNeural network models of the greeenhouse climate J. Agric. Eng. Res. 54 203–216 Occurrence Handle10.1006/jaer.1994.1078
F.H. Sklar C. Hunsaker (2001) The use and uncertainties of spatial data for landscape models: an overview with examples from Florida Everglades C. Hunsaker M.F. Goodchild M. Friedl T. Case (Eds) Spatial Uncertainty for Ecology Springer Verlag New York, USA 15–46
J.A. Stegemann N.R. Buenfeld (1999) ArticleTitleA Glossary of Basic Neural Network Terminology for Regression Problems Neural Comput. Appl 8 290–296 Occurrence Handle10.1007/s005210050034
M.K. Trzcinski L. Fahrig G. Merriam (1999) ArticleTitleIndependent effects of forest cover and fragmentation on the distribution of forest breeding birds Ecol. Appl. 9 586–593
H. Werner M. Obach (2001) ArticleTitleNew neural network types estimating the accuracy of response for ecological modelling Ecol. Model. 146 289–298 Occurrence Handle10.1016/S0304-3800(01)00314-3
R.F. Whitcomb C.S. Robbins J.F. Lynch B.L. Whitcomb M.K. Klimkiewicz D. Bystrak (1988) Effects of forest fragmentation on avifauna of the eastern deciduous forest R.L. Burgess D.M. Sharpe (Eds) Forest Island dynamics in man-dominated landscapes Springer Verlag New York, USA 125–204
M.R. Williams (1996) ArticleTitleSpecies-area curves: The need to include zeroes Global Ecol. Biogeogr. Lett. 5 91–93
R.H. Yahner (1997) ArticleTitleLong-term dynamics of bird communities in a managed forested landscape Wilson Bull. 109 595–613
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Monteil, C., Deconchat, M. & Balent, G. Simple Neural Network Reveals Unexpected Patterns of Bird Species Richness in Forest Fragments. Landscape Ecol 20, 513–527 (2005). https://doi.org/10.1007/s10980-004-3317-x
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10980-004-3317-x