What type of study is this?

September 10, 2025

Stepping up Support Vector Machine Algorithm for Flood Prediction

Key Points

Accurate flood predictions were achieved with an accuracy rate of 92%, indicating effective use of machine learning.
The model was evaluated with metrics such as accuracy, precision, recall, and F1-score to assess its performance.
Data collection involved historical rainfall, water level, soil moisture, and river flow discharge records for model training.
Local governments and communities can utilize this model to plan flood disaster mitigation strategies more efficiently.

Abstract

Flooding is one of the natural disasters that often occurs in Dompu Regency, especially around the Rabalaju River. To anticipate the adverse impacts caused, an accurate prediction system is needed to detect the potential for flooding. This research aims to apply the machine learning method Support Vector Machine (SVM) as a flood prediction model in Rabalaju River. The data used in this research includes historical data on rainfall, water level, soil moisture, and river flow discharge. The research stages include data collection, data preprocessing, SVM model building, and model performance evaluation using accuracy, precision, recall, and F1-score metrics. The results showed that the SVM method was able to provide accurate predictions with an accuracy rate of 92%. The implementation of this method is expected to help related parties, such as local governments and local communities, in mitigating flood disasters more effectively. This research also provides further development recommendations, such as model integration with the Python programming language for real-time data monitoring.

Ask AI

Helpful

Bookmark