|
Image Processing
|
A Neural Network Model for estimating Surface Chlorophyll and Sediment Content at the Lake Kasumi Gaura of Japan
5. Conclusion
The Neural Network model was able to model the transfer function to a much higher accuracy than multiple regression analysis as expected. The performance of the NN model varies with varying number of hidden layer nodes. The model could not represent the higher values of Chl-a satisfactorily. For a more effective and accurate model to represent the water quality of the site under investigation, the author proposes collection of larger data set including measurements of other primary components believed to contribute to the lake water color such Chromophoric dissolved oxygen material(CDOM) in coincidence with overpass of modern satellite sensor(such as Landsat TM or SeaWIFS).
References
- Keiner, L.E. and Yan, X.H., 1998. A Neural Network Model for Estimating Sea Surface Chlorophyll and Sediments from Thematic Mapper Imagery. Remote Sensing of Environment, Elsevier, 66:153-165.
- Masters, T, 1993. Practical Neural Network Recipes in C++. Academis Press, 491pp.
- Oki, H, 1997. Study of Lake basin Land use and its Impact on Lake Water Quality. Doctoral Thesis, University of Tsukuba Library, 141pp.
- Rumelhart, D., Hinton, G.E., and Williams, R.J., 1986a. Learning Representations by back-propagating errors. Nature (London), 323, pp533-536.
|
|
|
|
|
