The Use of Neural Networks in Identifying Error Sources in Satellite-Derived Tropical SST Estimates

Sensors

Yung-Hsiang Lee²  Chung-Ru Ho²  Feng-Chun Su¹  Nan-Jung Kuo² 

[1] Department of Marine Biotechnology and Resources, National Sun Yat-sen University, Kaohsiung 80424, Taiwan; E-Mail:;Department of Marine Environmental Informatics, National Taiwan Ocean University, Keelung 20224, Taiwan; E-Mails:

关键词: infrared sensor;    data mining;    neural network;    sea surface temperature;    tropical pacific;   

DOI  :  10.3390/s110807530

来源: mdpi

【 摘 要 】

An neural network model of data mining is used to identify error sources in satellite-derived tropical sea surface temperature (SST) estimates from thermal infrared sensors onboard the Geostationary Operational Environmental Satellite (GOES). By using the Back Propagation Network (BPN) algorithm, it is found that air temperature, relative humidity, and wind speed variation are the major factors causing the errors of GOES SST products in the tropical Pacific. The accuracy of SST estimates is also improved by the model. The root mean square error (RMSE) for the daily SST estimate is reduced from 0.58 K to 0.38 K and mean absolute percentage error (MAPE) is 1.03%. For the hourly mean SST estimate, its RMSE is also reduced from 0.66 K to 0.44 K and the MAPE is 1.3%.

【 授权许可】

CC BY   
© 2011 by the authors; licensee MDPI, Basel, Switzerland.