滑坡监测动态数据挖掘方法研究  

A Method of Dynamic Data Mining for Landslide Monitoring Data

作　　者：段功豪[1] 牛瑞卿[1] 

机构地区：[1]中国地质大学地球物理与空间信息学院,武汉430074

出　　处：《长江科学院院报》2013年第5期38-41,50,共5页Journal of Changjiang River Scientific Research Institute

基　　金：国家973计划资助项目(2011CB710601);国家863计划资助项目(2012AA121303);国土资源部重大科学研究项目(SXKY3-3-2)

摘　　要：为有效挖掘海量、动态的滑坡监测数据中的有用信息及规律,提出了一种利用Oracle触发器监测数据的挖掘方法。以八字门滑坡为研究对象,结合ARIMA模型对累积位移进行预测,利用触发器精炼监测数据和优化模型参数,提升预测模型的拟合精度。实验结果表明,该方法能有效改良传统静态数据挖掘结果,有助于人们认识到动态数据挖掘在滑坡灾害监测中的价值。To efficiently excavate the knowledge from substantial and dynamic landslide monitoring data, we putforward a data mining approach using oracle trigger to monitor data. In order to improve the fitting casting model, the time series model ARIMA （Autoregressive Integrated Moving Average Model） precision ot tore-was employed to forecast the accumulative displacement and the Oracle trigger was used to refine the monitoring data and optimize the model parameter. Bazimen landslide was taken as a case study. The results indicate that the method improves the mining result of traditional static data and helps people to realize the value of dynamic data in landslide preven-tion.

关 键 词：动态数据挖掘 滑坡监测 ORACLE触发器 ARIMA 

分 类 号：P642.22[天文地球—工程地质学]