Dynamic and robust wildfire risk prediction system

an unsupervised approach

Mahsa Salehi, Laura Irina Rusu, Timothy Lynar, Anna Phan

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

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 languageEnglish
Title of host publicationKDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Subtitle of host publicationAugust 13-17, 2016 San Francisco, CA, USA
EditorsAlex Smola, Charu Aggarwal
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages245-254
Number of pages10
ISBN (Electronic)9781450342322
DOIs
Publication statusPublished - 2016
Externally publishedYes
EventACM International Conference on Knowledge Discovery and Data Mining 2016 - Hilton San Francisco Union Square, San Francisco, United States of America
Duration: 13 Aug 201617 Aug 2016
Conference number: 22nd
http://www.kdd.org/kdd2016/

Conference

ConferenceACM International Conference on Knowledge Discovery and Data Mining 2016
Abbreviated titleSIGKDD 2016
CountryUnited States of America
CitySan Francisco
Period13/08/1617/08/16
OtherKDD 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

Salehi, M., Rusu, L. I., Lynar, T., & Phan, A. (2016). Dynamic and robust wildfire risk prediction system: an unsupervised approach. In A. Smola, & C. Aggarwal (Eds.), KDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: August 13-17, 2016 San Francisco, CA, USA (pp. 245-254). New York NY USA: Association for Computing Machinery (ACM). https://doi.org/10.1145/2939672.2939685
Salehi, Mahsa ; Rusu, Laura Irina ; Lynar, Timothy ; Phan, Anna. / Dynamic and robust wildfire risk prediction system : an unsupervised approach. KDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: August 13-17, 2016 San Francisco, CA, USA. editor / Alex Smola ; Charu Aggarwal. New York NY USA : Association for Computing Machinery (ACM), 2016. pp. 245-254
@inproceedings{6b0f272ba99b4e19b9ac6d6013d3370e,
title = "Dynamic and robust wildfire risk prediction system: an unsupervised approach",
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.",
keywords = "Bushfires, Context-based anomaly detection, Data stream mining, Risk prediction, Unsupervised learning, Wildfires",
author = "Mahsa Salehi and Rusu, {Laura Irina} and Timothy Lynar and Anna Phan",
year = "2016",
doi = "10.1145/2939672.2939685",
language = "English",
pages = "245--254",
editor = "Smola, {Alex } and Aggarwal, {Charu }",
booktitle = "KDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery (ACM)",
address = "United States of America",

}

Salehi, M, Rusu, LI, Lynar, T & Phan, A 2016, Dynamic and robust wildfire risk prediction system: an unsupervised approach. in A Smola & C Aggarwal (eds), KDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: August 13-17, 2016 San Francisco, CA, USA. Association for Computing Machinery (ACM), New York NY USA, pp. 245-254, ACM International Conference on Knowledge Discovery and Data Mining 2016, San Francisco, United States of America, 13/08/16. https://doi.org/10.1145/2939672.2939685

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 proceedingConference PaperResearchpeer-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 -

Salehi M, Rusu LI, Lynar T, Phan A. Dynamic and robust wildfire risk prediction system: an unsupervised approach. In Smola A, Aggarwal C, editors, KDD' 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: August 13-17, 2016 San Francisco, CA, USA. New York NY USA: Association for Computing Machinery (ACM). 2016. p. 245-254 https://doi.org/10.1145/2939672.2939685