中长期地震危险性概率预测中的统计检验方法Ⅱ:N-test和L-test方法

Statistical Test Methods of Intermediate-term and Long-term Probabilistic ForecastingⅡ : N-test and L-test Method

本文介绍了国际"地震可预测性合作研究"CSEP计划中,用于地震概率预测模型检验的N-test和L-test方法的基本原理、发展动态。以地震活动平滑模型(smoothed seismicity model)在新疆天山中部地区的中长期预测结果为例,本文尝试使用N-test和L-test统计检验方法对预测结果进行评价。结果表明,上述方法能够较好地评价预测结果,并有助于构建更为科学合理的地震预测模型及相关参数设置。

In this paper, we introduce the principles and developments of the N-test and L- test methods which have been used to evaluate earthquake probabilistic forecasting models as routine statistical test methods in the CSEP （Collaboratory for the Study of Earthquake Predictability） project. Selecting the middle section of Tianshan region as the study area, we perform evaluation of the Smoothed Seismicity model for intermediate-term and longterm retrospective forecasting with N-test and L-test methods. The results show that N- test and L-test methods are efficient to evaluate the earthquake prediction models and can be used to optimize parameter setting in the earthquake forecasting models.