ABSTRACT
Natural disasters such as flooding, wildfires, and mudslides are rare events, but they affect citizens at unpredictable times and the impact on human life can be significant. Citizens located close to events can provide detailed, real-time data streams capturing their event response. Instead of visualizing individual updates, an integrated spatiotemporal map yields ‘big picture’ event information. We investigate the question of whether information from affected citizens is sufficient to generate a map of an unfolding natural disaster. We built the Citizen Disaster Reaction Multi-Agent Simulation (CDR-MAS), a multi-agent system that simulates the reaction of citizens to a natural disaster in an urban region. We proposed an rkNN classification algorithm to aggregate the update streams into a series of colored Voronoi event maps. We simulated the 2018 Montecito Creek mudslide and customized the CDR-MAS with the local environment to systematically generate stream data sets. Our experimental evaluation showed that event mapping based on citizen update streams is significantly influenced by the amount of citizen participation and movement. Compared with a baseline of 100% participation, with 40% citizen participation, the event region was predicted with 40% accuracy, showing that citizen update streams can provide timely information in a smart city.
Acknowledgments
The authors would like to thank Marc Christen from the RAMMS team in Switzerland for his support with running the mudslide simulations.
Disclosure statement
No potential conflict of interest was reported by the authors.
Additional information
Funding
Notes on contributors
Iranga Subasinghe
Iranga Subasinghe is a third-year Ph.D. student in the School of Computing and Information Science's Spatial Information Science and Engineering program at the University of Maine. He earned a bachelor's degree in Information Technology from the Curtin University, Australia. His doctoral research investigates new methods of real-time processing of citizen data streams, especially in the context of natural disasters.
Silvia Nittel
Silvia Nittel is an Associate Professor, Spatial Informatics, in the School of Computing and Information Science at the University of Maine. She earned a Ph.D. in Computer Science from the University of Zurich, Switzerland. Her research focus is on processing and analysis massive amounts of environmental sensor data streams in real time and the computation and presentation of spatiotemporal fields based on sensor data streams. Her main research area is geosensor networks.
Michael Cressey
Michael Cressey is a second-year Master's student in the School of Computing and Information Science at the University of Maine. He has worked on GIS software development at DeLorme Mapping, ESRI and TomTom. His Master's degree focuses on data stream engines and spatial/temporal data.
Melissa Landon
Melissa Landon is an Associate Professor of Civil and Environmental Engineering at the University of Maine. She earned a Ph.D. degree in Civil and Environmental Engineering at the University of Massachusetts, Amherst. Her research interest is in offshore geotechnics, including site characterization, physical modeling of soil-structure, and foundation engineering for offshore tidal and wind infrastructure.
Prashanta Bajracharya
Prashanta Bajracharya is a second-year master's student in the Department of Civil and Environmental Engineering at the University of Maine. He earned a bachelor’s degree in Civil Engineering from Tribhuvan University, Nepal. His research investigates flood attenuation and other benefits provided by Natural Infrastructure, with a focus on wetlands.