Big Data and Predictive Analytics in Fire Risk Using Weather Data.
Big data
fire risk
gradient boosting tree
machine learning
weather
Journal
Risk analysis : an official publication of the Society for Risk Analysis
ISSN: 1539-6924
Titre abrégé: Risk Anal
Pays: United States
ID NLM: 8109978
Informations de publication
Date de publication:
Jul 2020
Jul 2020
Historique:
received:
28
02
2018
revised:
03
06
2019
accepted:
20
03
2020
pubmed:
28
4
2020
medline:
28
4
2020
entrez:
28
4
2020
Statut:
ppublish
Résumé
The objective of this article is to study the impact of weather on the damage caused by fire incidents across the United States. The article uses two sets of big data--fire incidents data from the National Fire Incident Reporting System (NFIRS) and weather data from the National Oceanic and Atmospheric Administration (NOAA)-to obtain a single comprehensive data set for prediction and analysis of fire risk. In the article, the loss is referred to as "Total Percent Loss," a metric that is calculated based on the content and property loss incurred by an owner over the total value of content and property. Gradient boosting tree (GBT), a machine learning algorithm, is implemented on the processed data to predict the losses due to fire incidents. An R
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1438-1449Informations de copyright
© 2020 Society for Risk Analysis.
Références
Badger, S. G. (2008). Large-loss fires in the United States-2009. Bilthoven, The Netherlands: National Fire Protection Association.
Barbero, R., Abatzoglou, J. T., Kolden, C. A., Hegewisch, K. C., Larkin, N. K., & Podschwit, H. (2015). Multi-scalar influence of weather and climate on very large-fires in the Eastern United States. International Journal of Climatology, 35(8), 2180-2186.
Behrendt, A., Payyappalli, V. M., & Zhuang, J. (2019). Modeling the cost effectiveness of fire protection resource allocation in the United States: Models and a 1980-2014 case study. Risk Analysis, 39(6), 1358-1381.
Bureau of Economic Analysis. (n.d). Regional price parities by state and metro area. Retrieved from https://www.bea.gov/data/prices-inflation/regional-price-parities-state-and-metro-area.
Department of Homeland Security. (n.d). National Fire Incident Reporting System (NFIRS) home page. Retrieved from https://www.nfirs.fema.gov/.
Dwoskin, E. (2014). How New York's Fire Department Uses Data Mining. Retrieved from https://blogs.wsj.com/digits/2014/01/24/how-new-yorks-fire-department-uses-data-mining/.
Elith, J., Leathwick, J. R., & Hastie, T. (2008). A working guide to boosted regression trees. Journal of Animal Ecology, 77(4), 802-813.
Fire Science. Weather elements that affect fire behavior. Retrieved from http://www.auburn.edu/academic/forestry_wildlife/fire/.
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29, 1189-1232.
Friedman, J. H. (2002). Stochastic gradient boosting. Computational Statistics & Data Analysis, 38(4), 367-378.
Guelman, L. (2012). Gradient boosting trees for auto insurance loss cost modeling and prediction. Expert Systems with Applications, 39(3), 3659-3667.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning, Vol. 112. New York:Springer.
Keeley, J. E. (2009). Fire intensity, fire severity and burn severity: A brief review and suggested usage. International Journal of Wildland Fire, 18(1), 116-126.
Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In IJCAI, Vol. 14, (pp. 1137-1145). Montreal, Canada.
Lau, C. K., Lai, K. K., Lee, Y. P., & Du, J. (2015). Fire risk assessment with scoring system, using the support vector machine approach. Fire Safety Journal, 78, 188-195.
Miller, J. D., Skinner, C., Safford, H., Knapp, E. E., & Ramirez, C. (2012). Trends and causes of severity, size, and number of fires in northwestern California, USA. Ecological Applications, 22(1), 184-203.
National Centers for Environmental Information. (n.d). National Oceanic and Atmospheric Administration (NOAA). Retrieved from https://www.ncdc.noaa.gov/cdo-web/.
United States Census Bureau. (n.d). Relationship files. Retrieved from https://www.census.gov/geographies/reference-files/time-series/geo/relationship-files.html.
United States Fire Administration. (n.d). Download fire data and data analysis tools. Retrieved from https://www.usfa.fema.gov/data/statistics/order_download_data.html.
United States Fire Administration. (2018). Volunteer fire departments in recruitment crisis. Retrieved from https://www.usfa.fema.gov/operations/infograms/120618.html.
Watts, J. M. & Kaplan, M. E. (2001). Fire risk index for historic buildings. Fire Technology, 37(2), 167-180.
Zhuang, J., Payyappalli, V. M., Behrendt, A., & Lukasiewicz, K. (2017). Total cost of fire in the United States. Fire Protection Research Foundation.