Abstract
The space-based precipitation products are commonly used for regional and/or global hydrologic modelling and climate studies. However, the accuracy of onboard satellite measurements is limited due to the spatial-temporal sampling limitations, especially for extreme events such as very heavy or light rain. On the other hand, ground-based radar is more mature science for quantitative precipitation estimation (QPE). Nowadays, ground radars are critical for providing local scale rainfall estimation for operational forecasters to issue watches and warnings, as well as validation of various space measurements and products. This paper introduces a neural network based data fusion mechanism to improve satellite-based precipitation retrievals by incorporating dual-polarization measurements from ground-based dense radar network. The prototype architecture of this fusion system is detailed. Results from urban scale application in Dallas-Fort Worth (DFW) Metroplex are presented.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
