Introducing a LSTM based Flood Forecasting Model for the Nilwala river basin with a Mobile Application – a Review

Abstract

Flooding is one of the most devasting natural disasters in the world. The impact of flooding is damage to property, Agriculture, Infrastructure of a country and destroy human life. Flood Forecasting models and proper awareness about floods, sufficient communication between the flood victims and the responsible authorities are important to safeguard the life of human and the infrastructure of a country. This paper contains review of different Machine Learning methods and Algorithms like Artificial Neural Networks (ANN), Support Vector Machine (SVM), Multilayer Perception (MLP), Convolution Neural Networks (CNN) and Long Short-Term Memory (LSTM) which are used to forecast floods. Long Short-Term Memory is one of the Recurrent Neural Network models to forecast Flood. According to the reviewed literature Long Short-Term Memory networks are better than ANN, MLP and SVM because Long Short-Term Memory models can learn long-term patterns better.