Title :
Research on the fault tolerance in retrieving atmospheric refractivity by microwave radiometer data
Author :
Li Jiang-man ; Shu Ting-ting ; Guo Li-xin ; Lin Le-ke ; Zhao Zhen-wei
Author_Institution :
Sch. of Sci., Xidian Univ., Xi´an, China
Abstract :
Ground-based microwave radiometer has proven to be a powerful tool to detect the atmosphere. The common algorithms are linear regression, neural network, and relevance vector machine. A fault tolerance evaluation has been considered on the above three algorithms in retrieving atmospheric refractivity. A simulation experiment reveals that the fault tolerance of relevance vector machine is very good, while the other two are worse. To improve the fault tolerance of linear regression and neural network, we can add measurement error to the brightness temperature when training.
Keywords :
atmospheric techniques; atmospheric temperature; fault tolerance; microwave devices; neural nets; radiometers; refractive index; regression analysis; atmospheric refractivity retreival; brightness temperature; fault tolerance evaluation; ground-based microwave radiometer; linear regression algorithm; measurement error; microwave radiometer data; neural network; relevance vector machine; Artificial neural networks; Fault tolerance; Fault tolerant systems; Measurement errors; Microwave radiometry; Refractive index; Support vector machines;
Conference_Titel :
Antennas, Propagation & EM Theory (ISAPE), 2012 10th International Symposium on
Conference_Location :
Xian
Print_ISBN :
978-1-4673-1799-3
DOI :
10.1109/ISAPE.2012.6408831