A Method for Improving Initial Attack with Deployment Strategy for Firefighting Water Reserve Points

Abstract

When a forest fire occurs, timely and effective initial attacks can control the fire in its early stages, reducing the risk of spread and minimizing disaster losses. Enhancing the efficiency of forest fire suppression and the success rate of initial attacks has become a critical issue. Therefore, this study thoroughly investigated the key factors of the initial attack phase of forest fires, employing the weighted cross-entropy similarity and relative entropy models, combined with Geographic Information Systems (GIS) and machine learning technologies for precise simulation and analysis. The research introduced additional firefighting water reserve points in the study area to enhance the suppression capability and efficiency of unit firefighting resources, thereby increasing the success rate of the initial attack and reducing the losses caused by fires. An empirical study in Xichang City, Sichuan Province, China, demonstrated that this method significantly improves the success rate of initial attacks. Simulation results indicate that, under various weather conditions, especially extreme weather, the newly established firefighting water reserve points greatly enhance the success rate of initial attacks. This approach not only aids in the scientific planning of firefighting resources but also provides a practical foundation and theoretical guidance for future research to further improve the success rate of initial attacks.

Keywords

Firefighting / Initial attacks / Relative entropy / Weighted cross-entropy / Wildfire

References

[1] Arabatzis, G., G. Kolkos, A. Stergiadou, A. Kantartzis, and S. Tampekis. 2024. Optimal allocation of water reservoirs for sustainable wildfire prevention planning via AHP-TOPSIS and forest road network analysis. Sustainability 16(2): Article 936.

[2] Chander G, Markham BL, Helder DL. Summary of current radiometric calibration coefficients for Landsat MSS, TM, ETM+, and EO-1 ALI sensors. Remote Sensing of Environment, 2009, 113(5): 893-903

[3] Chandrasekaran V, Shah P. Relative entropy optimization and its applications. Mathematical Programming, 2017, 161: 1-32

[4] Chang CI, Chen K, Wang J, Althouse MLG. A relative entropy-based approach to image thresholding. Pattern Recognition, 1994, 27(9): 1275-1289

[5] Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 2002, 16: 321-357

[6] Chen, T., and C. Guestrin. 2016. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13–17 August 2016, San Francisco, CA, USA, 785–794.

[7] Cover TM, Thomas JA. Entropy, relative entropy and mutual information. Elements of Information Theory, 1991, 2(1): 12-13

[8] Cuckovic, Z. 2016. Advanced viewshed analysis: A quantum GIS plug-in for the analysis of visual landscapes. Journal of Open Source Software 1(4): Article 32.

[9] Eugenio FC, Dos Santos AR, Fiedler NC, Ribeiro GA, Da Silva AG, Juvanhol RS, Schettino VR, Marcatti GE, et al.. GIS applied to location of fires detection towers in domain area of tropical forest. Science of the Total Environment, 2016, 562: 542-549

[10] Feyisa GL, Meilby H, Fensholt R, Proud SR. Automated water extraction index: A new technique for surface water mapping using Landsat imagery. Remote Sensing of Environment, 2014, 140: 23-35

[11] Gao D, Liu Y, Hu B, Wang L, Chen W, Chen Y, He T. Time synchronization based on cross-technology communication for IoT networks. IEEE Internet of Things Journal, 2023, 10(22): 19753-19764

[12] Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 2017, 202: 18-27

[13] Haussler D. A general minimax result for relative entropy. IEEE Transactions on Information Theory, 1997, 43(4): 1276-1280

[14] Hirsch KG, Martell DL. A review of initial attack fire crew productivity and effectiveness. International Journal of Wildland Fire, 1996, 6(4): 199-215

[15] Ji S, Zhang Z, Ying S, Wang L, Zhao X, Gao Y. Kullback-Leibler divergence metric learning. IEEE Transactions on Cybernetics, 2022, 52(4): 2047-2058

[16] Lee Y, Lee B, Kim KH. Optimal spatial allocation of initial attack resources for firefighting in the Republic of Korea using a scenario optimization model. Journal of Mountain Science, 2014, 11(2): 323-335

[17] Li J. Study on countermeasures for prevention and control of forest fires in Liangshan Prefecture. Journal of Wildland Fire Science, 2019, 37(3): 9-14

[18] Liang, X.S. 2018. Causation and information flow with respect to relative entropy. Chaos: An Interdisciplinary Journal of Nonlinear Science 28(7): Article 075311.

[19] Lydersen JM, North MP, Collins BM. Severity of an uncharacteristically large wildfire, the Rim Fire, in forests with relatively restored frequent fire regimes. Forest Ecology and Management, 2014, 328: 326-334

[20] Maraş, E.E., K. Dönmez, and Y. Emecen. 2023. GIS-based determination of the optimal heliport and water source locations for forest fire suppression using multi-objective programming. Aerospace 10(3): Article 305.

[21] McFeeters SK. The use of the normalized difference water index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 1996, 17(7): 1425-1432

[22] Mühlenbein H, Höns R. The estimation of distributions and the minimum relative entropy principle. Evolutionary Computation, 2005, 13(1): 1-27

[23] Myneni RB, Hall FG, Sellers PJ, Marshak AL. The interpretation of spectral vegetation indexes. IEEE Transactions on Geoscience and Remote Sensing, 1995, 33(2): 481-486

[24] Ntaimo L, Gallego-Arrubla JA, Gan J, Stripling C, Young J, Spencer T. A simulation and stochastic integer programming approach to wildfire initial attack planning. Forest Science, 2013, 59(1): 105-117

[25] Paudel A, Martell DL, Woolford DG. Factors that affect the timing of the dispatch of initial attack resources to forest fires in Northeastern Ontario Canada. International Journal of Wildland Fire, 2019, 28(1): 15-24

[26] Pettorelli N, Vik JO, Mysterud A, Gaillard J-M, Tucker CJ, Stenseth NC. Using the satellite-derived NDVI to assess ecological responses to environmental change. Trends in Ecology & Evolution, 2005, 20(9): 503-510

[27] Plucinski MP. Modelling the probability of Australian grassfires escaping initial attack to aid deployment decisions. International Journal of Wildland Fire, 2013, 22(4): 459-468

[28] Ramalho, A.H.C., E.F. Da Silva, J.P.M. Silva, N.C. Fiedler, F.D. Maffioletti, L.D. Biazatti, T.R. Moreira, R.S. Juvanhol, and A.R. Dos Santos. 2021. Allocation of water reservoirs to fight forest fires according to the risk of occurrence. Journal of Environmental Management 296: Article 113122.

[29] Ramalho, A.H.C., N.C. Fiedler, A.R. Dos Santos, R.S. Juvanhol, T.M. De Oliveira Pelúzio, H.M. Dias, R.S. Pereira, F.D. Maffioletti, et al. 2024. Forest firefighting technology: Strategic water reservoir placement for terrestrial and aerial vehicles. International Journal of Disaster Risk Reduction 108: Article 104496.

[30] Rodrigues M, Alcasena F, Vega-García C. Modeling initial attack success of wildfire suppression in Catalonia, Spain. Science of the Total Environment, 2019, 666: 915-927

[31] Rokni K, Ahmad A, Selamat A, Hazini S. Water feature extraction and change detection using multitemporal Landsat imagery. Remote Sensing, 2014, 6(5): 4173-4189

[32] Sakellariou, S., A. Sfougaris, and O. Christopoulou. 2020. Location planning of fire service fleet based on forest fire susceptibility. WSEAS Transactions on Environment and Development 16: Article 643.

[33] Wang, S., Y. Dai, J. Shen, and J. Xuan. 2021. Research on expansion and classification of imbalanced data based on SMOTE algorithm. Scientific Reports 11(1): Article 24039.

[34] Wei Y, Bevers M, Belval EJ. Designing seasonal initial attack resource deployment and dispatch rules using a two-stage stochastic programming procedure. Forest Science, 2015, 61(6): 1021-1032

[35] Wulder, M.A., D.P. Roy, V.C. Radeloff, T.R. Loveland, M.C. Anderson, D.M. Johnson, S. Healey, Z. Zhu, et al. 2022. Fifty years of Landsat science and impacts. Remote Sensing of Environment 280: Article 113195.

[36] Xinhua News. 2020. Liangshan Prefecture Xichang City “3·30” forest fire incident investigation results announced [EB/OL]. National Forest and Grassland Fire Prevention Command Office. https://slcyfh.mem.gov.cn/xxfb/xydt/202012/t20201222_509117.html. Accessed 19 Apr 2026 (in Chinese).

[37] Xu, Y., K. Zhou, and F. Zhang. 2023. Modeling wildfire initial attack success rate based on machine learning in Liangshan, China. Forests 14(4): Article 740.

[38] Ye, J., N. Wang, M. Sun, Q. Liu, N. Ding, and M. Li. 2023. A new method for the rapid determination of fire disturbance events using GEE and the VCT algorithm—A case study in southwestern and northeastern China. Remote Sensing 15(2): Article 413.

[39] Zhang D, You X, Liu S, Yang K. Multi-colony ant colony optimization based on generalized Jaccard similarity recommendation strategy. IEEE Access, 2019, 7: 157303-157317

RIGHTS & PERMISSIONS

The Author(s)