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 a...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.展开更多
基金the National Key Project (Grant No. 97-926-05-03), Key Project of the CAS (Grant No. KZ952-J1-404) Guangdong Provincial Natural Science Foundation (Grant No. 990311).
文摘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.
