基于BP神经网络的滑坡风险性评价研究
文献类型：会议论文
| 作者 | 王萌1,2,3 ; 乔建平1,3; 石莉莉1,2,3
|
| 出版日期 | 2010 |
| 会议名称 | International Conference on Engineering and Business Management（EBM2010) |
| 会议日期 | 2010-3-25 |
| 会议地点 | 四川成都 |
| 关键词 | BP神经网络 滑坡 风险性评价 |
| 页码 | 5343- |
| 其他题名 | Research of Landslide Risk Assessment Based on BP Neural Network |
| 通讯作者 | 王萌 |
| 中文摘要 | 滑坡发生的影响因素众多，其风险性与各因素间多成非线性关系。目前的风险性评价方 法难以满足这些要求。而近年发展起来的神经网络模型属于非线性动态系统，具有符合滑坡风险 性评价的研究特点。因此本文应用GIS 技术和BP 神经网络相结合的方法，以重庆市万州区为示 范区，建立起区域滑坡风险性评价流程。以滑坡风险程度分级标准为基础构造学习样本集,通过 神经网络的自学习功能,建立起区域滑坡风险度等级与各影响因素之间复杂的非线性关系。结果 表明:用万州区样本训练的神经网络收敛的较好,训练好的神经网络可达到较高的识别率和可信 度。因此利用BP 神经网络进行滑坡风险性评价具有可行性。 |
| 英文摘要 | The inducing factors of landslide are numerous. Commonly, they have nonlinear relationship with landslide risk. Current methods cannot meet the needs of evaluating landslide risk. The artificial neural network which is developing in recent years belongs to a kind of nonlinear dynamic system and has characteristics which can be fit for landslide risk assessment. This work presents the result of applying the GIS technology and BP neural network in establishing the process of regional landslide risk assessment with Wanzhou district of Chongqing city as the study area. Based on the standard of landslide risk classification, learning sample set was set up. Subsequently, the complicated nonlinear relationship between regional landslide risk grades and inducing factors was established by neural network self-study ability. The result shows that the sample set of Wanzhou district is convergent well in BP neural network and the trained one has higher recognition and reliability. Consequently, the method is feasible for landslide risk assessment. |
| 会议主办者 | 武汉大学;美国James Madison大学;美国科研出版社 |
| 会议录 | Proceedings of International Conference on Engineering and Business Management（EBM2010)
 |
| 分类号 | TP183;P642.22 |
| 语种 | 中文 |
| ISBN号 | 978-1-935068-05-1 |
| 源URL | [http://ir.imde.ac.cn/handle/131551/6288]  |
| 专题 | 成都山地灾害与环境研究所_山地灾害与地表过程重点实验室 |
| 作者单位 | 1.中国科学院水利部成都山地灾害与环境研究所 2.中国科学院研究生院 3.中国科学院山地灾害与地表过程重点实验室 |
| 推荐引用方式 GB/T 7714 | 王萌,乔建平,石莉莉. 基于BP神经网络的滑坡风险性评价研究[C]. 见:International Conference on Engineering and Business Management（EBM2010). 四川成都. 2010-3-25. |
入库方式： OAI收割
来源：成都山地灾害与环境研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。