Challenges and Research Directions from the Operational Use of a Machine Learning Damage Assessment System via Small Uncrewed Aerial Systems at Hurricanes Debby and Helene

2025-06-18

AI Summary

This study addresses four operational bottlenecks encountered during real-world emergency deployments of sUAS-ML damage assessment systems—dynamic input image resolution, misalignment between imagery and geospatial data, offline limitations due to wireless communication dependency, and insufficient output format compatibility—observed during responses to Hurricanes Debby and Helene and Pennsylvania flooding. We present the first end-to-end operational deployment of a sUAS (WingtraOne) integrated with a custom lightweight ML detection model, incorporating multi-scale image adaptation, robust georegistration, and offline inference capabilities to generate damage assessments from high-resolution orthomosaics (>3.5 G pixels). Results validate field feasibility, identify critical engineering constraints, and propose three core optimization pathways: enhancing model robustness to resolution variability, improving georegistration fault tolerance, and strengthening offline deployment reliability. This work provides empirical foundations and a technical framework for standardizing sUAS-ML systems in disaster response.

Technology Category

• Machine Learning: Scalability of ML Systems
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

This paper details four principal challenges encountered with machine learning (ML) damage assessment using small uncrewed aerial systems (sUAS) at Hurricanes Debby and Helene that prevented, degraded, or delayed the delivery of data products during operations and suggests three research directions for future real-world deployments. The presence of these challenges is not surprising given that a review of the literature considering both datasets and proposed ML models suggests this is the first sUAS-based ML system for disaster damage assessment actually deployed as a part of real-world operations. The sUAS-based ML system was applied by the State of Florida to Hurricanes Helene (2 orthomosaics, 3.0 gigapixels collected over 2 sorties by a Wintra WingtraOne sUAS) and Debby (1 orthomosaic, 0.59 gigapixels collected via 1 sortie by a Wintra WingtraOne sUAS) in Florida. The same model was applied to crewed aerial imagery of inland flood damage resulting from post-tropical remnants of Hurricane Debby in Pennsylvania (436 orthophotos, 136.5 gigapixels), providing further insights into the advantages and limitations of sUAS for disaster response. The four challenges (variationin spatial resolution of input imagery, spatial misalignment between imagery and geospatial data, wireless connectivity, and data product format) lead to three recommendations that specify research needed to improve ML model capabilities to accommodate the wide variation of potential spatial resolutions used in practice, handle spatial misalignment, and minimize the dependency on wireless connectivity. These recommendations are expected to improve the effective operational use of sUAS and sUAS-based ML damage assessment systems for disaster response.

Problem

• Challenges in ML damage assessment using sUAS during hurricanes
• Spatial resolution and misalignment issues in disaster imagery
• Need for improved wireless connectivity in operational deployments

Innovation

• sUAS-based ML system for damage assessment
• Handles spatial resolution variation in imagery
• Minimizes dependency on wireless connectivity