Multimodal Analysis of Geo-social Media Data for Improved Disaster Management: From Science to Digital Practice
The challenges that emergency services face when dealing with disasters are becoming increasingly complex. Thus, methods of analysing new digital information for situation assessment and operational planning is of crucial importance. This talk presents an approach for multi-modal analysis of digital data such as geo-social media posts using artificial intelligence (AI), helping to ensure the protection and rescue of people and critical infrastructure. The approach presented aims at the AI-supported and automated analysis of this data so that holistic, spatio-temporal situation information is available to end users. It fuses information from social media including semantic topics, sentiments and emotions, spatial hot spots, and temporal changes. The talk outlines the potential of digital data analysis for operational practice: The research results were tested in a realistic application during a large-scale disaster exercise with around 900 emergency staff. The large-scale exercise, coordinated by an professional operations team, was designed around a once-in-a-century flood event and included four operational phases, namely a building collapse, flooded buildings, the derailment of a dangerous goods train, and people floating in a river. The results of the exercise demonstrate that digital data sources can provide crucial added value for situation assessment and staff work, both in terms of rapid situation assessment and efficient resource and operational planning.
Lecture by Resch Bernd.
Data Storytelling and Big Data value chain in Natural Disaster Management
This lecture explores the concepts of Data Storytelling and the Big Data value chain in the context of Natural Disaster Management. It delves into the significance of effectively communicating data to inform decision-making and seeks to uncover the potential of utilizing big data to improve disaster response and mitigation efforts. The lecture discusses the challenges posed by natural disasters and the need for comprehensive data analysis to understand their impacts. It presents Data Storytelling as a powerful tool to present complex data in a compelling and understandable manner, empowering stakeholders to make informed choices. Furthermore, the lecture examines the Big Data value chain, emphasizing its components such as data acquisition, storage, processing, analysis, visualization, and interpretation, and their crucial role in disaster management. It highlights how this chain can enable improved situational awareness, early warning systems, resource allocation, and risk assessment. Through a combination of case studies and interactive discussions, the lecture aims to equip participants with the knowledge and skills to harness the potential of data storytelling and the big data value chain to enhance natural disaster management strategies.
Lecture by Antonio Filograna.
Deep Learning for Post-Earthquake Safety Evaluation of Masonry Buildings
Natural disasters present multifaceted challenges that necessitate swift and accurate responses. In the realm of post-earthquake safety assessments, the rapid and precise evaluation of damages is pivotal to ensure the optimal allocation of resources and facilitate effective emergency management. Many earthquake-prone nations employ standardized forms, such as the Italian AeDES, New Zealand Earthquake Rapid Assessment, and American ATC-20 Rapid Evaluation Safety Assessment, to capture and analyze damage data during inspections. However, the manual compilation of these forms can be error-prone, leading to potential misrepresentations of the actual damage scenario. The lecture introduces a Deep Learning-based methodology designed to enhance the accuracy and efficiency of these assessments. The tool can recognize, localize, and quantify damages by processing and analyzing drone photos of the affected buildings. Participants will gain insights into the methodology of this approach, its real-world applications, and its potential to reshape the future of natural disaster management using big data analytics.
Lecture by Giovanni Giacco.
Maestro: Forecasting and Risk Management in Forest Fires via IoT Technologies
The Maestro telemetry system predicts forest fire risk based on geolocated weather data collected by sensor nodes. Sensor nodes provide a low-cost solution to reliably monitor the microclimate of forested areas and to correlate the current conditions with possible prolonged drought. In case of fire, nodes fall into emergency mode by transmitting more frequent measurements to support real-time prediction of how the fire spreads, for effectively managing the available firefighting forces and for implementing appropriate population evacuation plans.
Lecture by Prof. Panagiotis Katsaros.
Forest Fire Monitoring and Measuring with Multiple Cooperating Drones
Real-time forest fire perception, monitoring and measuring is a very complex problem of that requires the fusion of different types of sensors and cameras. Using several cooperating aerial robots (drones) is an ideal approach to gather high quality images and measurements at different vantage points suitable for fire status estimation and to process them in a decentralized manner exploiting on-board drone computation capacity. This presentation will summarize different approaches, schemes, methods and will present some results obtained in wildfire experiments.
Lecture by Jose Ramiro Martinez De Dios.
Drone imaging for NDMs
Lecture by Nikolaos Militsis.