.png){kind=icon}
.png){kind=icon}
Return
Converting Raw Data Into Actionable Information: A topical review of artificial intelligence, machine learning, and digital twins in disaster management
.png){kind=icon}
OA
AI
A
M
J
E
L
S
B
B
C
P
M
E
D
D
M
DOI：10.1109/mgrs.2025.3642854.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Advances in Earth observations [from satellites, ground measurements, Internet of Things (IoT) devices, and both physical sensors (PSs) and virtual sensors (VSs)], artificial intelligence (AI), and telecommunications offer tremendous potential for disaster management. Converting these data streams into actionable information, however, requires structured and standardized approaches. Most existing literature reviews focus on a single element, Earth observations, AI, or digital twins (DTs), without examining their combined potential. This review article integrates AI, DTs, and geospatial data fusion into a novel unified technology ecosystem for disaster management, highlighting DTs as a framework for data integration, a host environment for AI, and a tool for simulation and visualization. We also identify key performance gaps, illustrate their implications through disaster-relevant examples, and outline a research and implementation road map, providing a comprehensive foundation for advancing operational AI-enabled DTs.
Keywords:
Artificial intelligence
Disaster management
Internet of Things
Real-time systems
Image sensors
Floods
Earth Observing System
Satellites
Machine learning
Digital twins
Journal
IF:
16.4
Papers:
1.0W
Citations:
5.1K
Organization
N
I
Cited Papers