Abstract -- The purpose of this project is to build a decision-making model for pre-warming the debris flow. We analyze the measured data of debris flow from to support the decision making model. The goal of this project is to increase the accuracy in the pre-warning system, and forecast the risk degree of the debris flow. This model is a useful supporting material for the prevention and reduction of debris flow disaster. The occurrence factors of debris flow in the studied site consist of two types, i.e. latency factors and stimulated factors. Those factors are collected by the related instruments. Then, we apply fuzzy statistics to study factors inter-relationship. The fuzzy inference and decision-making method are used to analyze the relationship grade and estimate the risk degree of debris flow. The model will be a useful reference material for the debris flow pre-warning system.