Using an artificial neural network to characterize the relative suitability of environments for forest types in a complex tropical vegetation mosaic

Summary A predictive understanding of the environmental controls on forest distributions is essential for the conservation of biodiversity and management of landscapes in the tropics. This is particularly true now because of potentially rapid climate change. The floristic complexity of tropical forests and the lack or absence of data severely limits the applicability of modelling methods based on the ecology or distribution of individual species. Here we present an artificial neural network (ANN) model using the information available in the humid tropics of North Queensland: a structural classification of forest types, maps of the forest mosaic, and estimates of spatial environmental variables. The ANN model characterizes the relative suitabilities of environments for 15 forest classes defined by their physiognomy and canopy structure. Inputs include seven climate variables, nine soil parent-material classes, and seven terrain variables. The data used to train the model consisted of a stratified random sample of 75000 points. Output of the model is used to measure the dissimilarity between the environment at each location and the environment that would be most suitable for the forest type that is mapped there. The model is highly successful at distinguishing the relative suitability of environments for the forest classes with 75% of the region's forest mosaic accurately predicted by the model at a one hectare resolution. In contrast, a comparable maximum likelihood classification has an accuracy of only 38%. In the remaining 25% of the region the environments are quite dissimilar to what would be expected for the forest types present there. This is especially the case at boundaries between forest classes and for a transitional forest class. Areas mapped as this disturbed, transitional class are generally classified by the model as having environments suitable to the forest type they are most likely to become. The approach has high potential for the analysis of climate change impacts as well as inferring vegetation patterns in the past and should be applicable wherever vegetation maps and spatial estimates of climate variables are available.

[1]  C. Peng,et al.  simulating carbon dynamics along the Boreal Forest Transect Case Study (BFTCS) in central Canada: 2. Sensitivity to climate change , 1998 .

[2]  James F. Reynolds,et al.  7 – Scaling Ecophysiology from the Plant to the Ecosystem: A Conceptual Framework , 1993 .

[3]  M. Hopkins,et al.  Evidence of a Holocene and continuing recent expansion of lowland rain forest in humid, tropical North Queensland , 1996 .

[4]  A. Starfield,et al.  TIME LAGS AND NOVEL ECOSYSTEMS IN RESPONSE TO TRANSIENT CLIMATIC CHANGE IN ARCTIC ALASKA , 1997 .

[5]  A role-type model (rope) and its application in assessing climate change impacts on forest landscapes , 1995 .

[6]  Ronald P. Neilson,et al.  A rule-based vegetation formation model for Canada , 1993 .

[7]  W. B. Yates,et al.  Classification of remotely sensed data by an artificial neural network: issues related to training data characteristics , 1995 .

[8]  A. Markham.  Potential impacts of climate change on ecosystems: a review of implications for policymakers and conservation biologists , 1996 .

[9]  Daniel G. Brown,et al.  Supervised classification of types of glaciated landscapes using digital elevation data , 1998 .

[10]  H. R. Gimblett,et al.  Applying neural networks to vegetation management plan development , 1997 .

[11]  A. Solomon,et al.  Boreal forest carbon stocks and wood supply: past, present and future responses to changing climate, agriculture and species availability , 1997 .

[12]  Sandra Díaz,et al.  Plant functional traits and environmental filters at a regional scale , 1998 .

[13]  H. Shugart,et al.  The transient response of terrestrial carbon storage to a perturbed climate , 1993, Nature.

[14]  M. Hopkins,et al.  Charcoal evidence of the spatial extent of the Eucalyptus woodland expansions and rainforest contractions in North Queensland during the late Pleistocene , 1993 .

[15]  F. Stuart Chapin,et al.  Model of Transient Changes in Arctic and Boreal Vegetation in Response to Climate and Land Use Change , 1996 .

[16]  R. Hebda.  Atmospheric Change, Forests and Biodiversity , 1998 .

[17]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[18]  W. Baker,et al.  Using GIS to model tree population parameters in the Rocky Mountain National Park forest–tundra ecotone , 1997 .

[19]  L. Webb.  Environmental Relationships of the Structural Types of Australian Rain Forest Vegetation , 1968 .

[20]  G. Hoogenboom,et al.  Development of a neural network model to predict daily solar radiation , 1994 .

[21]  L. Webb,et al.  A Physiognomic Classification of Australian Rain Forests , 1959 .

[22]  Angela Lee,et al.  Perspectives on … Environmental Systems Research Institute, Inc , 1997 .

[23]  R. Monserud,et al.  Change in Siberian phytomass predicted for global warming. , 1996 .

[24]  A. Solomon,et al.  Climate Change and Terrestrial Biomass: What if Trees do not Migrate? , 1997 .

[25]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[26]  W. Silver.  The Potential Effects of Elevated Co2 and Climate Change on Tropical Forest Soils and Biogeochemical Cycling , 1998 .

[27]  Thomas M. Smith,et al.  Modeling the Potential Response of Vegetation to Global Climate Change , 1992 .

[28]  Richard Lippmann,et al.  Neural Network Classifiers Estimate Bayesian a posteriori Probabilities , 1991, Neural Computation.

[29]  Fernando Gustavo Tomasel,et al.  Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models , 1997 .

[30]  E. Schulze.  Plant Life Forms and Their Carbon, Water and Nutrient Relations , 1982 .

[31]  B. Turner,et al.  Performance of a neural network: mapping forests using GIS and remotely sensed data , 1997 .

[32]  Wolfgang Cramer,et al.  A simulation model for the transient effects of climate change on forest landscapes , 1993 .

[33]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[34]  T. A. Kursar.  Relating Tree Physiology to Past and Future Changes in Tropical Rainforest Tree Communities , 1998 .

[35]  R. G. Oderwald,et al.  Assessing Landsat classification accuracy using discrete multivariate analysis statistical techniques. , 1983 .

[36]  A. Fischlin,et al.  Assessing impacts of climatic change on forests in the Alps , 1997 .

[37]  V. E. Derr,et al.  Prediction of El Nino events in the Pacific by means of neural networks , 1995 .