Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI - 2018)

Abstract

Floods, the naturally occurring hydrological phenomena, caused due to the meteorological events like intense or prolonged rainfall, unusual water overflow of high coastal estuaries on the result of storm surges. On an account of a lot of concrete structures in urban areas, high-intensity rainfall causes urban flooding and as there is no much soil available for water to percolate, this leads to huge drainage problems in urban cities. These types of floods cause harm to houses, buildings, humans, animals, farming land. Flooding leads to contamination of drinking water, spreading of diseases. In recent years, due to the combination of meteorological, hydrological and topographical modeling terminologies, advancement in data collection methods and algorithm analysis, the results of flood forecasting have been improved. In this paper, we have studied different techniques for flood prediction involving Neural Networks, Fuzzy Logic, and GIS-based systems with various algorithms considering different factors. The study shows, on introducing local parameters, increasing the size of acceptable error bounds, and combining different algorithms, better performance of the model is achieved.