Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/3920
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPradhan, Padmini P-
dc.contributor.authorPradhan, Biswajit-
dc.contributor.authorKhatua, Kishanjit Kumar-
dc.date.accessioned2023-01-18T04:39:41Z-
dc.date.available2023-01-18T04:39:41Z-
dc.date.issued2022-12-
dc.identifier.citationInternational conference Sustainable Technologies for River Erosion Alleviation and Management (STREAM-2022) , IIT Guwahati, 14th-16th December 2022en_US
dc.identifier.urihttp://hdl.handle.net/2080/3920-
dc.descriptionCopyright belongs to proceeding publisheren_US
dc.description.abstractFlood risks are among the many water-related concerns that have the potential to cause the most damage. Urban flooding and the risk it poses are growing issues with global significance, but they are especially serious in developing nations like India, where the risk is typically understudied and little understood. Consequently, it is crucial to develop a stage-discharge model that would aid in flood prediction. In comparison to the past, floods in mountainous areas are increasingly more frequent, and this trend is expected to continue owing to global warming. The study presents the adaptive neural-based fuzzy inference system (ANFIS) approach to estimate the flood risk for the Subarnarekha River at the Rajghat Gauge site. Techniques for assessing the risk of flooding are based on a variety of factors, including socioeconomic, geometric hydraulic surfaces, and meteorological data. Characterizing the environment, figuring out the type and severity of hazards, and estimating susceptibility and risk are the four key steps in assessing flood risk. The current study uses independent parameters such as water elevation, precipitation, average temperature, soil moisture, and relative humidity. Various error statistics have been used to analyze the model's efficiency. The results show an expected improvement over past studies with improved R- squared values. The MAE, MAPE, RMSE, and R2 were used to assess the models' performances with 20.96, 0.187, 284.28, and 0.97 values, respectively. Flood catastrophe management may benefit significantly from the strengthening of community resilience through socioeconomic empowerment and increased adaptive ability.en_US
dc.subjectFlood risken_US
dc.subjectANFISen_US
dc.subjectStatisticalen_US
dc.subjectStage-dischargeen_US
dc.subjectHydraulicen_US
dc.subjectUrban floodingen_US
dc.titleFlood Risk Assessment of Subarnarekha River Using Adaptive Neural-Based Fuzzy Inference System (ANFIS)en_US
dc.typeArticleen_US
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2022_STREAM_PPPradhan_Flood.pdf292.95 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.