Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison between Neural Network and Conventional Statistical Analysis Methods for Estimation of Water Quality Using Remote Sensing

원격탐사를 이용한 수질평가시의 인공신경망에 의한 분석과 기존의 회귀분석과의 비교

  • Published : 1999.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

A comparison of a neural network approach with the conventional statistical methods, multiple regression and band ratio analyses, for the estimation of water quality parameters in presented in this paper. The Landsat TM image of Lake Daechung acquired on March 18, 1996 and the thirty in-situ sampling data sets measured during the satellite overpass were used for the comparison. We employed a three-layered and feedforward network trained by backpropagation algorithm. A cross validation was applied because of the small number of training pairs available for this study. The neural network showed much more successful performance than the conventional statistical analyses, although the results of the conventional statistical analyses were significant. The superiority of a neural network to statistical methods in estimating water quality parameters is strictly because the neural network modeled non-linear behaviors of data sets much better.

본 연구에서는 원격탐사를 이용하여 수질 파라미터들을 평가하는데 기존의 다중 회귀나 밴드비 회귀 분석을 이용한 통계적인 방법과 신경망을 이용한 방법을 비교하였다. 사용된 영상은 1996년 3월 18일 대청호 유역의 Landsat TM 영상이며, 30개의 현장 실측치가 위성이 통과하는 시간대에 샘플링되었다. 적용된 신경망은 3개의 층으로 구성된 전향 신경망이며 훈련방법으로는 역전파를 사용하였다. 본 연구에서는 가용한 훈련 데이터 셀이 작으므로 cross-validation 방법이 적용되었다. 비록 기존의 회귀분석에 의한 결과도 어느 정도 유의하게 나왔지만, 신경망에 의한 결과가 훨씬 성공적인 수행을 보여주었다. 신경망을 이용한 수질평가는 신경망이 자료의 비선형적 속성을 잘 반영해주기 때문에 기존의 통계적 기법보다 훨씬 나은 결과를 제공한다고 판단된다.

Keywords

References

  1. International Journal of Remote Sensing v.19 no.8 Wetland classification using optical and radar data and neural network classification Augusteijn, M.F.;C.E. Warrender
  2. International Journal of Remote Sensing v.14 Detecting water quality paramenters in Norfolk Broads, U.K., using Landsat imagery Baban, S.M.J.
  3. Estuarine, Coastal and Shelf Science v.44 Environmental Monitoring of Estuaries;Estimating and Mapping Various Environmental Indicators in Breydon Water Estuary, U.K., using Landsat TM Imagery Baban, S.M.J.
  4. Neural Computing: an Introduction Beale, R.;T. Jackson
  5. IEEE Transactions on Geoscience and Remote Sensing v.30 no.3 Multispectral classification of Landsat-Images using neural networks Bishof, H.;W. Schneider;A.J. Pinz
  6. Journal of Marine System v.9 no.4 Chlorophyll estimation in the southeastern Mediterranean using CZCS images: Adaptation of an algorithm and its validation Gitelson, A.(et al.)
  7. Applied Optics v.22 Phytoplankton pigment concentrations in the Middle Atlantic Bight: Comparison of ship determinations and CZCS estimates Gordon, H.(et al.)
  8. Water Quality Evaluation for Coastal Waters and Lake Sihwa Using Remote Sensing Techniques Jeong, J.C.
  9. Pattern Recognition and Image Analysis Gose, E.R.;Johnsonbaugh;S. Jost
  10. The Satellite Remote Sensing of Environmental Processes in Delaware Bay Keiner, L.
  11. Assessment of Lake Water Quality Using LANDSAT TM Imagery Data Kim, T.K.
  12. Journal of Geophysical Research v.100 A neural network as a nonlinear transfer model for retrieving surface wind speeds from the special sensor microwave imager Krasnopolsky, V.;L. Breaker;W. Gemmill
  13. IEEE Conference of on Neural Networks Proceedings v.5 Efficient cross-validation for feedforward neural networks Kwok, T.Y.;D.Y. Teung
  14. Photogrammetric Engineering and Remote Sensing v.52 Use of Thematic Mapper data to assess water quality in Green Bay and central Lake Michiga Lathrop, R.;T. Lillesand
  15. Practical neural network recipes in C++ Masters, T.
  16. International Journal of Remote Sensing v.15 Estimates of water quality in coastal waters using multi-data Landsat Thematic Mapper data Pattiaratch, C.(et al.)
  17. C++ Neural Networks & Fuzzy Logic Rao, V.B.;H.V. Rao
  18. Remote Sensing of Environment v.33 The relationship of MSS and TM digital data with suspended sediments, shlorophyll and temperature in Moon Lake Ritchie, J.;C. Cooper;F. Shciebe
  19. International Journal of Remote Sensing v.14 An Improved in-water algorithm for the determination of chlorophll and suspended sediment concentration from Thematic Mapper data in coastal waters Tassan, S.
  20. Journal of Geophysical Research v.98 A neural network approach for modeling nonlinear trasfer functions: Application for wind retrieval from spaceborne scatterometer data Thiria, S.(et al.)
  21. Remote Sensing of Environment v.21 Croteria for the use of regression analysis for remote sensing of sediment and pollutants Whitlock, C.;C. Kuo;S. LeCroy
  22. International Journal of Remote Sensing v.15 no.16 Artificial neural network techniques for estimating heavy convective rainfall and recognizing cloud mergers from satellite data Zhang, M.;R.A. Scofield