Flood replication using ANN model concerning with various catchment characteristics: Narmada river basin
By: Samantaray, Sandeep
.
Contributor(s): Agnihotri, Ankita.
Publisher: USA Springer 2023Edition: Vol.104(2), Jun.Description: 381-396p.Subject(s): Humanities and Applied SciencesOnline resources: Click here
In:
Journal of the institution of engineers (India): Series ASummary: Amongst the most destructive natural hazards, flood is the major cause of destruction to life and property. To ascertain the affected area under flood, development of flood models in various watersheds is the most important factor for decision makers. Lately, data mining techniques like artificial neural network (ANN) are being widely used to a higher extent for flood modelling. Present paper focuses on developing a flood model taking various factors causing flood with the help of ANN technique and Geographic Information System (GIS) for modelling and simulating flood affected areas lying under Narmada River Basin. ANN model was developed using MATLAB software, considering nine factors causing floods. Catchment characteristics are extracted by the application of GIS. The performance of the model is determined by considering four performance indices, including coefficient of determination (R2), mean square error (MSE), sum squared error (SSE), and root-mean-square error (RMSE). The results revealed that model 1 showed best performance with R2 value of 0.9907, MSE value of 0.000488, and SSE value of 7.69, whereas model 5 performed poorly with R2 (0.9036), highest MSE (0.000743), and SSE (2.89). Obtained results revealed suitable agreement amid predicted and actual hydrological datasets.
| Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|
Articles Abstract Database
|
School of Engineering & Technology Archieval Section | Not for loan | 2023-1742 |
Amongst the most destructive natural hazards, flood is the major cause of destruction to life and property. To ascertain the affected area under flood, development of flood models in various watersheds is the most important factor for decision makers. Lately, data mining techniques like artificial neural network (ANN) are being widely used to a higher extent for flood modelling. Present paper focuses on developing a flood model taking various factors causing flood with the help of ANN technique and Geographic Information System (GIS) for modelling and simulating flood affected areas lying under Narmada River Basin. ANN model was developed using MATLAB software, considering nine factors causing floods. Catchment characteristics are extracted by the application of GIS. The performance of the model is determined by considering four performance indices, including coefficient of determination (R2), mean square error (MSE), sum squared error (SSE), and root-mean-square error (RMSE). The results revealed that model 1 showed best performance with R2 value of 0.9907, MSE value of 0.000488, and SSE value of 7.69, whereas model 5 performed poorly with R2 (0.9036), highest MSE (0.000743), and SSE (2.89). Obtained results revealed suitable agreement amid predicted and actual hydrological datasets.
Click on an image to view it in the image viewer
There are no comments for this item.