An Integrated Two-Stage Deep-Learning Tool for Rapid Post-Hurricane Damage Identification and Repair Scheduling
arXiv:2606.29117v1 Announce Type: cross Abstract: Post-hurricane damage assessment and repair scheduling can require computationally intensive simulation and optimization. This paper presents an integrated two-stage deep-learning tool for rapid damaged-line identification and repair-schedule computation. An available offline synthetic dataset for the IEEE 9500-node test feeder contains 1,700 hurricane scenarios with exposure features, grid metadata, fragility parameters, OpenDSS outputs, damaged-line labels, and Adaptive Large Neighborhood Search reference schedules. Stage 1 benchmarks MLP, Re
The increasing frequency and intensity of natural disasters, coupled with advancements in deep learning and computational power, make the development of rapid response tools critical.
This development allows for faster and more efficient disaster recovery, reducing economic losses and speeding up the restoration of essential services, which is crucial for infrastructure resilience.
The ability to quickly assess damage and schedule repairs post-hurricane will significantly improve disaster management logistics compared to traditional, often manual, assessment methods.
- · Insurance companies
- · Utility companies
- · Disaster relief organizations
- · Construction and repair services
- · Traditional manual damage assessment firms
- · Communities reliant on slow recovery processes
Significantly reduced power outage durations and faster restoration of critical infrastructure post-disaster.
Lower overall economic impact from natural disasters due to expedited recovery and more precise resource allocation.
Potential for integration into broader smart city and resilient infrastructure frameworks, creating a new standard for urban disaster preparedness.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG