Reconstruction of satellite chlorophyll-a data using a modified DINEOF method: a case study in the Bohai and Yellow seas, China

A data-interpolating empirical orthogonal function (DINEOF) method was applied to 8 day composited satellite-derived chlorophyll-a (chl-a) images to produce a long-term, cloud-free chl-a data set over the Bohai Sea and Yellow Sea from 1997 to 2010. In this study, two additional procedures, a depth subdivision scheme and a new process of outlier detection and removal, improved the overall performance of this interpolating technique. The whole chl-a data set was divided into three subsets according to 20 and 50m isobaths and the DINEOF reconstruction was performed on each subset. This subdivision scheme can significantly improve the accuracy of reconstruction, but is achieved with loss of computational efficiency due to the increased number of iterations required for reconstruction of the three subsets. A simple and new outlier detection method based on standardized residuals theory was developed to eliminate the spurious values (outliers) from the chl-a data set. The accuracy of the DINEOF reconstruction was significantly improved by the application of the outlier detection and removal process.