Performance Comparison of Multilayer Feed Forward and Radial Basis Feed Forward Neural Networks in River Stage Prediction

Nowadays, satellite image processing plays a crucial role for the research developments in many fields of study including Astronomy, Remote Sensing, GIS, Agriculture Monitoring and Disaster Management. The remotely sensed images are utilized in many of the researches with the aim of predicting natural disasters so that essential precautions can be taken to protect the environment. Besides the other, the water resource analysis plays a vital role in these researches. Traditionally, lots of methods are utilized for the analysis and determination of the level of water in water resources. In this work, the river water resource is analyzed to determine the stage of the water level using multilayer feed forward and radial basis feed forward networks and their performance is measured. The existing works are not effective because they determine only the changes that occur in the water level and does not translate them into meaningful results that indicates its status i.e., whether it is in the danger zone or not.