| 人工神经网络在深圳市水库富营养化评价中的应用 |
| |
| 引用本文： | 林高松,黄晓英,李娟.人工神经网络在深圳市水库富营养化评价中的应用[J].环境监测管理与技术,2010,22(1):59-63. |
| |
| 作者姓名： | 林高松 黄晓英 李娟 |
| |
| 作者单位： | 深圳市环境科学研究院,广东,深圳,518001 |
| |
| 摘 要： | 对富营养化评价标准进行插值获取大量的样本,建立了基于BP人工神经网络的富营养化评价模型。将模型应用于评价深圳市13座主要水库的富营养化状况,对其成因进行分析,并提出了对策与建议。研究结果表明,石岩水库与深圳水库为轻度富营养化,占评价水库总数的15.4%;西丽水库等11座水库为中营养,占评价水库总数的84.6%。人工神经网络用于建立湖库富营养评价模型是适合的。
|
| 关 键 词： | 人工神经网络 富营养化评价 水库 深圳 |
Application of Artificial Neural NetworkM ethod on Eutrophication Assessmentfor Shenzhen Reservoirs |
| |
| LIN Gao-song,HUANG Xiao-ying,LI Juan.Application of Artificial Neural NetworkM ethod on Eutrophication Assessmentfor Shenzhen Reservoirs[J].The Administration and Technique of Environmental Monitoring,2010,22(1):59-63. |
| |
| Authors: | LIN Gao-song HUANG Xiao-ying LI Juan |
| |
| Affiliation: | ( Shenzhen Academy of Environmental Science, Shenzhen, Guangdong 518001, China) |
| |
| Abstract: | Abundant of training samples were gotten via interpolation of eutrophication assessment standard, and a eutrophication assessment model was established based on back propagation artificial neural networks. The model was used to assess nutritional situation of thirteen main reservoirs of Shenzhen, and its cause was analyzed, and then strategies and advices were brought forward. Research result showed that 15.4% reservoirs were slightly eutrophic including Shiyan Reservoir and Shenzhen Reservoir, and 84.6% reservoirs were middle nutri- tion. Artificial neural networks without factitious weight were suitable to bright up eutrophication assessment model whose result was objective. |
| |
| Keywords: | Artificial neural networks Eutrophication evaluation Reservoir Shenzhen |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《环境监测管理与技术》浏览原始摘要信息 |
|
点击此处可从《环境监测管理与技术》下载全文 |
|
