Soil Erosion and Sediment Prediction at Watershed Scale Under Single Rainfall Event Based on Support Vector Regression

LI Bin-bing; ZHENG Fen-li; LONG Dongcai; LI Jing

您当前的位置：

首页 >

文章列表页 >

Soil Erosion and Sediment Prediction at Watershed Scale Under Single Rainfall Event Based on Support Vector Regression

- Soil Erosion and Sediment Prediction at Watershed Scale Under Single Rainfall Event Based on Support Vector Regression
- Bulletin of Soiland Water Conservation Vol. 26, Issue 6, Pages: 120-125(2007)
- 作者机构：
  
  1. 陕西师范大学旅游与环境学院
  2. 西北农林科技大学资源环境学院,陕西,西安,715600
  3. 武警工程学院
  4. ,北京,100083
  5. 武警工程学院西北农林科技大学资源环境学院, , , .,陕西,西安,715600
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2007
- 稿件说明：
移动端阅览
LI Bin-bing, ZHENG Fen-li, LONG Dongcai, et al. Soil Erosion and Sediment Prediction at Watershed Scale Under Single Rainfall Event Based on Support Vector Regression[J]. Bulletin of Soiland Water Conservation, 2007, 26(6): 120-125.
DOI：

LI Bin-bing, ZHENG Fen-li, LONG Dongcai, et al. Soil Erosion and Sediment Prediction at Watershed Scale Under Single Rainfall Event Based on Support Vector Regression[J]. Bulletin of Soiland Water Conservation, 2007, 26(6): 120-125. DOI：

摘要

基于次降雨小流域侵蚀产沙过程的复杂性、非线性

利用支持向量机回归和主成分分析方法。确定了影响次降雨小流域侵蚀产沙量的关键因子

包括浑水径流深、洪峰最大流量、降雨量和30 min最大降雨强度。建立了向量机回归支持下的次降雨小流域侵蚀产沙预测模型。利用60次侵蚀产沙实测资料

对模型预报精度进行了分析

结果表明

基于支持向量回归的次降雨流域侵蚀产沙预报模型具有较好的预测精度

预测精度平均为在86%。该研究为揭示次降雨小流域土壤侵蚀规律提供了新的途径和方法。

Abstract

Based on complexit y and nonlinearit y of soil erosion and sediment in small watershed under single rainfall event

the support vector regression(SVR) and method of the principal component analysis(PCA) were used to determine key factors affecting soil erosion and sediment from Wangjiagou watershed under sin- gle rainfall event.Results showed tha t mud runoff depth

peak flood discharge

maximum 30 min rainfall in- tensity

and rainfall amount were key factors affecting soil erosion and sediment in Wangjiagou watershed.An erosion prediction model by SVR was developed based on observed data for 60 rainfall events in Wangjia-gou watershed.The model validation indicated that the model predicted precision reached as much as 86% for60 rainfall events.The research illustrates that SVR provides a new approach to study complexity and non- linearity of soil erosion and sediment in small watershed under a single rainfall event.

关键词

Keywords

references

Views

1195

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Soil and Water Conservation Regionalization of Lishui River Watershed in Hunan Province

Analysis on Driving Forces of Construction Land Changes of Xianyang City

Ecosystem Reconstruction Model of Degraded Grasslands in Mixed Cropland一Grassland Zone in Northern Shaanxi Province

Characteristics of wind-sand environment and gully entering process in Shajiawan small watershed in middle reaches of Yellow River

Research progress on microbial-biochar interaction mechanisms in saline-alkali soil improvement

Related Author

YIN Hui

LI Jing-bao

LIAO-Ting

ZHOU He-ping

CAO Ni

CAO Ming-ming

DU Zhong-chao

HAN Shen-shan

Related Institution

Agricultural College, Guangxi University

College of Resources and Environment Science, Hunan Normal University

Department of Urban and Resources Science, Northwestern University

College of tour and Resources,Environment,Xianyang Normal University

Scientific Research Department of Xinyang Normal University,, He′nan

⁰