基于SVM⁃RF的泥石流窗口坝闭塞度判别研究∗

焦亮

您当前的位置：

首页 >

文章列表页 >

基于SVM⁃RF的泥石流窗口坝闭塞度判别研究∗

更新时间：2025-09-25

- 基于SVM⁃RF的泥石流窗口坝闭塞度判别研究∗
- Research on the Occlusion of Debris Flow Window-frame Dam based on SVM and RF Methods
- 防灾减灾工程学报 2020年第3期页码：439-446
- 作者机构：
  
  中国科学院山地灾害与地表过程重点实验室,四川,成都,610041
- 作者简介：
- 基金信息：
  
  国家自然科学基金面上项目(41772343)、中国科学院“西部青年学者”项目（2018）资助
- DOI：
  中图分类号： P642.23
- 纸质出版：2020
- 稿件说明：
移动端阅览
焦亮,柳金峰,游勇,袁东,周文兵.基于SVM⁃RF的泥石流窗口坝闭塞度判别研究∗[J].防灾减灾工程学报,2020,(3):439-446

JIAO Liang. Research on the Occlusion of Debris Flow Window-frame Dam based on SVM and RF Methods[J]. 2020, (3): 439-446.
焦亮,柳金峰,游勇,袁东,周文兵.基于SVM⁃RF的泥石流窗口坝闭塞度判别研究∗[J].防灾减灾工程学报,2020,(3):439-446 DOI：

JIAO Liang. Research on the Occlusion of Debris Flow Window-frame Dam based on SVM and RF Methods[J]. 2020, (3): 439-446. DOI：

摘要

为了研究野外泥石流防治工程中窗口坝的开口闭塞类别，基于量纲分析理论，以室内水槽试验模拟实际工程，分析模型试验与实际工程的相关物理量及对应的相似准数；引入支持向量机和随机森林分类模型，在开源机器学习工具Scikit?Learn中，采用python编程实现算法；以室内水槽试验数据作为支持向量机和随机森林的训练样本，进行机器学习得到分类模型，提出一种用于判别泥石流窗口坝闭塞类型的新方法；将测试结果与经验公式中闭塞度判别值F的分类结果进行正确率对比，结果表明，F值的分类准确率为88%，而支持向量机为92%，随机森林为94%，随机森林分类效果最好，机器学习理论为泥石流窗口坝在实践中的设计提供了新思路。

Abstract

In order to investigate the window-frame block categories of the field debris flow prevention engineering projects

the laboratory flume experiment is conducted to simulate the actual condition

using dimensional analysis method to ensure the similarity criterion of model test and the actual engineering. This research introduces the basic theory of support vector machine and random forest and realizes the algorithm in python language environment through the open source machine learning tool Scikit-Learn. Making the laboratory flume experiment data as the training sample of support vector machines and random forests then

got the learning classification model

put forward a new method for identifying debris flow dam block type. The test results compared with the empirical formula of discriminant value F block degree of accuracy of the classification

the results show that the F value of classification accuracy is 88%

and the support vector machine (SVM) was 92%

the random forest was 94%. The random forest classification effect is best. The machine learning theory provides a new idea on the debris flow window-frame dam design in practice.

关键词

Keywords

references

周必凡，李德基，吕孺人，等.泥石流防治指南[M].北京：科学出版社,1991.Zhou B F,Li D J,Lyu R R,et al.Guidelines for debris flow control[M].Beijing:Science Press,1991.(in Chinese)

李德基.透水型拦挡坝在泥石流防治中的应用[J].中国地质灾害与防治学报,1997,8(4):60-66.Li D J.The application of permeable dam in debris flowcontrol[J].The Chinese journal geological hazard and control,1997,8(4):60-66.(in Chinese)

康志成，罗德富，张军，等.中国泥石流灾害与防治[M].北京:科学出版社，1996.Kang Zh Ch,Luo D F,Zhang J,et al.China debris fl-ow injury prevention[J].Beijing:Science Press,1986.(in Chinese)

赵彦波，游勇，柳金峰，等.泥石流窗口坝闭塞类型及其临界条件实验研究[J].防灾减灾工程学报,2015,35(2):256-262.Zhao Y B,You Y,Liu J F,et al.Experimental study on blocked types and critical conditions of window frame dam Preventing debris flow[J].Journal of Disaster Prevention and Mitigation Engineering,2015,35(2):256-262.(in Chinese)

赵彦波，游勇，柳金峰，等.泥石流窗口坝调节泥砂粒径试验研究[J].长江科学院院报,2016,33(3):9-13.Zhao Y B,You Y,Liu J F,et al.Experimental study on the function of window-frame dam in changing sediment size distribution for debris flow prevention[J].Journal of Yangtze River Scientific Research Institute,2016,33(3):9-13.(in Chinese)

刘曙亮，游勇，柳金峰，等.窗口坝拦截泥石流性能试验研究[J].长江科学院院报,2015,32(8):40-44.Liu Sh L,You Y,Liu J F,et al.Experimental study on perfo-rmance of window-frame dam intercepting debris flow[J].Journal of Yangtze River Scientific Research Institute,2015,32(8):40-44.(in Chinese)

边肇祺，张学工.模式识别[M].2版.北京：清华大学出版社,2000.Bian Zh Q,Zhang X G.Schematic identification[M].2rd ed.Beijing:Tsinghua University Press,2000.(in Chinese)

Andrew A M.An introduction to support vector ma-chines and other kernel-based learning methods[J].Kybernetes,2000,32(1):1-28.

邓乃扬.数据挖掘中的新方法[M].北京：科学出版社,2004.Deng N Y.A new way of numerical drilling[M].Beijing:Science Press,2004.(in Chinese)

张锦水，何春阳，潘耀忠，等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J].遥感学报,2006,10(1):49-57.Zhang J Sh,He Ch Y,Pan Y Zh,et al.The high spatial resolution RS image classification based on SVM method with the multi-source data[J].Journal of Remote Sensing,2006,10(1):49-57.(in Chinese)

李晓黎，刘继敏，史忠植.基于支持向量机与无监督聚类相结合的中文网页分类器[J].计算机学报,2001,24(1):62-68.Li X L,Liu J M,Shi Zh Zh.A chinese web page classifier based on support vector machine and unsupervised clustering[J].Chinese Journal of Computers,2001,24(1):62-68.(in Chinese)

王雪峰，周国标.基于SVM的人脸识别方法研究[J].上海应用技术学院学报(自然科学版),2006,6(2):104-107.Wang X F,Zhou G B.A Research on the SVM method for facial recognition[J].Journal of Shanghai Institute of Technology(Natural Science),2006,6(2):104-107.(in Chinese)

张红涛，胡玉霞，毛罕平，等.基于SVM的储粮害虫图像识别分类[J].农机化研究,2008(8):36-38.Zhang H T,Hu Y X,Mao H P,et al.Image recognition and classification of the stored-grain pests based on support vector machine[J].Agricultural Research,2008(8):36-38.(in Chinese)

Breiman L.Random forests,machine learning 45[J].? Journal of Clinical Microbiology,2001,2:199-228.

方匡南，吴见彬，朱建平，等.随机森林方法研究综述[J].统计与信息论坛,2011,26(3):32-38.Fang K N,Wu J B,Zhu J P,et al.Concerning forest method research[J].Statistics and Information Forum,2011,26(3):32-38.(in Chinese)

周志华.机器学习[M].北京：清华大学出版社,2016.Zhou Zh H.Machine learning[M].Beijing:Tsinghua University Press,2016.(in Chinese)

Platt J C.Sequential minimal optimization:a fast algorithm for training support vector machines[C]//Advances in Kernel Methods-support Vector Learning.Cambridge,UK:Computer Science,Microsoft Research Technical Report,1998,19:98,212-223.

谈庆明.量纲分析[M].安徽：中国科学技术大学出版社,2005.Tan Q M.Dimensional analysis[M].Anhui:University of Science and Technology of China Press,2005.(in Chinese)

杨忆，李建国，葛方振，等.基于Scikit-Learn的垃圾短信过滤方法实证研究[J].淮北师范大学学报(自然科学版),2016,37(4):39-41.Yang Y,Li J G,Ge F Zh,et al.An empirical study on spam messages detection method based on scikit-learn[J].Journal of Huaibei Normal University(Natural Science),2016,37(4):39-41.(in Chinese)

Garreta R,Moncecchi G.Learning scikit-learn:machine learning in python[M].Birmingham,UK:Packt Publishing,2013.

浏览量

378

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于机器学习的连续刚构桥施工线形预测研究

基于PSO‑LightGBM模型的边坡稳定性预测研究

基于主动学习支持向量机的预应力锚索加固边坡可靠度分析

钢筋混凝土结构抗火性能研究进展

基于机器学习算法的非饱和土水特征曲线预测