.png){kind=icon}
.png){kind=icon}
Return
Near–real-time conflict-related fire detection in Sudan using unsupervised deep learning
.png){kind=icon}
OA
AI
K
D
D
DOI：10.1016/j.srs.2026.100446.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Detects conflict-related fires from daily satellite imagery. • Uses unsupervised deep learning for rapid fire detection. • Tracks war zone conflicts with near-real-time analysis. • Artificial intelligence spots landscape damage without manual labels. • Rapid damage assessment system supports fast humanitarian response.
Keywords:
Conflict-related fire monitoring
Unsupervised deep learning
Variational autoencoder (VAE)
Latent-space change detection
High-resolution satellite imagery
Near–real-time monitoring
Fire damage detection
Conflict monitoring
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.2
Papers:
457
Citations:
980
Organization
Cited Papers