Assessing Long Term Impacts of Disaster Using Predictive Data Analytics Based on Machine Learning Algorithms

Abstract

The term disaster refers to a significant problem that could have a significant impact on the community or society. The effects of disaster can have both an immediate and a long-term influence on a region. Data is an essential component in the process of analyzing the effects of disaster. The application of data analytics technique has the ability to evaluate the effects of various kinds of disasters. Collectively, the approaches of data analytics and machine learning play a significant role in the process of transforming and being able to make judgments regarding our social, economical, mental, and psychological aspects. It is challenging to evaluate the long-term impacts for a variety of factors affecting employment, education, jobs, agriculture, society, etc., as well as the influence on the local population. The purpose of this research work is to evaluate the impacts, ranging from the short term to the long term. Several data agencies were used to carry out surveys and information collection procedures. To monitor the situation and anticipate the needs of the victims, organizations may employ these resources to overcome the challenges associated with disaster management. The evaluation examines the nature of the disaster as well as the long-term consequences. Predicting the long-term repercussions of disaster can be accomplished through the utilization of data analytics techniques and machine learning algorithms. The operation of the algorithms is dependent upon the input data sets, the nature of the disaster (whether it be natural or man made), and the direct and indirect effects of the disaster. With the use of the data sets that are now accessible, it is possible to make predictions regarding both the short term and long-term effects of the disaster. After the completion of the data gathering process, the data will be prepared with the assistance of data analytics tools, and the data sets will be further subdivided for the purposes of training and testing.