Developing a Portable Solution for Post-Event Analysis Pipelines

TL;DR

The study tackles the need for portable, automated post-event analysis in natural hazards by delivering a Science Gateway-based framework that orchestrates photogrammetric reconstruction and semantic segmentation from UAV imagery. The approach combines Apache Airflow, CWL, and Docker to enable reproducible, cross-platform workflows implemented as two DAGs for photogrammetry and machine learning, running on the INAF PLEIADI HPC/HTC infrastructure. Preliminary field tests in Italy illustrate detailed 3D representations and semantic overlays, validating the framework's potential for rapid damage assessment while highlighting challenges from vegetation, domain shift, and early-stage maturity. The work advances practical hazard mapping by providing a reusable, scalable pipeline and a web-visible visualization interface for stakeholders and insurers.

Abstract

In recent years, the monitoring and study of natural hazards have gained significant attention, particularly due to climate change, which exacerbates incidents like floods, droughts, storm surges, and landslides. Together with the constant risk of earthquakes, these climate-induced events highlight the critical necessity for enhanced risk assessment and mitigation strategies in susceptible areas such as Italy. In this work, we present a Science Gateway framework for the development of portable and fully automated post-event analysis pipelines integrating Photogrammetry techniques, Data Visualization and Artificial Intelligence technologies, applied on aerial images, to assess extreme natural events and evaluate their impact on risk-exposed assets.

Figures (8)

• Figure 1: Science Gateway distributed deployment based on the Workflow platform
• Figure 2: Post-event analysis pipeline
• Figure 3: Graphical overview of the workflow and exported data
• Figure : Tiled Model
• Figure : Tiled Model