Wildfire Susceptibility Mapping Using Deep Learning and Machine Learning Models Based on Multi-Sensor Satellite Data Fusion: A Case Study of Serbia
Problem
Identifying wildfire-susceptible locations and key fire-driving factors across Serbia to support prevention and mitigation.
Why it matters
Wildfires cause significant damage, and susceptibility maps help target prevention efforts.
What the AI did
Machine learning (XGBoost) and deep learning (Kolmogorov-Arnold networks, deep neural network) models trained on 199,598 wildfire samples and 16 variables from multi-sensor satellite data produced wildfire susceptibility maps.
Results
Very-high-vulnerability area of Serbia: XGBoost 11.5%, KAN 14.8%, DNN 15.2%, Ensemble 12.7%.
Impact
Produced integrated wildfire susceptibility maps for Serbia to guide prevention planning.
Record
| Venue | Fire |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Uroš Durlević, Velibor Ilić, Aleksandar Valjarević |
| Citations | 26 (OpenAlex, at import time) |
| References | 76 |
| Model or method | XGBoost, Kolmogorov-Arnold networks (KANs), deep neural network (DNN) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/fire8100407 |
| Open access | gold |
| Keywords | wildfire susceptibility, XGBoost, Kolmogorov-Arnold networks, satellite data fusion, Serbia |
Importance rating
significant — thousands to millions affected
Wildfire susceptibility mapping for an entire country (Serbia, 88,361 km²) using 199,598 samples; maps guide national fire prevention and mitigation planning.
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|