|
Superiority of the maximum entropy (MaxEnt) model over random forest for flood susceptibility mapping with limited data in semi-arid regions
|
Ali Haghi Zadeh *   , Negar Arjmand , Reza Fathi Ganji |
|
|
|
Abstract: (15 Views) |
| Floods are one of the most destructive natural disasters, inflicting extensive human and financial losses on communities. The occurrence and intensification of this phenomenon result from the dynamic and complex interaction of multiple environmental and anthropogenic factors. This research was conducted with the aim of flood susceptibility zoning using artificial intelligence models in the Alishtar watershed, Lorestan Province, Iran. The study area, covering 797.64 km², is part of the Karkheh sub-basin and has a semi-arid, cold climate with an average annual precipitation of 570 mm. In this study, 10 influential factors—including slope, aspect, precipitation, distance from roads, distance from rivers, soil type, land use, geological formation, Topographic Wetness Index (TWI), and drainage density—were used as input data. Out of a total of 58 observation points (33 flood points and 25 non-flood points), 70% were used for model training and 30% for validation. The performance of two models—Random Forest (RF) and Maximum Entropy (MaxEnt)—was evaluated using the ROC curve and the Area Under the Curve (AUC) index. The results indicated that the MaxEnt model, with AUC values of 0.98 in the training phase and 0.93 in the validation phase, demonstrated the best performance in predicting flood susceptibility. Analysis of the influencing factors revealed that most floods occurred in precipitation classes of 600–700 mm, distances of 0–100 m from roads and rivers, slope classes of 0–5% and 5–15%, northwest-facing aspects, rainfed agricultural land use, and old alluvial formations. Additionally, a direct relationship was observed between the TWI index and flood occurrence. Finally, the final flood susceptibility zonation map was prepared using the superior MaxEnt model. This research demonstrates that the use of artificial intelligence models, particularly Maximum Entropy (MaxEnt), serves as an efficient tool for identifying flood-prone areas and contributes to effective planning and management for flood control in similar regions. |
Article number: 5 |
| Keywords: Flood susceptibility, Machine learning, Geographic Information System (GIS), Semi-arid regions, Mapping |
|
|
|
Type of Study: Research |
Subject:
Special
Received: 2026/07/2 | Revised: 2026/07/19 | Accepted: 2026/07/22 | ePublished ahead of print: 2026/07/31 | ePublished: 2026/07/31
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
