Enhancing Flood Prediction in Urban Areas: A Machine Learning Approach for Makassar City

Abstract

Accurate and rapid predictions regarding urban flooding, are essential in supporting risk mitigation efforts. Flood phenomena have the potential to cause extensive damage and disrupt the functions of economic and governmental sectors. However, these impacts can be minimized through comprehensive planning and preparation to reduce potential losses. Machine learning techniques have emerged as a promising method for predicting complex hydrological processes. This research develops a flood prediction model by comparing seven machine learning algorithms, namely Logistic Regression, Linear Discriminant Analysis, k-Nearest Neighbors, Gaussian Naive Bayes, Support Vector Machine, AdaBoost, and Random Forest. The results show that Random Forest has the highest performance, demonstrating the reliability of Random Forest in processing complex urban flood datasets. This model is expected to enhance disaster preparation and contribute significantly to flood risk management in urban areas.

Access to Document

Other files and links

• Link to publication in Scopus
• Open Access Version Available

Fingerprint