Abstract
Transfer functions that implement organism–environment relationships are now commonly used for inferring past environmental conditions in paleoecology. Specific software for developing and evaluating commonly used modelling techniques such as Weighted averaging (WA), Weighted averaging partial least square (WA-PLS), Maximum likelihood (ML), and Modern analog technique (MAT) are available. A new software programme, PaleoNet, is now available for modelling organism–environment relationships which is specifically designed for the development and the evaluation of artificial neural network (ANN) based transfer functions in paleoecology. Here we present the main characteristics of this new software PaleoNet (User guide version 1.01) and discuss in more detail one of its specific features: the pruning.
Similar content being viewed by others
References
Bigler C, Hall RI (2002) Diatoms as indicators of climatic and limnological change in Swedish Lapland: a 100-lake calibration set and its validation for paleoecological reconstructions. J Paleolimnol 27:97–115
Birks HJB, Line JM, Juggins S, Stevenson AC, ter Braak CJF (1990) Diatoms and pH reconstructions. Phil Trans Roy Soc Lond B 327:263–278
Fallu MA, Pienitz R (1999) Diatomées lacustres de Jamésie-Hudsonie (Québec) et modèle de reconstitution des concentration de carbone organique dissous. Ecoscience 6:603–620
Fallu MA, Allaire N, Pienitz R (2002) Distribution of freshwater diatoms in 64 labrador (Canada) lakes: species–environment relationships along latitudinal gradients and reconstruction models for water colour and alkalinity. Can J Fish Aquat Sci 59:329–349
Gregory-Eaves I, Smol JP, Finney BP, Edwards ME (1999) Diatom-based transfer functions for inferring past climatic and environmental changes in Alaska, USA. Arct Antarct Alp Res 31:353–365
Imbrie J, Kipp NG (1971) A new micropaleontological method for quantitative paleoclimatology: application to a late Pleistocene Carribean core. In: Turekian KK (ed) The late cenozoic glacial ages. Yale University Press, New Haven and London, pp 71–181
Juggins S, ter Braak CJF (1993) CALIBRATE – a program for species-environment calibration by weighted averaging partial least squares regression. Department of Geography, University of Newcastle, Newcastle upon Tyne, UK
Juggins S, ter Braak CJF (1995) WAPLS. Unpublished computer program, version 1.0, Department of Geography, University of Newcastle, Newcastle upon Tyne, UK
Juggins S (2004) C2 User guide. Software for ecological and paleoecological data analysis and visualisation. University of Newcastle, Newcastle upon Tyne, UK, 69 pp
Köster D, Racca JMJ, Pienitz R (2004) Diatom-based inference models and reconstructions revisited: methods and transformations. J Paleolimnol 32:233–245
Kucera M, Weinelt M, Kiefer T, Pflaumann U, Hayes A, Chen MT, Mix AC, Barrows TT, Cortijo E, Duprat J, Juggins S, Waelbroeck C (2005) Reconstruction of sea-surface temperatures from assemblages of planktonic foraminifera: multi-tecnique approach based on geographically constrained calibration data sets and its application to glacial Atlantic and Pacific Oceans. Quaternary Sci Rev 24:951–998
Larocque I, Hall RI, Grahn E (2001) Chironomids as indicators of climate change: a 100-lake training set from a subarctic region of northern Sweden (Lapland). J Paleolimnol 26:307–322
Malmgren BA, Nordlund U (1997) Application of artificial neural networks to palaoceanographic data. Palaeogeogr Palaeoclimatol Palaeoecol 136:359–373
Malmgren BA, Kucera M, Nyberg J, Waelbroeck C (2001) Comparison of statistical and neural network techniques fro estimating past sea-surface temperatures from planktonic foraminifer census data. Paleoceanography 16:520–530
Philibert A, Prairie YT (2002) Diatom-based transfer functions for western Quebec lakes (Abitibi and Haute Maurice): the possible role of epilimnetic CO2 concentration in influencing diatom assemblages. J Paleolimnol 27:465–480
Racca JMJ, Philibert A, Racca R, Prairie YT (2001) A comparison between diatom-pH-inference models using Artificial Neural Networks (ANNs), Weighted Averaging (WA) and Weighted Averaging Partial Least Square (WA-PLS) regressions. J Paleolimnol 26:411–422
Racca JMJ, Wild M, Birks HJB, Prairie YT (2003) Separating wheat from chaff: diatom taxon selection using an artificial neural network pruning algorithm. J Paleolimnol 29:123–133
Racca JMJ, Gregory-Eaves I, Pienitz R, Prairie YT (2004) Tailoring palaeolimnological diatom-based transfer functions. Can J Fish Aquat Sci 61:2440–2454
Reed R (1993) Pruning algorithms – a survey. IEEE Trans Neural Networks 4:740–747
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representation by back-propagating errors. Nature 323:533–536
Telford RJ, Birks HJB (2005) The secret assumption of transfer functions: a problems with spatial autocorrelation in evaluating model performance. Quaternary Sci Rev 24:2173–2179
ter Braak CJF, van Dam H (1989) Inferring pH from diatoms: a comparison of old and new calibration methods. Hydrobiologia 178:209–223
ter Braak CJF, Juggins S (1993) Weighted averaging partial least squares regression (WA-PLS): an improved method for reconstructing environmental variables from species assemblages. Hydrobiologia 269/270:485–502
ter Braak CJF, Juggins S, Birks HJB, van der Voet H (1993) Weighte daveraging partial least squares regression (WA-PLS): Definition and comparison with other methods for species–environment calibration. In Patil GP, Rao CR (eds) Multivariate Environmental Statistics. Elsevier Science Publishers, Amsterdam, pp 525–560
Thimm G, Fiesler E (1997) Pruning of neural networks. IDIAP Research Report 97–03. Dalle Molle institute for perceptive artificial intelligence. Martigny, Valais, Switzerland
Vasko K, Toivonen HTT, Korhola A (2000) A Bayesian Multinomial Gaussian Response Model for organism-based environmental reconstruction. J Paleolimnol 24:243–250
Walker IR, Smol JP, Engstrom DR, Birks HJB (1991) An assessment of Chironomidae as quantitative indicators of past climatic-change. Can J Fish Aquat Sci 48:975–987
Yacoub M, Bennani Y (1997) “HVS: A heuristic for variable selection in multilayer artificial neural network classifier”, international conference on artificial neural networks and intelligent engineering, ANNIE ’97, Missouri, USA
Acknowledgements
We would like to thanks John Birks, Christian Bigler, Marie-Andrée Fallu, Irene Gregory-Eaves, Dörte Köster, Isabelle Larocque, Aline Philibert and Ian Walker for their permission to use their calibration data set. PaleoNet was developed at the University of Nouvelle Calédonie. The development of this software has benefitted from support obtained through the NSERC-CRO project “Late Pleistocene Paleoclimate of Eastern Beringia” awarded to Les Cwynar, from NSERC operating grants awarded to R. Pienitz and Y.T. Prairie and from the Conseil National de la Recherche grants awarded to R. Racca.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Racca, J.M.J., Racca, R., Pienitz, R. et al. PaleoNet: new software for building, evaluating and applying neural network based transfer functions in paleoecology. J Paleolimnol 38, 467–472 (2007). https://doi.org/10.1007/s10933-006-9082-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10933-006-9082-x