碩士 / 國立海洋大學 / 海洋科學系 / 90 / Traditional bio-optical algorithm uses regression method to derive chlorophyll concentration form radiance, such as the OC2 algorithm for the Sea-viewing Wide Field-of-view Sensor (SeaWiFS). In this study, a back propagation neural network is employed to set up the bio-optical algorithm between chlorophyll concentration in the oceans and radiance from the oceans. The advantages of the neural network algorithm are 1) the ability for solving the non-linear transfer function between chlorophyll concentration and radiance is better than that of regression method. 2) it uses the information of all bands instead of the two-band ratio of traditional algorithm.
Bio-optical data from SeaWiFS Bio-optical Algorithm Mini-workshop (SeaBAM) were used to develop and verify the neural network algorithm. The result show that the coefficient of determination ( R ) for the neural network algorithm is 0.98 and the root-mean-square (RMS) error of derived chlorophyll concentration is 0.59 ug/l. They are much better than the results of version 2 of OC2 (OC2v2) algorithm, while the R is 0.56 and the RMS error is 2.84 ug/l.
| Identifer | oai:union.ndltd.org:TW/090NTOU0276006 |
| Date | January 2002 |
| Creators | Feng-Chiung Su, 蘇蜂鈞 |
| Contributors | Chung-Ru Ho, 何宗儒 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 80 |
Page generated in 0.0014 seconds