<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Floods can cause significant problems for humans and can damage the economy. Implementing a reliable flood monitoring warning system in risk areas can help to reduce the negative impacts of these natural disasters. Artificial intelligence algorithms and statistical approaches are employed by researchers to enhance flood forecasting. In this study, a dataset was created using unique features measured by sensors along the Hunza River in Pakistan over the past 31 years. The dataset was used for classification and regression problems. Two types of machine learning algorithms were tested for classification: classical algorithms (Random Forest, RF and Support Vector Classifier, SVC) and deep learning algorithms (Multi-Layer Perceptron, MLP). For the regression problem, the result of MLP and Support Vector Regression (SVR) algorithms were compared based on their mean square, root mean square and mean absolute errors. The results obtained show that the accuracy of the RF classifier is 0.99, while the accuracies of the SVC and MLP methods are 0.98; moreover, in the case of flood prediction, the SVR algorithm outperforms the MLP approach.</p>
</abstract>

Floods can cause significant problems for humans and can damage the economy. Implementing a reliable flood monitoring warning system in risk areas can help to reduce the negative impacts of these natural disasters. Artificial intelligence algorithms and statistical approaches are employed by researchers to enhance flood forecasting. In this study, a dataset was created using unique features measured by sensors along the Hunza River in Pakistan over the past 31 years. The dataset was used for classification and regression problems. Two types of machine learning algorithms were tested for classification: classical algorithms (Random Forest, RF and Support Vector Classifier, SVC) and deep learning algorithms (Multi-Layer Perceptron, MLP). For the regression problem, the result of MLP and Support Vector Regression (SVR) algorithms were compared based on their mean square, root mean square and mean absolute errors. The results obtained show that the accuracy of the RF classifier is 0.99, while the accuracies of the SVC and MLP methods are 0.98; moreover, in the case of flood prediction, the SVR algorithm outperforms the MLP approach.

Artificial Intelligence Based Flood Forecasting for River Hunza at Danyor Station in Pakistan

Archives of Hydro-Engineering and Environmental Mechanics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Floods can cause significant problems for humans and can damage the economy. Implementing a reliable flood monitoring warning system in risk areas can help to...

Artificial Intelligence Based Flood Forecasting for River Hunza at Danyor Station in Pakistan

Publié en ligne: 17 févr. 2023

Pages: 59 - 77

Reçu: 06 oct. 2022

DOI: https://doi.org/10.2478/heem-2022-0005

Mots clés
Hydrometeorology, Random Forest, Support Vector, Multilayer Perceptron, Machine Learning, Flood Forecasting

© 2022 Muhammad Waseem Yaseen et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Artificial Intelligence Based Flood Forecasting for River Hunza at Danyor Station in Pakistan

Publié en ligne: 17 févr. 2023

Pages: 59 - 77

Reçu: 06 oct. 2022

DOI: https://doi.org/10.2478/heem-2022-0005

Mots clésHydrometeorology, Random Forest, Support Vector, Multilayer Perceptron, Machine Learning, Flood Forecasting

© 2022 Muhammad Waseem Yaseen et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Mots clés
Hydrometeorology, Random Forest, Support Vector, Multilayer Perceptron, Machine Learning, Flood Forecasting