What is it about?

During flooding events, decision makers and first responders depend on streamflow and flood inundation information for situational awareness, giving them the ability to effectively allocate resources, enable evacuations, and reduce property losses. Risk awareness is largely dependent on the collection, analysis, and communication of accurate hydrologic data from various sources, one of the most important being real-time and historical streamflow data provided by U.S. Geological Survey (USGS) streamgages. Losing near-real time streamgage data can make a difference between life or death, loss of property, or travel time with safety.

Featured Image

Why is it important?

These gages can be damaged by high water and debris, however, and stop transmitting data. Because uninterrupted transmittal of accurate streamflow data is critical for hydrological prediction systems and effective decision-making based on flood forecasts and unfolding real-time events, any missing data due to disruption has significant and wide-ranging implications (NHWC, 2006; Holmes et al., 2012).


To address this issue, the weather forecasting community has long sought to develop functioning and effective streamflow prediction models, the importance of which is reflected in a growing body of literature that focuses on streamflow dynamics. Streamflow Hydrology Estimate using Machine Learning (SHEM) research addresses whether a predictive estimate can accurately replicate actual streamflow data during a streamgage failure scenario, and do so in a sufficiently timely manner to be useful to decision makers and first responders.

Dr. Tim Petty
University of Alaska Fairbanks

Read the Original

This page is a summary of: Streamflow Hydrology Estimate Using Machine Learning (SHEM), JAWRA Journal of the American Water Resources Association, August 2017, Wiley,
DOI: 10.1111/1752-1688.12555.
You can read the full text:




The following have contributed to this page