基于数据挖掘的人类活动影响下水文效应研究  

Research on hydrological effects with impact of human activities based on data mining

作　　者：李伟[1,2] 张弛[1] 周惠成[1] 雷炎[2] 王志坤[2] 

机构地区：[1]大连理工大学建设工程学部水利工程学院,辽宁大连116024 [2]辽宁省水利水电科学研究院,辽宁沈阳110003

出　　处：《大连理工大学学报》2010年第6期997-1002,共6页Journal of Dalian University of Technology

基　　金：国家自然科学基金委员会-二滩水电开发有限公司雅砻江水电联合研究基金资助项目(50579095)

摘　　要：首先通过对流域下垫面变化、水利工程运行情况的分析,得到人类活动对流域水循环影响的变点,并采用降雨径流趋势分析的方法对其进行验证;然后着重利用数据挖掘的方法分析变点后人类活动影响下的水文效应;最后以丰满水库流域为例,建立了基于数据挖掘方法中决策树模型的水库拦洪比推理模式,经检验,该推理模式精度较高,应用该模式对流域场次洪水洪量预报修正的效果较好,其结果可以用于指导实际洪水预报与水库调度.Firstly,the change-point of the impact of human activities on watershed hydrological cycle is gained with the analysis of watershed underlaying surface changes and hydraulic projects running conditions,and it is validated by analysis on rainfall runoff trend.Then,hydrological effects with human activities are stressed based on data mining method.And finally,the reservoir storage scales inference model is established based on decision tree with Fengman Reservoir watershed for example. It is verified that the precision of the inference model is comparatively high,the corrected effect of the flood volume forecasting results using the established model is nice and the model can be applied to practically supervise flood forecasting and reservoir operation.

关 键 词：人类活动影响 变点 水文效应 数据挖掘 决策树 

分 类 号：TV121.9[水利工程—水文学及水资源]