Using Artificial Neural Network Models to Integrate Hydrologic and Ecological Studies of the Snail Kite in the Everglades, Usa

Hydrologists and ecologists have been working in the Everglades on integrating a long-term hydrologic data network and a short-term ecological database to support ecological models of the habitat of the snail kite, a threatened and endangered bird. Data mining techniques, including artificial neural network (ANN) models, were applied to simulate the hydrology of snail kite habitat in the Water Conservation Area 3A of the Everglades. Hydroperiods of water depths have a significant affect on the nesting and foraging of the snail kite. Seventeen water-depth recorders are co-located at transects where extensive plant samples are collected. These continuous recorders were established in 2002. A long-term network of three water-level recorders has been maintained since 1991. Using inputs representing the three long-term gages, very accurate ANN models were developed as input to predict the water depths at the 17 short-term sites. The models were then used to hindcast water depths to 1991, resulting, much longer water-level record to help scientists better learn how the snail kite's habitat is affected by changing hydrology. A Decision Support System (DSS) was developed to disseminate the models in an easily used package. The DSS is a MS Excel TM /VBA application that integrates the models and database with interactive controls and streaming graphics to run long-term simulations. As part of the Everglades restoration Interim Operating Plan (IOP), a regional hydrologic model is used to generate water levels for alternative flow regulation schedules. The alternative IOP water levels are input to the DSS to predict the hydrology of the snail kite habitat. The application demonstrates how very accurate empirical models can be built directly from data and readily deployed to end-users to support interdisciplinary studies. Figure 1. Mapping showing study area and location of continuous gaging stations. Figure 1. Mapping showing study area and location of continuous gaging stations.