The increasing trend in frequency of natural disasters in tandem with globalization of business makes the agricultural supply chain significantly vulnerable to disruption. This thesis presents a pragmatic approach for creating a Business Continuity Model that can notify supply chain planners when there is an increase in risk of agriculture supply chain disruption due to natural disasters. The methodology presented in this thesis applied big data analytics and machine learning algorithms along with agriculture product related exponential decay function to create a regionalized composite risk score, that incorporated both direct and indirect risk associated with the Agriculture Fresh Supply Chain. This model will aid supply chain planners in creating and implementing contingency plans, at the right time per given food production location. This risk score can help food manufacturing organizations to have a Business Continuity Plan that alleviate agriculture business supply chain interruptions. An example application of this model is illustrated with a melon packaging industry.