Flood Prediction Analysis Using Supervised Machine Learning Techniques

Abstract

FloodsalsoknownasCataractshavecomethemostwell-knownandmurderous cataclysmic events of this century. Absence of a successful deluge soothsayingframe has brought about grave loss of mortal actuality and structure. This has reiterated thesignificance of having in place a deluge vaccination system. This paper looks at developingthe most effective deluge determining model. AI computations and a hearty, productive andprecisedelugeanticipationframewillgivealltheabecedarianaidandbackingdemandedto the residers and government. Hence, the Decision Tree Model is being erected. Thismodel actualizes colorful computations on datasets with a compass of delicacy. The modelutilizes an AI computation which predicts Floods, transferring cautions to the original andgovernment authorities using an Android Operation. The comparison of the results hahasbeen performed on three Machine Learning Algorithms that are Decision Tree, RandomForest and Gradient Boost. This model focuses on perfecting the rate of vaccination bydealingwith furtherintricate information andahigh-position algorithm.