Abstract
Ability to predict the risk of damaging events (e.g. wildfires) is crucial in helping emergency services in their decision making processes, to mitigate and reduce the impact of such events. Today, wildfire rating systems have been in operation extensively in many countries around the world to estimate the danger of wildfires. In this paper we propose a data-driven approach to predict wildfire risk using weather data. We show how we address the inherent challenge arising due to the temporal dynamicity of weather data. Weather observations naturally change in time, with finer-scale variation (e.g. stationary day or night) or large variations (non stationary day or night), and this determines a temporal variation of the predicted wildfire danger. We show how our dynamic wildfire danger prediction model addresses the aforementioned challenge using context-based anomaly detection techniques. We call our predictive model a Context-Based Fire Risk (CBFR) model. The advantage of our model is that it maintains multiple historical models for different temporal variations (e.g. day versus night), and uses ensemble learning techniques to predict wildfire risk with high accuracy. In addition, it is completely unsupervised and does not rely on expert knowledge, which makes it flexible and easily applied to any region of interest. Our CBFR model is also scalable and can potentially be parallelised to speed up computation. We have considered multiple wildfire locations in the Blue Mountains, Australia as a case study, and compared the results of our system with the existing well-established Australian wildfire rating system. The experimental results show that our predictive model has a substantially higher accuracy in predicting wildfire risk, which makes it an effective model to supplement the operational Australian wildfire rating system.
| Original language | English |
|---|---|
| Title of host publication | KDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |
| Subtitle of host publication | August 13-17, 2016 San Francisco, CA, USA |
| Editors | Alex Smola, Charu Aggarwal |
| Place of Publication | New York NY USA |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 245-254 |
| Number of pages | 10 |
| ISBN (Electronic) | 9781450342322 |
| DOIs | |
| Publication status | Published - 2016 |
| Externally published | Yes |
| Event | ACM International Conference on Knowledge Discovery and Data Mining 2016 - Hilton San Francisco Union Square, San Francisco, United States of America Duration: 13 Aug 2016 → 17 Aug 2016 Conference number: 22nd http://www.kdd.org/kdd2016/ |
Conference
| Conference | ACM International Conference on Knowledge Discovery and Data Mining 2016 |
|---|---|
| Abbreviated title | SIGKDD 2016 |
| Country | United States of America |
| City | San Francisco |
| Period | 13/08/16 → 17/08/16 |
| Other | KDD 2016, a premier interdisciplinary conference, brings together researchers and practitioners from data science, data mining, knowledge discovery, large-scale data analytics, and big data. |
| Internet address |
Keywords
- Bushfires
- Context-based anomaly detection
- Data stream mining
- Risk prediction
- Unsupervised learning
- Wildfires
Cite this
}
Dynamic and robust wildfire risk prediction system : an unsupervised approach. / Salehi, Mahsa; Rusu, Laura Irina; Lynar, Timothy; Phan, Anna.
KDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: August 13-17, 2016 San Francisco, CA, USA. ed. / Alex Smola; Charu Aggarwal. New York NY USA : Association for Computing Machinery (ACM), 2016. p. 245-254.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - Dynamic and robust wildfire risk prediction system
T2 - an unsupervised approach
AU - Salehi, Mahsa
AU - Rusu, Laura Irina
AU - Lynar, Timothy
AU - Phan, Anna
PY - 2016
Y1 - 2016
N2 - Ability to predict the risk of damaging events (e.g. wildfires) is crucial in helping emergency services in their decision making processes, to mitigate and reduce the impact of such events. Today, wildfire rating systems have been in operation extensively in many countries around the world to estimate the danger of wildfires. In this paper we propose a data-driven approach to predict wildfire risk using weather data. We show how we address the inherent challenge arising due to the temporal dynamicity of weather data. Weather observations naturally change in time, with finer-scale variation (e.g. stationary day or night) or large variations (non stationary day or night), and this determines a temporal variation of the predicted wildfire danger. We show how our dynamic wildfire danger prediction model addresses the aforementioned challenge using context-based anomaly detection techniques. We call our predictive model a Context-Based Fire Risk (CBFR) model. The advantage of our model is that it maintains multiple historical models for different temporal variations (e.g. day versus night), and uses ensemble learning techniques to predict wildfire risk with high accuracy. In addition, it is completely unsupervised and does not rely on expert knowledge, which makes it flexible and easily applied to any region of interest. Our CBFR model is also scalable and can potentially be parallelised to speed up computation. We have considered multiple wildfire locations in the Blue Mountains, Australia as a case study, and compared the results of our system with the existing well-established Australian wildfire rating system. The experimental results show that our predictive model has a substantially higher accuracy in predicting wildfire risk, which makes it an effective model to supplement the operational Australian wildfire rating system.
AB - Ability to predict the risk of damaging events (e.g. wildfires) is crucial in helping emergency services in their decision making processes, to mitigate and reduce the impact of such events. Today, wildfire rating systems have been in operation extensively in many countries around the world to estimate the danger of wildfires. In this paper we propose a data-driven approach to predict wildfire risk using weather data. We show how we address the inherent challenge arising due to the temporal dynamicity of weather data. Weather observations naturally change in time, with finer-scale variation (e.g. stationary day or night) or large variations (non stationary day or night), and this determines a temporal variation of the predicted wildfire danger. We show how our dynamic wildfire danger prediction model addresses the aforementioned challenge using context-based anomaly detection techniques. We call our predictive model a Context-Based Fire Risk (CBFR) model. The advantage of our model is that it maintains multiple historical models for different temporal variations (e.g. day versus night), and uses ensemble learning techniques to predict wildfire risk with high accuracy. In addition, it is completely unsupervised and does not rely on expert knowledge, which makes it flexible and easily applied to any region of interest. Our CBFR model is also scalable and can potentially be parallelised to speed up computation. We have considered multiple wildfire locations in the Blue Mountains, Australia as a case study, and compared the results of our system with the existing well-established Australian wildfire rating system. The experimental results show that our predictive model has a substantially higher accuracy in predicting wildfire risk, which makes it an effective model to supplement the operational Australian wildfire rating system.
KW - Bushfires
KW - Context-based anomaly detection
KW - Data stream mining
KW - Risk prediction
KW - Unsupervised learning
KW - Wildfires
UR - http://www.scopus.com/inward/record.url?scp=84985038320&partnerID=8YFLogxK
U2 - 10.1145/2939672.2939685
DO - 10.1145/2939672.2939685
M3 - Conference Paper
SP - 245
EP - 254
BT - KDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
A2 - Smola, Alex
A2 - Aggarwal, Charu
PB - Association for Computing Machinery (ACM)
CY - New York NY USA
ER -