Estimating Fire Weather Indices Via Semantic Reasoning Over Wireless Sensor Network Data Streams

摘要

Wildfires are frequent, devastating events in Australia that regularly cause significant loss of life andwidespread property damage. Fire weather indices are a widely-adopted method for measuring fire dangerand they play a significant role in issuing bushfire warnings and in anticipating demand for bushfiremanagement resources. Existing systems that calculate fire weather indices are limited due to low spatialand temporal resolution. Localized wireless sensor networks, on the other hand, gather continuous sensordata measuring variables such as air temperature, relative humidity, rainfall and wind speed at highresolutions. However, using wireless sensor networks to estimate fire weather indices is a challenge due todata quality issues, lack of standard data formats and lack of agreement on thresholds and methods forcalculating fire weather indices. Within the scope of this paper, we propose a standardized approach tocalculating Fire Weather Indices (a.k.a. fire danger ratings) and overcome a number of the challenges byapplying Semantic Web Technologies to the processing of data streams from a wireless sensor networkdeployed in the Springbrook region of South East Queensland. This paper describes the underlyingontologies, the semantic reasoning and the Semantic Fire Weather Index (SFWI) system that we havedeveloped to enable domain experts to specify and adapt rules for calculating Fire Weather Indices. Wealso describe the Web-based mapping interface that we have developed, that enables users to improve theirunderstanding of how fire weather indices vary over time within a particular region. Finally, we discussour evaluation results that indicate that the proposed system outperforms state-of-the-art techniques interms of accuracy, precision and query performance.