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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2011-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/11/8/7530/ |
| _version_ | 1811184917247164416 |
|---|---|
| author | Yu-Hsin Cheng Yung-Hsiang Lee Chung-Ru Ho Nan-Jung Kuo Feng-Chun Su |
| author_facet | Yu-Hsin Cheng Yung-Hsiang Lee Chung-Ru Ho Nan-Jung Kuo Feng-Chun Su |
| author_sort | Yu-Hsin Cheng |
| collection | DOAJ |
| description | 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%. |
| first_indexed | 2024-04-11T13:20:25Z |
| format | Article |
| id | doaj.art-9a6a216df8e34f81a867ee63087521be |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:20:25Z |
| publishDate | 2011-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9a6a216df8e34f81a867ee63087521be2022-12-22T04:22:12ZengMDPI AGSensors1424-82202011-07-011187530754410.3390/s110807530The Use of Neural Networks in Identifying Error Sources in Satellite-Derived Tropical SST EstimatesYu-Hsin ChengYung-Hsiang LeeChung-Ru HoNan-Jung KuoFeng-Chun SuAn 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%.http://www.mdpi.com/1424-8220/11/8/7530/infrared sensordata miningneural networksea surface temperaturetropical pacific |
| spellingShingle | Yu-Hsin Cheng Yung-Hsiang Lee Chung-Ru Ho Nan-Jung Kuo Feng-Chun Su The Use of Neural Networks in Identifying Error Sources in Satellite-Derived Tropical SST Estimates Sensors infrared sensor data mining neural network sea surface temperature tropical pacific |
| title | The Use of Neural Networks in Identifying Error Sources in Satellite-Derived Tropical SST Estimates |
| title_full | The Use of Neural Networks in Identifying Error Sources in Satellite-Derived Tropical SST Estimates |
| title_fullStr | The Use of Neural Networks in Identifying Error Sources in Satellite-Derived Tropical SST Estimates |
| title_full_unstemmed | The Use of Neural Networks in Identifying Error Sources in Satellite-Derived Tropical SST Estimates |
| title_short | The Use of Neural Networks in Identifying Error Sources in Satellite-Derived Tropical SST Estimates |
| title_sort | use of neural networks in identifying error sources in satellite derived tropical sst estimates |
| topic | infrared sensor data mining neural network sea surface temperature tropical pacific |
| url | http://www.mdpi.com/1424-8220/11/8/7530/ |
| work_keys_str_mv | AT yuhsincheng theuseofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT yunghsianglee theuseofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT chungruho theuseofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT nanjungkuo theuseofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT fengchunsu theuseofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT yuhsincheng useofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT yunghsianglee useofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT chungruho useofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT nanjungkuo useofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates AT fengchunsu useofneuralnetworksinidentifyingerrorsourcesinsatellitederivedtropicalsstestimates |