Long Short-Term Memory Network versus Support Vector Machine for Flood Prediction
Malaysia is prone to flood disasters, which are considered the most hazardous natural disasters. This study compares the use of Long Short Term Memory (LSTM) networks and Support Vector Machines (SVM) in predicting future flash floods. Additionally, this study examines the effect of using the Synthe...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Book |
| Language: | en |
| Published: |
IntechOpen
2023
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/12494/1/1149386 http://eprints.uthm.edu.my/12494/ https://www.intechopen.com/chapters/1149386 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Malaysia is prone to flood disasters, which are considered the most hazardous natural disasters. This study compares the use of Long Short Term Memory (LSTM) networks and Support Vector Machines (SVM) in predicting future flash floods. Additionally, this study examines the effect of using the Synthetic Minority Oversampling Technique (SMOTE) in order to address imbalanced data. In this study, flooding for the year 2021 will be predicted based on the best-performing model. Experimental results indicated that the treatment had a positive impact on the study’s outcome. An analysis of the outcomes of the models before and after treatment was conducted in order to determine which model delivers a higher degree of accuracy. SVM with RBF kernel is the most effective model before and after SMOTE treatment, out of all those evaluated in the study. Next, SVM model using RBF kernel after treatment was used to forecast flooding for 2021. Seven out of 12 floods were predicted by the model, which equates to 58.33% accuracy. Since the deep learning model did not perform well, future researchers could experiment with different numbers of hidden layers and hyperparameter settings to increase the accuracy.
Keywords |
|---|