Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models

Abstract We tested the potential of artificial neural networks (ANNs) as predictive tools in ecology. We compared the performance of ANNs and regression models (RM) in predicting ecosystems attributes, with special emphasis on temporal (interannual) predictions of functional attributes of the ecosystem at regional scales. We tested the predictive power of ANNs and RMs using simulated data for six functional traits derived from the seasonal course of the normalized difference vegetation index (NDVI): the annual integral of the NDVI curve (NDVI-I), the maximum (MAX) and minimum (MIN) NDVI, the date of the MAX NDVI (DM) and the date of start (SGS) and end (EGS) of the growing season. For one of these traits (NDVI-I), we also generated a set of data that incorporated the effects of the state of the system in previous years (inertial effects). Even simple non-linearities in the actual functional form of the relationship between environmental variables and ecosystem attributes preclude a precise prediction of these attributes when the rules are not explicit. That was evident for predictions based on both ANNs and RMs under absolutely deterministic conditions (error-free scenario). Non-linearities in the simulated traits of the NDVI curve derive from multiplicative terms in the models. Under the presence of these non-linear terms, a different aggregation of the driving variables (monthly vs. annual or quarterly climatic data) reduce substantially the ability of both RMs and ANNs to predict the independent variable. For the six traits analyzed, the ANNs were able to make better predictions than RMs. The correlation between observed and predicted values of each of the six traits considered was higher for the ANNs than for the RMs. ANNs showed clear advantages to capture inertial effects. The ANN used was able to use previous year information on climate to estimate current year NDVI-I much better than the RM that used the same input information.

[1]  W. Parton,et al.  Primary Production of the Central Grassland Region of the United States , 1988 .

[2]  C. Field,et al.  A reanalysis using improved leaf models and a new canopy integration scheme , 1992 .

[3]  George P. Malanson,et al.  Realized versus fundamental niche functions in a model of chaparral response to climatic change , 1992 .

[4]  Z. K. Liu,et al.  Classification of remotely-sensed image data using artificial neural networks , 1991 .

[5]  D. Currie,et al.  Global patterns of animal abundance and species energy use , 1993 .

[6]  D. McCann.  A Neural Network Short-Term Forecast of Significant Thunderstorms , 1992 .

[7]  O. Sala,et al.  Effect of animal husbandry on herbivore-carrying capacity at a regional scale , 1992, Nature.

[8]  Bruce K. Wylie,et al.  Satellite and ground-based pasture production assessment in Niger: 1986-1988 , 1991 .

[9]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[10]  J. Paruelo,et al.  Biozones: vegetation units defined by functional characters identifiable with the aid of satellite sensor images , 1992 .

[11]  D. Lloyd,et al.  A phenological classification of terrestrial vegetation cover using shortwave vegetation index imagery , 1990 .

[12]  A. Diouf,et al.  AVHRR monitoring of savanna primary production in Senegal, West Africa: 1987-1988 , 1991 .

[13]  Steven W. Running,et al.  A vegetation classification logic-based on remote-sensing for use in global biogeochemical models , 1994 .

[14]  José M. Paruelo,et al.  REGIONAL PATTERNS OF NORMALIZED DIFFERENCE VEGETATION INDEX IN NORTH AMERICAN SHRUBLANDS AND GRASSLANDS , 1995 .

[15]  S. Prince.  Satellite remote sensing of primary production: comparison of results for Sahelian grasslands 1981-1988 , 1991 .

[16]  W. K. Lauenroth,et al.  Inertia in Plant Community Structure: State Changes After Cessation of Nutrient‐Enrichment Stress , 1995 .

[17]  D. Milchunas,et al.  Quantitative Effects of Grazing on Vegetation and Soils Over a Global Range of Environments , 1993 .

[18]  Philip D. Wasserman,et al.  Advanced methods in neural computing , 1993, VNR computer library.

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

[20]  S. McNaughton,et al.  Ecosystem-level patterns of primary productivity and herbivory in terrestrial habitats , 1989, Nature.

[21]  I. Kanellopoulos,et al.  Land-cover discrimination in SPOT HRV imagery using an artificial neural network - a 20-class experiment , 1992 .

[22]  H. L. Houérou,et al.  Relationship between the variability of primary production and the variability of annual precipitation in world arid lands , 1988 .

[23]  O. Sala,et al.  Long-Term Forage Production of North American Shortgrass Steppe. , 1992, Ecological applications : a publication of the Ecological Society of America.

[24]  George L. Ball,et al.  Neural network architectures for monitoring and stimulating changes in forest resource management , 1995 .

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

[26]  Compton J. Tucker,et al.  Satellite remote sensing of total herbaceous biomass production in the Senegalese Sahel - 1980-1984 , 1985 .

[27]  David S. Schimel,et al.  Texture, climate, and cultivation effects on soil organic matter content in U.S. grassland soils , 1989 .

[28]  A. Fischer.  A model for the seasonal variations of vegetation indices in coarse resolution data and its inversion to extract crop parameters , 1994 .

[29]  K. Cole.  Past Rates of Change, Species Richness, and a Model of Vegetational Inertia in the Grand Canyon, Arizona , 1985, The American Naturalist.

[30]  J. Paruelo,et al.  Relative Abundance of Plant Functional Types in Grasslands and Shrublands of North America , 1996 .

[31]  D. Kleinbaum,et al.  Applied Regression Analysis and Other Multivariate Methods , 1978 .

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