Using neural networks to predict spatial structure in ecological systems

Matthew Aitkenhead, M. J. Mustard, Allan James Stuart McDonald

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

We describe an approach in which a neural network (NN) can be trained on sets of driving variables (inputs) and output variables relating to spatial structure. The trained NN provides a predictive tool for defining spatial structure in a specified ecological system. We demonstrate the approach using a modified version of the Crawley and May [J. Theor. Biol. 125 (1987) 475] model that describes simplified annual/perennial plant interactions in a disturbed system. The model is implemented within a cellular automaton with randomised start conditions and is run for periods of up to 50 time steps (50 years). Neural networks are trained using a large set of modelled situations, and the ability of the network to predict plant spatial distributions is then measured. Different image analysis methods are applied,to the plant array, and the ability of each method to provide an accurate description of the end-state of the modelled system is investigated. Reconstruction of the plant array from these image analysis measurements is carried out using a stochastic error minimisation method. The partial derivatives method is applied to the trained neural network in order to determine which variables input to the model most strongly influence the eventual plant population distribution. In the example presented, it is found that a relatively simple boundary:area ratio measurement provides a rapid and effective method of describing the spatial structure of the plant community, while the variables that are most influential on the system's end-state are those describing annual fecundity and perennial mortality rates. (C) 2004 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)393-403
Number of pages10
JournalEcological Modelling
Volume179
DOIs
Publication statusPublished - 2004

Keywords

  • Crawley-May
  • cellular automata
  • neural networks
  • population dynamics
  • community structure
  • POPULATION-DYNAMICS
  • NEW-ZEALAND
  • PATTERNS
  • COMMUNITY
  • ANNUALS
  • MODELS
  • PLANTS

Cite this

Using neural networks to predict spatial structure in ecological systems. / Aitkenhead, Matthew; Mustard, M. J.; McDonald, Allan James Stuart.

In: Ecological Modelling, Vol. 179, 2004, p. 393-403.

Research output: Contribution to journalArticle

Aitkenhead, Matthew ; Mustard, M. J. ; McDonald, Allan James Stuart. / Using neural networks to predict spatial structure in ecological systems. In: Ecological Modelling. 2004 ; Vol. 179. pp. 393-403.
@article{859793f7f4a849f488bdeceeea3a1e0e,
title = "Using neural networks to predict spatial structure in ecological systems",
abstract = "We describe an approach in which a neural network (NN) can be trained on sets of driving variables (inputs) and output variables relating to spatial structure. The trained NN provides a predictive tool for defining spatial structure in a specified ecological system. We demonstrate the approach using a modified version of the Crawley and May [J. Theor. Biol. 125 (1987) 475] model that describes simplified annual/perennial plant interactions in a disturbed system. The model is implemented within a cellular automaton with randomised start conditions and is run for periods of up to 50 time steps (50 years). Neural networks are trained using a large set of modelled situations, and the ability of the network to predict plant spatial distributions is then measured. Different image analysis methods are applied,to the plant array, and the ability of each method to provide an accurate description of the end-state of the modelled system is investigated. Reconstruction of the plant array from these image analysis measurements is carried out using a stochastic error minimisation method. The partial derivatives method is applied to the trained neural network in order to determine which variables input to the model most strongly influence the eventual plant population distribution. In the example presented, it is found that a relatively simple boundary:area ratio measurement provides a rapid and effective method of describing the spatial structure of the plant community, while the variables that are most influential on the system's end-state are those describing annual fecundity and perennial mortality rates. (C) 2004 Elsevier B.V. All rights reserved.",
keywords = "Crawley-May, cellular automata, neural networks, population dynamics, community structure, POPULATION-DYNAMICS, NEW-ZEALAND, PATTERNS, COMMUNITY, ANNUALS, MODELS, PLANTS",
author = "Matthew Aitkenhead and Mustard, {M. J.} and McDonald, {Allan James Stuart}",
year = "2004",
doi = "10.1016/j.ecolmodel.2004.05.008",
language = "English",
volume = "179",
pages = "393--403",
journal = "Ecological Modelling",
issn = "0304-3800",
publisher = "Elsevier Science B. V.",

}

TY - JOUR

T1 - Using neural networks to predict spatial structure in ecological systems

AU - Aitkenhead, Matthew

AU - Mustard, M. J.

AU - McDonald, Allan James Stuart

PY - 2004

Y1 - 2004

N2 - We describe an approach in which a neural network (NN) can be trained on sets of driving variables (inputs) and output variables relating to spatial structure. The trained NN provides a predictive tool for defining spatial structure in a specified ecological system. We demonstrate the approach using a modified version of the Crawley and May [J. Theor. Biol. 125 (1987) 475] model that describes simplified annual/perennial plant interactions in a disturbed system. The model is implemented within a cellular automaton with randomised start conditions and is run for periods of up to 50 time steps (50 years). Neural networks are trained using a large set of modelled situations, and the ability of the network to predict plant spatial distributions is then measured. Different image analysis methods are applied,to the plant array, and the ability of each method to provide an accurate description of the end-state of the modelled system is investigated. Reconstruction of the plant array from these image analysis measurements is carried out using a stochastic error minimisation method. The partial derivatives method is applied to the trained neural network in order to determine which variables input to the model most strongly influence the eventual plant population distribution. In the example presented, it is found that a relatively simple boundary:area ratio measurement provides a rapid and effective method of describing the spatial structure of the plant community, while the variables that are most influential on the system's end-state are those describing annual fecundity and perennial mortality rates. (C) 2004 Elsevier B.V. All rights reserved.

AB - We describe an approach in which a neural network (NN) can be trained on sets of driving variables (inputs) and output variables relating to spatial structure. The trained NN provides a predictive tool for defining spatial structure in a specified ecological system. We demonstrate the approach using a modified version of the Crawley and May [J. Theor. Biol. 125 (1987) 475] model that describes simplified annual/perennial plant interactions in a disturbed system. The model is implemented within a cellular automaton with randomised start conditions and is run for periods of up to 50 time steps (50 years). Neural networks are trained using a large set of modelled situations, and the ability of the network to predict plant spatial distributions is then measured. Different image analysis methods are applied,to the plant array, and the ability of each method to provide an accurate description of the end-state of the modelled system is investigated. Reconstruction of the plant array from these image analysis measurements is carried out using a stochastic error minimisation method. The partial derivatives method is applied to the trained neural network in order to determine which variables input to the model most strongly influence the eventual plant population distribution. In the example presented, it is found that a relatively simple boundary:area ratio measurement provides a rapid and effective method of describing the spatial structure of the plant community, while the variables that are most influential on the system's end-state are those describing annual fecundity and perennial mortality rates. (C) 2004 Elsevier B.V. All rights reserved.

KW - Crawley-May

KW - cellular automata

KW - neural networks

KW - population dynamics

KW - community structure

KW - POPULATION-DYNAMICS

KW - NEW-ZEALAND

KW - PATTERNS

KW - COMMUNITY

KW - ANNUALS

KW - MODELS

KW - PLANTS

U2 - 10.1016/j.ecolmodel.2004.05.008

DO - 10.1016/j.ecolmodel.2004.05.008

M3 - Article

VL - 179

SP - 393

EP - 403

JO - Ecological Modelling

JF - Ecological Modelling

SN - 0304-3800

ER -