The Joint Technology Transfer Initiative (JTTI) ensures continuous development and transition of the latest scientific and technological advances into operations of the National Weather Service (NWS) with a focus on several themes: advancing data assimilation of new observations and data assimilation techniques for convective-scale weather prediction; improving water prediction capabilities through enhancements to National Water Model; and improving extreme precipitation forecasting.
Using machine learning to improve forecasts of excessive rainfall
Forecasters at NOAA’s Weather Prediction Center (WPC) are responsible for producing Excessive Rainfall Outlooks, which brings awareness to the potential for flood-inducing rains up to three days in advance. However, the amount of rain that qualifies as “excessive” varies from region to region, and pinpointing the specific areas likely to receive heavy rain is challenging, especially during the summer thunderstorm season. Through support from the Joint Technology Transfer Initiative, researchers from Colorado State University developed a forecast system that uses past forecasts and observations of heavy rainfall, along with machine learning algorithms, to identify the probability of flood-producing rains across the US at forecast lead times of 2-3 days. Close collaboration between the CSU scientists and WPC staff allowed for this forecast system to be transitioned into operational use, so that WPC forecasters now have an additional tool to bring awareness to areas that are at risk of potentially destructive and deadly heavy rain and flooding.
If you have questions or ideas, please contact us at email@example.com.
JTTI Program Overview Download
2019 JTTI Projects