Modeling net ecosystem metabolism with an artificial neural network and Bayesian belief network

  • Authors:

  • William A. Young, II;David F. Millie;Gary R. Weckman;Jerone S. Anderson;David M. Klarer;Gary L. Fahnenstiel

  • Affiliations:

  • Department of Industrial and Systems Engineering, Russ College of Engineering and Technology, Ohio University, Stocker Center 285, Athens, OH 45701-2979, USA;Florida Institute of Oceanography, University of South Florida, Saint Petersburg, FL 33701, USA;Department of Industrial and Systems Engineering, Russ College of Engineering and Technology, Ohio University, Stocker Center 285, Athens, OH 45701-2979, USA;Department of Industrial and Systems Engineering, Russ College of Engineering and Technology, Ohio University, Stocker Center 285, Athens, OH 45701-2979, USA;Old Woman Creek National Estuarine Research Reserve, Ohio Department of Natural Resources, West, Huron, OH 44839, USA;Great Lakes Environmental Research Laboratory, Lake Michigan Field Station, National Oceanic and Atmospheric Administration, Muskegon, MI 49441, USA

  • Venue:
  • Environmental Modelling & Software
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Artificial neural networks (ANNs) and Bayesian belief networks (BBNs) utilizing select environmental variables were developed and evaluated, with the intent to model net ecosystem metabolism (a proxy for system trophic state) within a freshwater wetland. Network modeling was completed independently for distinct data subsets, representing periods of 'low' and 'high' water levels throughout in the wetland. ANNs and BBNs were 'benchmarked' against traditional parametric analyses, with network architectures outperforming regression models. ANNs delivered the greatest predictive accuracy for NEM and did not require expert knowledge about system variables for their development. BBNs provided users with an interactive diagram depicting predictor interaction and the qualitative/quantitative effects of variable dynamics upon NEM, thereby affording better information extraction. Importantly, BBNs accommodated the imbalanced nature of the dataset and appeared less affected (than ANNs) with variable auto-correlation traits that are typically observed within large and 'noisy' environmental datasets.