Show simple item record

dc.contributor.authorRanasinghe, RM
dc.contributor.authorIlmini, WMKS
dc.date.accessioned2020-12-31T23:19:52Z
dc.date.available2020-12-31T23:19:52Z
dc.date.issued2020
dc.identifier.urihttp://ir.kdu.ac.lk/handle/345/3039
dc.description.abstractFlooding 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.en_US
dc.language.isoenen_US
dc.subjectFlood forecastingen_US
dc.subjectLSTMen_US
dc.subjectMobile Applicationen_US
dc.titleIntroducing a LSTM based Flood Forecasting Model for the Nilwala river basin with a Mobile Application – a Reviewen_US
dc.typeArticle Full Texten_US
dc.identifier.journal13th International Research Conference General Sir John Kotelawala Defence Universityen_US
dc.identifier.pgnos443-450en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record