Urban fire station location planning using predicted demand and service quality index
Tóm tắt
In this article, we propose a systematic approach for fire station location planning. We develop machine learning models, based on Random Forest and Extreme Gradient Boosting, for demand prediction and utilize the models further to define a generalized index to measure quality of fire service in urban settings. Our model is built upon spatial data collected from multiple different sources. Efficacy of proper facility planning depends on choice of candidates where fire stations can be located along with existing stations, if any. Also, the travel time from these candidates to demand locations need to be taken care of to maintain fire safety standard. Here, we propose a travel time-based clustering technique to identify suitable candidates. Finally, we develop an optimization problem to select best locations to install new fire stations. Our optimization problem is built upon maximum coverage problem, based on integer programming. We further develop a two-stage stochastic optimization model to characterize the confidence in our decision outcome. We present a detailed experimental study of our proposed approach in collaboration with city of Victoria Fire Department, MN, USA. Our demand prediction model achieves true positive rate of 80% and false positive rate of 20% approximately. We aid Victoria Fire Department to select a location for a new fire station using our approach. We present detailed results on improvement statistics by locating a new facility, as suggested by our methodology, in the city of Victoria.
Tài liệu tham khảo
Ahrens, M., Evarts, B.: Fire loss in the united states during 2019. National Fire Protection Association (NFPA) report (2020)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)
Ester, M., Kriegel, H.P., Sander, J. et al.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: kdd, pp. 226–231 (1996)
Turkoglu, D.C., Genevois, M.E.: A comparative survey of service facility location problems. Ann. Oper. Res., pp. 1–70 (2019)
Yao, J., Zhang, X., Murray, A.T.: Location optimization of urban fire stations: access and service coverage. Comput. Environ. Urban Syst. 73, 184–190 (2019)
Aktaş, E., Özaydın, Ö., Bozkaya, B., et al.: Optimizing fire station locations for the Istanbul metropolitan municipality. Interfaces 43(3), 240–255 (2013)
Nyimbili, P.H., Erden, T.: Comparative evaluation of gis-based best-worst method (bwm) for emergency facility planning: perspectives from two decision-maker groups. Nat. Hazards 105(1), 1031–1067 (2021)
Church, R.L., Li, W.: Estimating spatial efficiency using cyber search, gis, and spatial optimization: a case study of fire service deployment in los angeles county. Int. J. Geogr. Inf. Sci. 30(3), 535–553 (2016)
Chevalier, P., Thomas, I., Geraets, D., et al.: Locating fire stations: an integrated approach for Belgium. Socioecon. Plann. Sci. 46(2), 173–182 (2012)
Murray, A.T.: Advances in location modeling: Gis linkages and contributions. J. Geogr. Syst. 12(3), 335–354 (2010)
Soltani, A., Balaghi, R., Rezaei, M., et al.: Spatial analysis and urban land use planning with emphasis on hospital site selection, case study: Isfahan city. Bull. Geogr. Socio-economic Ser. 43(43), 71–89 (2019)
Abdullahi, S., Mahmud, A.R,B., Pradhan, B.: Spatial modelling of site suitability assessment for hospitals using geographical information system-based multicriteria approach at Gazvin city, Iran. Geocarto Int. 29(2), 164–184 (2014)
Erlenkotter, D.: A dual-based procedure for uncapacitated facility location. Oper. Res. 26(6), 992–1009 (1978)
Toregas, C., Swain, R., ReVelle, C., et al.: The location of emergency service facilities. Oper. Res. 19(6), 1363–1373 (1971)
Abareshi, M., Zaferanieh, M.: A bi-level capacitated p-median facility location problem with the most likely allocation solution. Transp. Res. Part B: Methodol. 123, 1–20 (2019)
Bolouri, S., Vafaeinejad, A., Alesheikh, A., et al.: Minimizing response time to accidents in big cities: a two ranked level model for allocating fire stations. Arab. J. Geosci. 13(16), 1–13 (2020)
O’Connor, C.D., Calkin, D.E., Thompson, M.P.: An empirical machine learning method for predicting potential fire control locations for pre-fire planning and operational fire management. Int. J. Wildland Fire 26(7), 587–597 (2017)
Sevinc, V., Kucuk, O., Goltas, M.: A Bayesian network model for prediction and analysis of possible forest fire causes. For. Ecol. Manage. 457(117), 723 (2020)
Eden, J.M., Krikken, F., Drobyshev, I.: An empirical prediction approach for seasonal fire risk in the boreal forests. Int. J. Climatol. 40(5), 2732–2744 (2020)
Choi, M.Y., Jun, S.: Fire risk assessment models using statistical machine learning and optimized risk indexing. Appl. Sci. 10(12), 4199 (2020)
Bui, D.T., Van Le, H., Hoang, N.D.: Gis-based spatial prediction of tropical forest fire danger using a new hybrid machine learning method. Eco. Inform. 48, 104–116 (2018)
Salehi, M., Rusu, L.I., Lynar, T. et al.: Dynamic and robust wildfire risk prediction system: an unsupervised approach. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 245–254 (2016)
Turco, M., Jerez, S., Doblas-Reyes, F.J., et al.: Skilful forecasting of global fire activity using seasonal climate predictions. Nat. Commun. 9(1), 1–9 (2018)
Cheng, T., Wang, J.: Integrated spatio-temporal data mining for forest fire prediction. Trans. GIS 12(5), 591–611 (2008)
Singh Walia, B., Hu, Q., Chen, J., et al.: A dynamic pipeline for spatio-temporal fire risk prediction. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 764–773 (2018)
Madaio, M., Chen, S.T., Haimson, O.L., et al.: Firebird: predicting fire risk and prioritizing fire inspections in Atlanta. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 185–194 (2016)
Agarwal, P., Tang, J., Narayanan, A.N.L., et al.: Big data and predictive analytics in fire risk using weather data. Risk Anal. 40(7), 1438–1449 (2020)
Jin, G., Zhu, C., Chen, X. et al.: Ufsp-net: a neural network with spatio-temporal information fusion for urban fire situation prediction. In: IOP Conference Series: Materials Science and Engineering, IOP Publishing, p. 012050 (2020)
Lau, C.K., Lai, K.K., Lee, Y.P., et al.: Fire risk assessment with scoring system, using the support vector machine approach. Fire Saf. J. 78, 188–195 (2015)
Salehi, M., Rashidi, L.: A survey on anomaly detection in evolving data: [with application to forest fire risk prediction]. ACM SIGKDD Explor. Newsl. 20(1), 13–23 (2018)
Jin, G., Wang, Q., Zhu, C., et al.: Urban fire situation forecasting: deep sequence learning with spatio-temporal dynamics. Appl. Soft Comput. 97(106), 730 (2020)
Jaldell, H.: How important is the time factor? saving lives using fire and rescue services. Fire Technol. 53(2), 695–708 (2017)
Association, N.F.P., et al.: NFPA 1720, standard for the organization and deployment of fire suppression operations, emergency medical operations, and special operations to the public by volunteer fire departments. National Fire Protection Association (2020)
Liu, K., Li, X., Zou, C.C. et al.: Ambulance dispatch via deep reinforcement learning. In: Proceedings of the 28th International Conference on Advances in Geographic Information Systems, pp 123–126 (2020)
Dey, A.: Planning the future fire station in the city of Victoria (2020)
Council, V.C.: Our Victoria Tomorrow. City Council (2019)
Giraud, T. et al.: osrm r package. https://cran.r-project.org/web/packages/osrm/index.html, [Accessed 2 Nov 2020] (2020)
R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria, https://www.R-project.org/ (2019)
Bishop, C.M.: Pattern recognition. Mach. Learn. 128(9) (2006)
Alpaydin, E.: Introduction to Machine Learning. MIT Press (2020)
Church, R., ReVelle, C.: The maximal covering location problem. In: Papers of the Regional Science Association, Springer, pp. 101–118 (1974)
Bureau, U.S.C.: City and town population totals: 2010-2019. https://www.census.gov/data/datasets/time-series/demo/popest/2010s-total-cities-and-towns.html, [Accessed 2 Nov 2020] (2019)
Wu, E.: Planning the future fire station in the city of Victoria https://conservancy.umn.edu/handle/11299/216227, [Accessed 1 Oct 2020] (2020)
County, C.: Carver county’s open data parcels. https://data-carver.opendata.arcgis.com/datasets/open-data-parcels, [Accessed 1 November 2020] (2020)
Census: Census data. https://data.census.gov/cedsci/all?g=0500000US27019.100000, [Accessed 1 Feb 2021] (2020)
FCC: Federal communications commission api documentation for developers. https://geo.fcc.gov/api/census/, [Accessed 1 Feb 2021] (2020)
Bureau, U.S.C.: U.S. census bureau census geocoding service. https://geocoding.geo.census.gov/, [Accessed 1 November 2020] (2020)
County, C.: Carver county’s open data portal. https://data-carver.opendata.arcgis.com/datasets/active-address-points-active911, [Accessed 1 November 2020] (2020)
ArcGIS: Arcgis online. https://www.arcgis.com/, [Accessed 1 Feb 2021] (2021)
County, C.: Fire district shapefiles, carver county’s open data portal. https://data-carver.opendata.arcgis.com/datasets/administrative-fire-districts, [Accessed 1 November 2020] (2020)
Council, C.C.: City township boundary, carver county’s open data portal. https://data-carver.opendata.arcgis.com/datasets/administrative-city-township-boundaries, [Accessed 1 November 2020] (2020)
Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
James, G., Witten, D., Hastie, T., et al.: An Introduction to Statistical Learning, vol. 112. Springer (2013)
Pebesma, E.: Simple Features for R: Standardized Support for Spatial Vector Data. R Journal 10(1), 439–446. https://doi.org/10.32614/RJ-2018-009 (2018)
Studio, I.I.C.O. (2020) V20.1. International Business Machines Corp, Armonk, USA