Chinese Science Bulletin

, Volume 46, Issue 2, pp 158–161

Inversion of oceanic chlorophyll concentrations by neural networks

  • Haigang Zhan
  • Ping Shi
  • Chuqun Chen
Notes

DOI: 10.1007/BF03187014

Cite this article as:
Zhan, H., Shi, P. & Chen, C. Chin.Sci.Bull. (2001) 46: 158. doi:10.1007/BF03187014

Abstract

Neural networks (NNs) for the inversion of chlorophyll concentrations from remote sensing reflectance measurements were designed and trained on a subset of the SeaBAM data set. The remaining SeaBAM data set was then applied to evaluating the performance of NNs and compared with those of the SeaBAM empirical algorithms. NNs achieved better inversion accuracy than the empirical algorithms in most of chlorophyll concentration range, especially in the intermediate and high chlorophyll regions and Case II waters. Systematic overestimation existed in the very low chlorophyll (<0.031 mg/m3) region, and little improvement was obtained by changing the size of the training data set.

Keywords

neural network chlorophyll concentration remote sensing reflectance inversion Case II waters 

Copyright information

© Science in China Press 2001

Authors and Affiliations

  • Haigang Zhan
    • 1
    • 2
  • Ping Shi
    • 1
  • Chuqun Chen
    • 1
  1. 1.South China Sea Institute of OceanologyChinese Academy of SciencesGuangzhouChina
  2. 2.South China Sea Fisheries InstituteChinese Academy of Fisheries ScienceGuangzhouChina

Personalised recommendations