Yang Jianqiang^1,2, Gao Zhenhui², Ding Dewen³, Sun Peiyan², Lin Qingliang², and Shi Qiang^2
1Environmental Science and Engineering School, Shanghai Jiaotong University, Shanghai, 200240, China; ²The North Sea Monitoring Center, State Oceanic Administration, Qingdao, 266003, China; ³Key Laboratory of Science and Engineering for Marine ecological Environment State Oceanic Administration, Qingdao, 266061, China

Abstract

Harmful red tide is a kind of : exceptional phenomenon aroused by many factors, catastrophe and nonlinear are its .characteristics. Harmful red tide warning is a hotspot in the areas of marine science. In this paper, the model of A-K neural network, which has plasticity, and is unsupervised, is worked out. The principle and algorithm are described . The application of A-K network models in the areas of harmful red tide warning of BaYuquan in LiaoNing Province shows that it can deal with many problems about classification ideally, and is applied.

Keywords: red tides, artificial neural networks, warning, self-organization