A novel method for training neural networks for time-series prediction in environmental systems

Matthew Aitkenhead, Allan James Stuart McDonald, L. A. Dawson, G. Couper, R. P. Smart, M. Billett, D. Hope, S. Palmer

Research output: Contribution to journalArticlepeer-review

23 Citations (Scopus)


Soil, streamwater and climatic variables were measured hourly over several month periods in two situations in North-East (NE) Scotland, using data loggers and other measuring instruments. One of the locations was on agricultural land near Inverness while the other was at an acidic peat moorland site in the River Dee catchment. The data sets were used to train neural networks using three different methods, including a novel, biologically plausible system. Temporal pattern recognition capabilities using each method were investigated. The novel method proved equally capable in predicting future variable values using large data sets as the other two methods. An argument is made for this method, termed the 'Local Interaction' method, providing valid competition to other neural network and statistical methods in the detection of patterns and prediction of events in complex biological systems. (C) 2002 Elsevier Science B.V. All rights reserved.

Original languageEnglish
Pages (from-to)87-95
Number of pages8
JournalEcological Modelling
Issue number1-2
Early online date28 Jan 2003
Publication statusPublished - Apr 2003


  • stream dynamics
  • time-series prediction
  • neural networks
  • simulated annealing
  • backpropagation
  • environmental prediction

Cite this