DocumentCode :
484521
Title :
Hybrid Neural Network Technique to Estimate Rainfall from TRMM Measurements
Author :
Chandrasekar, V. ; Alqudah, Amin ; Wang, Yanting
Author_Institution :
Colorado State Univ., Fort Collins, CO
Volume :
4
fYear :
2008
fDate :
7-11 July 2008
Abstract :
Neural network is a nonparametric method to represent the relationship between radar measurements and rainfall rate. The relationship is derived directly from a dataset consisting of radar measurements and rain gauge measurements. Tropical Rainfall measuring Mission (TRMM) Precipitation Radar (PR) is known to be the first observation platform for mapping precipitation over the tropics. TRMM measured rainfall is important in order to study the precipitation distribution all over the globe in the tropics. TRMM ground validation is a critical important component in TRMM system. However, the ground sensing systems have quite different characterizations from TRMM in terms of resolution, scale, viewing aspect, and uncertainties in the sensing environments. In this paper a novel hybrid Neural Network model is presented to train ground radars for rainfall estimation using rain gage data and subsequently using the trained ground radar rainfall estimation to train TRMM PR based Neural networks. One year of ground data from Melbourne Florida and Houston Texas are used to demonstrate this hybrid approach. The performance of the rainfall product estimated from TRMM PR is compared against TRMM standard products. A direct gage comparison study is done to demonstrate the improvement brought in by the neural networks.
Keywords :
geophysics computing; meteorological instruments; meteorological radar; neural nets; rain; remote sensing by radar; Houston Texas; Melbourne Florida; Neural Network model; TRMM Precipitation Radar; Tropical Rainfall measuring Mission; USA; atmospheric precipitation distribution; atmospheric precipitation mapping; ground sensing systems; hybrid neural network technique; radar measurements; rain gauge measurements; rainfall estimation; Meteorological radar; Neural networks; Radar measurements; Rain; Reflectivity; Shape; Spaceborne radar; Spatial resolution; State estimation; Uncertainty; Neural networks; Precipitation; radar rainfall estimation; weather radar;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-2807-6
Electronic_ISBN :
978-1-4244-2808-3
Type :
conf
DOI :
10.1109/IGARSS.2008.4779715
Filename :
4779715
Link To Document :
بازگشت