Inspired by the functioning of the brain and biological nervous systems, artificial neural networks (ANNs) have been applied to various hydrologic problems in the last 10 years. In this study, ANN models are compared with traditional conceptual models in predicting watershed runoff as a function of rainfall, snow water equivalent, and temperature. The ANN technique was applied to model watershed runoff in three basins with different climatic and physiographic characteristics—the Fraser River in Colorado, Raccoon Creek in Iowa, and Little Patuxent River in Maryland. In the Fraser River watershed, the ANN technique was applied to model monthly streamflow and was compared to a conceptual water balance (Watbal) model. The ANN technique was used to model the daily rainfall-runoff process and was compared to the Sacramento soil moisture accounting (SAC-SMA) model in the Raccoon River watershed. The daily rainfall-runoff process was also modeled using the ANN technique in the Little Patuxent River basin, and the...

Trend analysis of annual flood peaks on 12 small urbanizing watersheds in northeastern Illinois indicated that annual peaks, and thus frequency and impact of flooding, increased over the past several decades. An increase in flood peaks could be attributed to intensive urbanization and increasing incidences of heavy rainfall. Average urbanization of the 12 watersheds increased significantly from 10.6% in 1954 to 61.8% in 1996. In addition, numerous studies have reported increasing frequency and intensity of heavy rainfall in the region. This outcome is consistent with lower design rainfall estimates produced by older studies, such as U.S. Weather Bureau Technical Paper No. 40 (TP-40), compared to more recent sources, such as National Oceanic and Atmospheric Administration Atlas-14. This study used a design storm approach and the Hydrologic Engineering Center for Hydrologic Modeling System (HEC-HMS) model to calculate design flood peaks. Hydrologic model parameters were calibrated using hourly rainfall-runo...