基于BP人工神经网络的长江口外海生态综合评价及其成因分析  

Integrated ecological assessment in Changjiang Estuary offshore based on BP ANN and analysis of its formation

作　　者：杨红[1] 戴桂香[1] 赵瀛[1] 丁骏[1] 陈健[1] 

机构地区：[1]上海海洋大学海洋科学学院,上海201306

出　　处：《海洋环境科学》2012年第6期893-896,905,共5页Marine Environmental Science

基　　金：国家908专项(HD3:908-01-BC22);上海市海洋环境工程重点学科开放基金(J50702)

摘　　要：以长江口外海域为研究区域,基于2008年秋季该海域2个峰面断面的海洋环境调查走航数据,以海水水质指标、浮游植物多样性指数及叶绿素a浓度为评价指标,运用BP人工神经网络的方法评价该海域生态环境质量状况,结合该海区的地形及水动力情况分析,结果表明:2008年秋季长江口外海域生态状况总体处于亚健康状态;31°N断面受长江冲淡水影响,生态状况近海劣于远海,但20号站位逆趋势好转,据监测,夏季其附近海域为赤潮高发区;30°N断面近岸受浙江沿岸上升流影响,生态状况好于31°N,但5号站位逆趋势恶化;5号和20号站位反映了上升流与长江口冲淡水的交汇区域的生态状况。BP人工神经网络用于生态环境评价,具有一定的客观性和通用性。Based on B-P ANN, a model of the integrated assessment of the ecological environment quality of the Changjiang estuary off-shore was presented. The marine environment underway statistics from fall of 2008 on two water fronts was applied. The metrics include five sea water quality objectives, a phytoplankton diversity index and the concentration of chlorophylla. The results showed that the eco-logical status of the Changjiang estuary offshore was in a sub-heahh condition in fall of 2008. With the 31°N section affected by the Changjiang diluted water, the ecological quality of near-shore was far worse than the open sea. However, the quality of St. 20 was im-proved. The high occurrence area of Red-tide in summer was in near sea. The ecological situation of 30 N section was better than 31° N＇s, owing to the coastal upwelling along the coast of Zhejiang. However St. 5 took a sharp turn to worse. The St. 5 and St. 20 reflected ecologic regimes of the upwelling intersection and Changjiang diluted water. It also found that BP artificial neural network has a certain level of objectivity and interchange ability to evaluate the ecological environment.

关 键 词：长江口 BP人工神经网络 上升流 冲淡水 

分 类 号：X55[环境科学与工程—环境工程]