You are here:
System learning approach to assess sustainability and forecast trends in regional dynamics: The San Luis Basin study, Colorado, U.S.A.
Citation:
Gonzalez, A., T. Eason, AND H. Cabezas. System learning approach to assess sustainability and forecast trends in regional dynamics: The San Luis Basin study, Colorado, U.S.A. ENVIRONMENTAL MODELLING & SOFTWARE. Elsevier Science, New York, NY, 81:01-11, (2016).
Impact/Purpose:
Indicators are indispensable for tracking conditions in human and natural systems, however, available data is sometimes far out of date and limit the ability to gauge system status. Techniques like regression and simulation are not sufficient because system characteristics have to be modeled ensuring over simplification of complex dynamics. This work presents a methodology combining the power of an Artificial Neural Network and Information Theory to capture patterns in a real dynamic system. The novelty and strength of this approach is in the application of Fisher information to preserve trends (1969-2010) without over fitting the neural network model projections; thereby, bounding the forecast (2011-2025). This methodology was applied to demographic, environmental, food and energy consumption, and agricultural production variables describing the San Luis Basin regional system in Colorado, U.S. Results indicate that the approaches developed provide viable assessments and future scenarios beneficial for management toward sustainability.
Description:
This paper presents a methodology that combines the power of an Artificial Neural Network and Information Theory to forecast variables describing the condition of a regional system. The novelty and strength of this approach is in the application of Fisher information, a key method in Information Theory, to preserve trends in the historical data and prevent over fitting projections. The methodology was applied to demographic, environmental, food and energy consumption, and agricultural production in the San Luis Basin regional system in Colorado, U.S.A. These variables are important for tracking conditions in human and natural systems. However, available data are often so far out of date that they limit the ability to manage these systems. Results indicate that the approaches developed provide viable tools for forecasting outcomes with the aim of assisting management toward sustainable trends. This methodology is also applicable for modeling different scenarios in other dynamic systems.
