Skip to main content
Advanced Search

Filters: Tags: regional scale (X)

2 results (44ms)   

View Results as: JSON ATOM CSV
The cascade correlation neural network was used to predict the two-year peak discharge (Q2) for major regional river basins of the continental United States (US). Watersheds ranged in size by four orders of magnitude. Results of the neural network predictions ranged from correlations of 0.73 for 104 test data in the Souris-Red Rainy river basin to 0.95 for 141 test data in California. These results are improvements over previous multilinear regressions involving more variables that showed correlations ranging from 0.26 to 0.94. Results are presented for neural networks trained and tested on drainage area, average annual precipitation, and mean basin elevation. A neural network trained on regional scale data in the...
This site is for data and information compilation and sharing related to the work of the Predictive Understanding of Multiscale Processes (PUMP) project. PUMP is advancing multi-scale, integrated modeling capabilities to address priority water resource issues within the Integrated Water Prediction (IWP) program, Integrated Water Science (IWS) Basin studies, Integrated Water Availability Assessments (IWAAs), and other relevant Water Mission Area (WMA) project efforts. Development and testing of modeling approaches occurs at multiple scales spanning national and sub-national domains.  Models will leverage physical process-driven approaches, data-driven approaches (statistical and machine learning (ML)), and hybrid...