Published July 30, 2020 | Version v1
Journal article Open

The use of Metaheuristic Algorithms in Early Prediction and Forecasting of Flood – A Use of Cuckoo Search Algorithm based Optimization for Flood Controlling

  • 1. Civil Engineering Department, Sardar Vallabhbhai National Institute of Technology, Surat, India. School of Engineering, P. P. Savani University, Kosamba, Surat, India.
  • 2. Civil Engineering Department, Sardar Vallabhbhai National Institute of Technology, Surat, India
  • 1. Publisher

Description

Flood is one of the disasters which have multiple impacts on the society and industry. It has severe impacts on the urban economy and has forced the scholars to develop resiliency plans. Various types of flood forecasting techniques developed by the scholars and have certain limitations. There are various types of multiple modeling techniques which are being used for flood controlling and each has certain limitations. The optimization techniques along with the artificial intelligence algorithms can be helpful for monitoring and early prediction of flood. The neural network models promises better accuracy compared to convention models for prediction, but they face great difficulties in selection of appropriate model parameters. In the said context, here an effort has been made to explore the importance of Cuckoo theorem in flood management. The cuckoo search algorithm can be used for parameter tuning. The hybrid approach of using cuckoo search algorithm with neural networks has given far better accuracy compared to standalone algorithms. The use of such Cuckoo Search Metaheuristic algorithm will help us to predict early warning system than any other method and helps us to align the flood controlling activities. The paper presents the used of variants of cuckoo search algorithm for early flood prediction. The paper unfolds major insights of flood scenarios along with the significance of flood control and monitoring.

Files

B3285079220.pdf

Files (290.7 kB)

Name Size Download all
md5:ecd0b9514f053defef063d5d94561eea
290.7 kB Preview Download

Additional details

Related works

Is cited by
Journal article: 2277-3878 (ISSN)

Subjects

ISSN
2277-3878
Retrieval Number
B3285079220/2020©BEIESP