A theoretical framework for improved fire suppression by linking management models with smart early fire detection and suppression technologies

Abstract

Bushfires are devastating to forest managers, owners, residents, and the natural environment. Recent technological advances indicate a potential for faster response times in terms of detecting and suppressing fires. However, to date, all these technologies have been applied in isolation. This paper introduces the latest fire detection and suppression technologies from ground to space. An operations research method was used to assemble these technologies into a theoretical framework for fire detection and suppression. The framework harnesses the advantages of satellite-based, drone, sensor, and human reporting technologies as well as image processing and artificial intelligence machine learning. The study concludes that, if a system is designed to maximise the use of available technologies and carefully adopts them through complementary arrangements, a fire detection and resource suppression system can achieve the ultimate aim: to reduce the risk of fire hazards and the damage they may cause.

References

AkayAE, WingMG, SivrikayaF, SakarD. A GIS-based decision support system for determining the shortest and safest route to forest fires: a case study in the mediterranean region of Turkey. Environ Monit Assess, 2012, 184(3): 1391-1407

AL-DhiefFT, SabriN, FouadS, LatiffNA, AlbaderMAA. A review of forest fire surveillance technologies: mobile ad-hoc network routing protocols perspective. J King Saud Univ-Com, 2019, 31(2): 135-146

AlexanderME, CruzMG. Are the applications of wildland fire behaviour models getting ahead of their evaluation again?. Environ Model Softw, 2013, 41: 65-71

BarmpoutisP, PapaioannouP, DimitropoulosK, GrammalidisN. A review on early forest fire detection systems using optical remote sensing. Sensors, 2020, 20(22): 6442

BonazountasM, KallidromitouD, KassomenosP, PassasN. A decision support system for managing forest fire casualties. J Environ Manage, 2007, 84(4): 412-418

BouabdellahK, NoureddineH, LarbiS. Using wireless sensor networks for reliable forest fires detection. Procedia Comput Sci, 2013, 19: 794-801

CalkinDE, GebertKM, JonesJG, NeilsonRP. Forest service large fire area burned and suppression expenditure trends, 1970–2002. J for, 2005, 103(4): 179-183

Çelik T, Özkaramanlı H, Demirel H (2007) Fire and smoke detection without sensors: image processing- based approach. In: 2007 15th European Signal Processing Conference. IEEE pp. 1794-98 https://doi.org/10.5281/ZENODO.40571

ÇetinAE, DimitropoulosK, GouverneurB, GrammalidisN, GünayO, HabiboǧluYH, TöreyinBU, VerstocktS. Video fire detection–review. Digit Signal Process, 2013, 23(6): 1827-1843

CetinAE, MerciB, GünayO, ToreyinBU, VerstocktS. Multisensor fire analysis, methods, and techniques for fire detection, 2016 Elsevier Ltd 61-82

CruzH, EckertM, MenesesJM. Efficient forest fire detection index for application in unmanned aerial systems (UASs). Sensors, 2016, 16(6): 893

CruzMG, SullivanA, LeonardR, MalkinS, MatthewsS, GouldJS. Fire behaviour knowledge in Australia: a synthesis of disciplinary and stakeholder knowledge on fire spread prediction capability and application, 2014 East Melbourne Bushfire Cooperative Research Centre

CunninghamAA, MartellDL. A stochastic model for the occurrence of man-caused forest fires. Can J Forest Res, 1973, 3(2): 282-287

DantzigGB, RamserJH. The truck dispatching problem. Manage Sci, 1959, 6(1): 80-91

DemirM, KucukosmanogluA, HasdemirM, AcarH, OzturkT. Assessment of forest roads and firebreaks in Turkey. Afr J Biotechnol, 2009, 8(18): 4553-4561

DennisonPE. Fire detection in imaging spectrometer data using atmospheric carbon dioxide absorption. Int J Remote Sens, 2006, 27(14): 3049-3055

ElmasC, SönmezY. A data fusion framework with novel hybrid algorithm for multi-agent decision support system for forest fire. Expert Syst Appl, 2011, 38(8): 9225-9236

FernandesP, BotelhoH, LoureiroC. NeuenschwanderLF, RyanKC. Fire hazard implications of alternative fuel management techniques—case studies from northern Portugal. Proceedings from the joint fire science conference and workshop, 2000 268-270

FlorecV, BurtonM, PannellD, KelsoJ, MilneG. Where to prescribe burn: the costs and benefits of prescribed burning close to houses. Int J Wildland Fire, 2020, 29: 440-458

FrizziS, BouchouichaM, GinouxJ-M, MoreauE, SayadiM. Convolutional neural network for smoke and fire semantic segmentation. IET Image Proc, 2021, 15(3): 634-647

GillessJK, FriedJS. Generating beta random rate variables from probabilistic estimates of fireline production times. Ann Oper Res, 2000, 95: 205-215

Giwa O, Benkrid A (2018) Fire detection in a still image using colour information, https://arxiv.org/abs/1803.03828

GünayO, ToreyinBU, KoseK, CetinAE. Online adaptive decision fusion framework based on entropic projections onto convex sets with application to wildfire detection in video. Opt Eng, 2011, 50(7): 077202

HallyB, WallaceL, ReinkeK, JonesS, SkidmoreA. Advances in active fire detection using a multi-temporal method for next-generation geostationary satellite data. Int J Digital Earth, 2019, 12(9): 1030-1045

HirschKG, RennerMA, RobinsonM. Integrating fire suppression costs into initial-attack models. Can J Forest Res, 2004, 34(9): 1871-1884

JohnsonEA, Van WagnerCE. The theory and use of two fire history models. Can J Forest Res, 1985, 15(1): 214-220

JonesS, ReinkeK, MitchellS, McConachieF, HollandC. Advances in the remote sensing of active fires: a review bus. Coop. Res. Cent. Program, 2017

Krasnov E, Bagaev D (2012) Conceptual analysis of firefighting robots’ control systems. In: 2012 IV International conference problems of cybernetics and informatics (PCI), IEEE, pp. 1–3. DOI: https://doi.org/10.1109/ICPCI.2012.6486328

KrüllW, ToberaR, WillmsI, EssenH, von WahlN. Early forest fire detection and verification using optical smoke, gas and microwave sensors. Procedia Eng, 2012, 45: 584-594

Liew SC (2021) Estimating fire temperature with short-wave infrared bands of high resolution satellites. In: The 42nd Asian Conference on Remote Sensing (ACRS2021) 22–24th November, 2021 in Can Tho University, Can Tho city, Vietnam

Marks M, He Y, Buckley G (2017) False alarms and cost analysis of monitored fire detection systems. In: Fire Safety Engineering Stream Conference: Quantification of Fire Safety: Fire Australia 2017. pp. 99–112. Sydney: Engineers Australia

MartellDL. JohnsonEA, MiyanishiK. Chapter 15 - Forest Fire Management. Forest Fires: behaviour and ecological effects, 2001 San Diego AP 527-583

MartellDL. Forest fire management. Handbook of operations research in natural resources, 2007 New York, NY Springer 489-509

MartellDL. A review of recent forest and wildland fire management decision support systems research. Curr for Rep, 2015, 1(2): 128-137

McCarthy GJ, Tolhurst KG, Wouters MA (2003) Prediction of firefighting resources for suppression operations in Victoria's parks and forests (Vol. 56). Department of Sustainability and Environment, East Melbourne Vic.

Victoria, MinasJP, HearneJW, HandmerJW. A review of operations research methods applicable to wildfire management. Int J Wildland Fire, 2012, 21(3): 189-196

MorganG, TolhurstK, PoynterM, CooperN, McGuffogT, RyanR, WoutersM, StephensN, BlackP, SheehanD. Prescribed burning in south-eastern Australia: history and future directions. Aust for, 2020, 83(1): 1-25

OliveiraS, OehlerF, San-Miguel-AyanzJ, CamiaA, PereiraJMC. Modeling spatial patterns of fire occurrence in Mediterranean Europe using multiple regression and random forest. For Ecol Manag, 2012, 275: 117-129

OlleroA, Martinez-de-DiosJR, MerinoL. Unmanned aerial vehicles as tools for forest-fire fighting. For Ecol Manag, 2006, 234(1): S263

ParksSA. Mapping day-of-burning with coarse-resolution satellite fire-detection data. Int J Wildland Fire, 2014, 23(2): 215-223

Rothermel RC (1972) A mathematical model for predicting fire spread in wildland fuels. Intermountain Forest & Range Experiment Station, Forest Service US Department of Agriculture

ScottV, DunnRCM. A prototype method to rate the link vulnerability of strategic rural roads. Road Transp Res, 2015, 24(2): 3-13

TanSY. PeltonJ, MadryS. Remote sensing applications and innovations via small satellite constellations. Handbook of small satellites, 2020 Cham Springer

TariqA, ShuH, SiddiquiS, MunirI, SharifiA, LiQ, LuL. Spatio-temporal analysis of forest fire events in the Margalla hills, Islamabad, Pakistan using socio-economic and environmental variable data with machine learning methods. J Forestry Res, 2022, 33: 183-194

TaylorM. Vulnerability analysis for transportation networks, 2017 Cambridge, MA Elsevier

ThompsonMP, GannonBM, CaggianoMD. Forest roads and operational wildfire response planning. Forests, 2021, 12(2): 110

TolhurstK, ShieldsB, ChongD. Phoenix: development and application of a bushfire risk management tool. Aust J Emerg Manag, 2008, 23(4): 47-54

VasićC, PredićB. Using GIS in dynamic rellocation of emergency ambulance vehicles. Int J Res Rev Comp Sci (IJRRCS), 2011, 2(1): 211-217

Vilar del HoyoL, Martín IsabelMP, Martínez VegaFJ. Logistic regression models for human-caused wildfire risk estimation: analysing the effect of the spatial accuracy in fire occurrence data. Eur J for Res, 2011, 130: 983-996

VipinV. Image processing-based forest fire detection. Int IJETAE, 2012, 2(2): 87-95

Wilson AE, Wiitala, MR (2005) An empirically based model for estimating wildfire suppression resource response times. United States Department of Agriculture Forest Service General Technical Report PNW vol. 656 p. 189 https://doi.org/10.1016/j.ejor.2024.03.005

ZazaliHH, TowersIN, SharplesJJ. A critical review of fuel accumulation models used in Australian fire management. Int J Wildland Fire, 2020, 30(1): 42-56

ZhaoL, LiuJ, PetersS, LiJ, MuellerN, OliverS. Learning class-specific spectral patterns to improve deep learning-based scene-level fire smoke detection from multi-spectral satellite imagery. RSASE, 2024

ZhaoH, JinJ, LiuY, GuoY, ShenY. FSDF: A high-performance fire detection framework. Expert Syst Appl 238 (part a), 2024

ZhaoL, LiuJ, PetersS, LiJ, OliverS, MuellerN. Investigating the impact of using IR bands on early fire smoke detection from landsat imagery with a lightweight CNN Model. Remote Sens, 2022, 14(13): 3047

Zhukov B, Lorenz E, Oertel D, Wooster M, Roberts G (2005) Experience of detection and quantitative characterization of fires during the experimental small satellite mission BIRD. DLR, Abt. Unternehmensorganisation und-information

Funding

University of South Australia