Seventh Conference on Artificial Intelligence and its Applications to the Environmental Sciences
23rd Conference on Hydrology


A Simple Data-Driven Model for Streamflow Prediction

Valliappa Lakshmanan, CIMMS/Univ. of Oklahoma, NOAA/NSSL, Norman, OK; and J. J. Gourley, Z. Flamig, and S. Giangrande

It is sometimes useful to create a statistical model to predict streamflow based on precipitation estimates over a basin. Because the model is independent of physical descriptions of the basin or initial states such as soil moisture conditions, soil infiltration characteristics, or land surface roughness, it can be used to justify the complexity required in a hydrologic model to adequately simulate streamflow.

In this paper, we developed a data-driven streamflow prediction model using observations of rainfall and runoff over the heavily instrumented Ft. Cobb basin in western Oklahoma. The statistical model was developed using five rainfall events and subsequent streamflow observations. Similarly, we calibrated two additional models using the same rainfall events that are based on a) a conceptual understanding of infiltration and runoff mechanisms and b) a spatially distributed, physical description of runoff production. Following the calibration period, each model was evaluated on independent events, including an event with a 100-year return period. This study addresses the concept of model parsimony and behavior in response to extreme events.

extended abstract  Extended Abstract (220K)

wrf recording  Recorded presentation

Joint Session 6, Hydrology and AI: Status and Applications–I
Tuesday, 13 January 2009, 11:00 AM-12:00 PM, Room 125A

Previous paper  Next paper

Browse or search entire meeting

AMS Home Page