Authors: Shaobo Zhong*, Beijing Research Center of Urban Systems Engineering, Wei Zhu, Beijing Research Center of Urban Systems Engineering, Zhanya Xu, Faculty of Information Engineering, China University of Geosciences
Topics: Hazards, Risks, and Disasters, Remote Sensing, UAS / UAV
Keywords: forest fire, collaborative sensing, knowledge graph
Session Type: Paper
Presentation File: No File Uploaded
Forest fire is great harmful to forest resources, human and property. This year, forest fire occurs frequently in some countries and regions including China. It is universally acknowledged all-sided, accurate and real-time information acquisition will substantially promote decision-making and fire-fighting in forest fire response. Technical support of collaboratively sensing meteorological situation, forest cover, electric power system, parking, hotel, residential places, emergency resources such as rescue power, hydrant or water supply, is imperious to provide materials for decision-making. Though there are ubiquitous sensors available nowadays, they need to be integrated to simultaneously sense in-situ situation of forest fire. Furthermore, those sensed information need to be further recognized and predicted to get insight into the situation and trend of forest fire. A framework is proposed to percept, comprehend and project the emergency situation of forest fire, which utilizes IoT, deep learning neural network, data mining algorithms for situation awareness from field sensors, drone imagery, Internet data. A knowledge graph of forest fire safety is considered as semantic support for enhancing situation extraction for those multiple data sources. Entity, property, and relationship related to forest fire safety is formalized with triple, specifically a geo-ontology is constructed. This framework will be implemented as an advanced information acquisition and cognition component of forest fire emergency management platform in mega cities with wildland-urban interface like Beijing.
To access contact information login