Watershed Similarity Analysis for Military Applications Using Supervised-unsupervised Artificial Neural Networks

Incorporation of Geographic Information Systems (GIS) into Unsupervised-Supervised Artificial Neural Networks (ANNs) was applied to quantify the similarity of watershed characteristics. The goal of this approach is to find the best match watershed from a large knowledge base of over one thousand quantifying watersheds and to determine the reliability of “transplant” watershed information during the clustering and classification stages. The prediction stage of the study compares the hydrographs between this unknown watershed and the best-selected watershed to verify the similarity performance. Three examples demonstrate use of random selection, average size, and median size watersheds to test the reliability of developing procedures. It is shown that the basin area ratio provides a reasonable conversion factor for adjusting the magnitude of the predictive hydrograph. While the monthly hydrographs comparison receives very satisfactory agreement, the daily hydrographs comparison also obtains reasonable results when a high degree of similarity is found in the knowledge base.