Cargando…

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

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Lee, Yung-Hsiang, Ho, Chung-Ru, Su, Feng-Chun, Kuo, Nan-Jung, Cheng, Yu-Hsin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Molecular Diversity Preservation International (MDPI) 2011
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3231724/
https://www.ncbi.nlm.nih.gov/pubmed/22164030
http://dx.doi.org/10.3390/s110807530
Descripción
Sumario: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%.