Method of regional early warning of geohazards based on the explicit statistical theory

Abstract：Regional early warning is an important means for improving the consciousness of geohazard prevention and reduction and effectively mitigating the loss caused by geohazards. In the early-warning method of explicit statistics, the effect of coupling of multiple factors such as geo-environmental change and precipitation is considered, thus overcoming the limitation of the single critical rainfall criterion. Based on the explicit statistic theory on geohazard early warning, applied studies have been carried out in the southeast of China. Twelve geo-environmental factors such as rock and soil types and topographic relief are selected to analyze the relationship between the distribution of geohazards and geo-environmental factors by using the determinacy coefficient function (CF), and the geohazard potentiality parameter is selected as an index of the geo-environment and quantitative calculation is performed. The very day rainfall and previous cumulative rainfall in one rain process are selected as an index of rainfall excitation conditions. Finally, the multi-regression analysis is used to analyze the relationships of the geo-environmental factor, rain excitation conditions and geohazards. Then an explicit statistic early-warning model for geohazards is constructed. Take for example the early warning during the land striking of the typhoon "Pearl" on May 18, 2006, the authors check the forecasting model and prove that the principle and model of explicit statistics early warning are feasible and practicable.