Study on Mangrove of Maximum Likelihood: Reclassification Method in Xiezhou Bay

Abstract

Liao, Y.; Liao, Y-Q.; Zhao, W-J.; Chen Q-H.; Li, T., and Yang, T.J., 2020. Study on mangrove of maximum likelihood: Reclassification method in Xiezhou bay. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Geospatial Research of Coastal Environments. Journal of Coastal Research, Special Issue No. 102, pp. 334-343. Coconut Creek (Florida), ISSN 0749-0208.Xiezhou Bay in Huidong was selected as the research area to explore the mechanism of maximum likelihood value-reclassification in this paper it deepened the degree of fragmentation and plaque extraction of maximum likelihood value and establish a point-to-point valuation extraction and classification model. This paper used the maximum likelihood to extract the GF-2 image mangrove forest in Xiezhou bay, in order to establish maximum likelihood point-to-point extraction mechanism. The maximum likelihood - reclassification model can be assignment and remove plaque. By comparing the KNN classification method test and field selecting sample validation samples, the maximum likelihood value - reclassification accuracy was as high as 89.29 %. This method greatly improves the accuracy of map extraction and field conditions. At the same time, our study provided scientific support for managing and mastering mangrove technologies.