应用KDD技术分析气象地质灾害与降水的关系

Using KDD Technology to Study Relationship between MGD and Precipitation

应用人工智能技术——数据库中知识发现(KDD)技术,分析研究发生在云南省境内造成重大损失的气象地质灾害的发生与当日及前期降水的关系。结果表明,绝大多数气象地质灾害都是由强降水诱发的,云南气象地质灾害与发生当日及前期降水的关系主要有3种类型,即暴雨诱发型、多日中大雨诱发型和连阴雨诱发型。所得到的云南气象地质灾害与当日及前期降水的定量关系,为云南地质灾害的气象监测、预报模式的建立提供了依据。

The Knowledge Discovery in Database （KDD） technology is used to analyze and investigate the relationship between precipitation and the damage-inducing meteorological geologic disasters in Yunnan Province. The findings conclude that most meteorological geologic disasters are induced by strong precipitation; there mainly are three types of relationship： induced by heavy rainfall, induced by multi-day moderate-to-heavy rainfall, and induced by consecutive rainfall. The quantitative relationship provides the evidence not only for the meteorological surveillance and forecast of meteorological geologic disasters, but also for the prediction model development in the Yunnan Province.