1- University of Mazandaran
2- University of Mazandaran ,h.roradeh@umz.ac.ir
2- University of Mazandaran ,
Abstract: (490 Views)
Objective: Floods are among the most significant natural disasters in Mazandaran Province, particularly in Sari County, where they cause widespread economic, social, and environmental damages each year. The main objective of this research is to identify and map flood hazard zones using machine learning algorithms, namely Random Forest (RF) and Support Vector Machine (SVM), and to apply an ensemble approach in order to enhance prediction accuracy and reduce model uncertainty.
Method: In this study, a set of spatial datasets including a Digital Elevation Model (DEM), land use/land cover derived from satellite imagery, geomorphological indices (slope, aspect, and drainage density), geological data, distance from roads and streams, vegetation index (NDVI), and climatic variables (precipitation and temperature) were collected. These datasets were processed using GIS and RS techniques and prepared for model training and validation. The models’ performance was assessed using evaluation metrics such as Accuracy, F1-score, AUC, and ROC curve analysis.
Findings: The results indicated that both RF and SVM demonstrated high performance in flood hazard mapping, as reflected by strong evaluation metrics. Moreover, the ensemble approach improved prediction reliability and reduced errors compared to single-model predictions. The generated maps revealed that a significant portion of Sari County falls within high and very high hazard zones, which overlap with are::as char::acterized by intense rainfall, high drainage density, and steep slopes.
Conclusion: This research highlights that machine learning algorithms, particularly when applied in an ensemble framework, are powerful tools for identifying flood-prone areas. The findings can serve as a scientific basis for urban planning, disaster management, and flood risk reduction strategies in Sari County and other comparable regions.
Method: In this study, a set of spatial datasets including a Digital Elevation Model (DEM), land use/land cover derived from satellite imagery, geomorphological indices (slope, aspect, and drainage density), geological data, distance from roads and streams, vegetation index (NDVI), and climatic variables (precipitation and temperature) were collected. These datasets were processed using GIS and RS techniques and prepared for model training and validation. The models’ performance was assessed using evaluation metrics such as Accuracy, F1-score, AUC, and ROC curve analysis.
Findings: The results indicated that both RF and SVM demonstrated high performance in flood hazard mapping, as reflected by strong evaluation metrics. Moreover, the ensemble approach improved prediction reliability and reduced errors compared to single-model predictions. The generated maps revealed that a significant portion of Sari County falls within high and very high hazard zones, which overlap with are::as char::acterized by intense rainfall, high drainage density, and steep slopes.
Conclusion: This research highlights that machine learning algorithms, particularly when applied in an ensemble framework, are powerful tools for identifying flood-prone areas. The findings can serve as a scientific basis for urban planning, disaster management, and flood risk reduction strategies in Sari County and other comparable regions.
Keywords: : Ensemble Approach, Flood, Hazard Zoning, Machine Learnig, Random Forest (RF), Sari County Support Vector Machine (SVM)
Send email to the article author
| Rights and permissions | |
 | This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
