Forecasting the Spatial Behavior of a Forest Fire at Uncertainty and Instability of the Process

Authors

DOI:

https://doi.org/10.37482/0536-1036-2021-1-20-34

Keywords:

forest, forest fire, operational forecast, uncertainty, instability, convolutional neural networks, intelligent system

Abstract

The Russian forest fund, being a public domain of the people and a special kind of federal property, requires sustainable management at the national level. One of the key principles of forest management is to ensure that forests are conserved and protected against a wide range of threats, primarily forest fires. Although forest fires are a natural component of forest ecosystems and cannot be completely eliminated, researchers have currently revealed a decrease in the regulatory function and an increase in the destructive function of forest fires. Understanding the interrelations between the environmental factors and forest fire history is necessary for the development of effective and scientifically sound forest safety plans. The main purpose of the study is to increase the efficiency of the formation of an operational forecast of a forest fire in difficult conditions of a real fire (at instability and uncertainty). The author analyzed statistical data on forest fires the USA, Canada, Russia and the five southern European Union member states (Portugal, Spain, France, Italy and Greece) and confirmed the conclusion on the increase in the frequency of large forest fires. The most widely used in practice forecasting models of forest fire dynamics (Van Wagner, Rothermel, Finney, Cruz, etc.) and their computer implementations (Prometheus, FlamMap, FARSITE, VISUAL-SEVEIF, WILDFIRE ANALYST) are presented in the article. It is proposed to develop an intelligent system designed to create an operational forecast of a forest fire using convolutional neural networks (CNN). The structure of this system is described. It includes three main subsystems: information, intelligent and user interface. A key element of the intelligent subsystem is a forest fire propagation model, which recognizes data from sequential images, predicts the forest fire dynamics, and generates an image with a fire spread forecast. The scheme of the proposed model is described. It includes the following stages: data input; preprocessing of input data; recognition of objects using CNNs; forecasting the forest fire dynamics; output of operational forecast. The implementation features of the stage “recognition of objects using CNNs” are presented in detail: core size for each convolutional layer 3×3, activation function ReLu(x), filter in 2×2 pooling layers with step 2, max-pooling method, Object recognition and Semantic segmentation methods at the networks output. 
For citation: Stankevich T.S. Forecasting the Spatial Behavior of a Forest Fire at Uncertainty and Instability of the Process. Lesnoy Zhurnal [Russian Forestry Journal], 2021, no. 1, pp. 20–34. DOI: 10.37482/0536-1036-2021-1-20-34
Acknowledgements: The research was carried out with the financial support from the Russian Foundation for Basic Research, project No. 18-37-00035 mol_а.

Downloads

Download data is not yet available.

Author Biography

Т. С. Станкевич, Калининградский государственный технический университет

Candidate of Engineering; ResearcherID: O-7418-2017

References

ГОСТ 17.6.1.01–83. Охрана природы. Охрана и защита лесов. Термины и определения: дата введения 1985–01–01. М.: Изд-во стандартов, 2002. 6 с. [State Standard. GOST 17.6.1.01–83. Nature Protection. Forest Protection and Preservation. Terms and Definitions. Moscow, Izdatel’stvo standartov, 2002, 6 р.].

ГОСТ 12.3.046–91. Система стандартов безопасности труда. Установки пожаротушения автоматические. Общие технические требования: дата введения 1993–01–01. М.: Изд-во стандартов, 2002. 4 с. [State Standard. GOST 12.3.046–91. Occupational Safety Standards System. Automatic Fire Fighting Systems. General Technical Requirements. Moscow, Izdatel’stvo standartov, 2002. 4 p.].

ГОСТ Р ИСО / МЭК 9126–93. Информационная технология. Оценка программной продукции. Характеристики качества и руководства по их применению: дата введения 1994–07–01. М.: Изд-во стандартов, 2004. 10 с. [State Standard RF ISO/IEC. GOST R ISO/IEC 9126–93. Information Technology. Software Product Evaluation. Quality Characteristics and Guidelines for Their Use. Moscow, Izdatel’stvo standartov, 2004. 10 p.].

Гришин А.М. Математическое моделирование лесных пожаров и новые способы борьбы с ними. Новосибирск: Наука, Сиб. отд-ние, 1992. 405 с. [Grishin A.M. Math ematical Modeling of Forest Fires and New Fire Fighting Techniques. Novosibirsk, Nauka Publ., 1992. 405 p.].

ЕМИСС . Режим доступа: https://fedstat.ru (дата обращения: 06.11.19). [Website of the Unified Interdepartmental Statistical Information System (UISIS)].

Катаева Л.Ю. Анализ динамических процессов аварийных ситуаций природного и техногенного характера: дис. ... д-ра физ.-мат. наук. Н. Новгород, 2009. 328 c. [Katayeva L.Yu. Analysis of Dynamic Processes of Natural and Technogenic Emergency Situations: Dr. Phys.-Math. Sci. Diss. Nizhny Novgorod, 2009. 328 p.].

Конституция Российской Федерации: от 12.12.1993 г. Режим доступа: http://www.consultant.ru/document/cons_doc_LAW_28399/ (дата обращения: 06.11.19). [Constitution of the Russian Federation Dated December 12, 1993].

Лесной кодекс Российской Федерации: федер. закон от 04.12.2006 г. № 200- ФЗ : принят Гос. Думой 08.11.2006 г. Режим доступа: http://www.consultant.ru/document/cons_doc_LAW_64299/ (дата обращения: 06.11.19). [Forest Code of the Russian Federation Dated December 4, 2006: the Federal Law No. 200-FZ].

Масленников Д.А. Особенности математического моделирования распространения лучистого теплового потока от очага горения при лесных пожарах на неоднородном рельефе: дис. ... канд. физ.-мат. наук. Н. Новгород, 2012. 109 с. [Maslennikov D.A. Features of Mathematical Modeling of Radiant Heat Flux Propagation from Burning Source in Case of Forest Fires on Heterogeneous Relief: Cand. Phys.-Math. Sci. Diss. Nizhny Novgorod, 2012. 109 p.].

Национальный доклад Российской Федерации по критериям и индикаторам сохранения и устойчивого управления умеренными и бореальными лесами (Монреальский процесс 2003 г.) // The Montreal Process. Режим доступа: https://www.montrealprocess.org/documents/publications/general/2003/RussiaR/main.html#_Toc45611963 (дата обращения: 06.11.19). [Russia’s Report on the Montreal Process. Criteria and Indicators for the Conservation and Sustainable Management of Temperate and Boreal Forests. 2003].

Ответ Федерального агентства лесного хозяйства № НК -09-50/8211 от 13.05.2019 г. [The Answer of the Federal Agency for Forestry No. NK-09-50/8211 Dated May 13, 2019].

Перминов В.А. Математическое моделирование возникновения верховых и массовых лесных пожаров: дис. ... д-ра физ.-мат. наук. Томск, 2010. 282 с. [Perminov V.A. Mathematical Modeling of the Occurrence of Crown and Large Forest Fires: Dr. Phys.-Math. Sci. Diss. Tomsk, 2010. 282 p.].

Поддубный А. Расчет экономического эффекта от внедрения системы автоматизации // Antegra consulting. Режим доступа: http://www.antegra.ru/news/experts/_det-experts/4/ (дата обращения: 06.11.19). [Poddubnyy A. Calculation of the Economic Effect from the Automation System Implementation. Antegra Consulting].

Порфирьев Б. Пожар по приказу // Эксперт. 2019. № 34(1130). Режим доступа: https://expert.ru/expert/2019/34/pozhar-po-prikazu/ (дата обращения: 06.11.19). [Porfiriev B.N. Fire by Order. Ekspert [Expert], no. 34(1130)].

Свидетельство о регистрации базы данных «Лесные пожары» № 2019620918 от 30.05.2019 г. / Станкевич Т.С. № 2019620843: заявл. 13.05.2019: опубл. 30.05.2019 [Stankevich T.S. Forest Fires. Certificate of State Registration of the Database No. RU2019620918, 2019].

Станкевич Т.С. Применение сверточных нейронных сетей для решения задачи оперативного прогнозирования динамики распространения лесных пожаров // Бизнес-информатика. 2018. № 4(46). С. 17–27. [Stankevich T.S. The Use of Convolutional Neural Networks to Forecast the Dynamics of Spreading Forest Fires in Real Time. Biznes-informatika [Business Informatics], 2018, vol. 4(46), pp. 17–27]. DOI: 10.17323/1998-0663.2018.4.17.27

Adab H., Kanniah K.D., Solaimani K. Modeling Forest Fire Risk in the Northeast of Iran Using Remote Sensing and GIS Techniques. Natural Hazards, 2013, vol. 65, pp. 1723–1743. DOI: 10.1007/s11069-012-0450-8

Agarwal P.K., Patil P.K., Mehal R. A Methodology for Ranking Road Safety Hazardous Locations Using Analytical Hierarchy Process. Procedia – Social and Behavioral Sciences, 2013, vol. 104, pp. 1030–1037. DOI: 10.1016/j.sbspro.2013.11.198

Angayarkkani K., Radhakrishnan N. An Effective Technique to Detect Forest Fire Region through ANFIS with Spatial Data. 3rd International Conference on Electronics Computer Technology, Kanyakumari, April 8–10, 2011. Kanyakumari, India, IEEE, 2011, pp. 24–30. DOI: 10.1109/ICECTECH.2011.5941794

Byram G.M. Combustion of Forest Fuels. Forest Fire: Control and Use. Ed. by K.P. Davis. New York, McGraw-Hill, 1959, pp. 61–89.

Chuvieco E., Aguadoa I., Yebraa M., Nieto H., Salas J., Martín M.P. et al. Development of a Framework for Fire Risk Assessment Using Remote Sensing and Geographic Information System Technologies. Ecological Modelling, 2010, vol. 221, iss. 1, pp. 46–58.

Cruz M.G., Alexander M.E., Wakimoto R.H. Development and Testing of Models for Predicting Crown Fire Rate of Spread in Conifer Forest Stands. Canadian Journal of Forest Research, 2005, vol. 35, no. 7, pp. 1626–1639. DOI: 10.1139/x05-085

Davis R., Yang Z., Yost A., Belongie C., Cohen W. The Normal Fire Environment – Modeling Environmental Suitability for Large Forest Wildfires Using Past, Present, and Future Climate Normals. Forest Ecology and Management, 2017, vol. 390, pp. 173–186. DOI: 10.1016/j.foreco.2017.01.027

Dimopoulou M., Giannikos I. Spatial Optimization of Resources Deployment for Forest Fire Management. International Transactions in Operational Research, 2001, vol. 8, iss, 5, pp. 523–534. DOI: 10.1111/1475-3995.00330

Dimopoulou M., Giannikos I. Towards an Integrated Framework for Forest Fire Control. European Journal of Operational Research, 2002, vol. 152, iss. 2, pp. 476–486. DOI: 10.1016/S0377-2217(03)00038-9

European Forest Fire Information System (EFFIS). Available at: http://effis.jrc.ec.europa.eu (accessed 06.11.19).

FARSITE. Fire Area Simulator. Available at: https://www.firelab.org/project/farsite (accessed 06.11.19).

Finney M.A. FARSITE: Fire area simulator – Model Development and Evaluation. Research Paper RMRS-RP-4. Ogden, UT, Rocky Mountain Research Station, 1998. 47 p. DOI: 10.2737/RMRS-RP-4

FlamMap. Fire Analysis Desktop Application. Available at: https://www.firelab.org/project/flammap (accessed 06.11.19).

Forest Fires Data. National Forestry Database. Available at: http://nfdp.ccfm.org/en/data/fires.php#tab311 (accessed 06.11.19).

Gigovíc L., Pourghasemi H.R., Drobnjak S., Bai S. Testing a New Ensemble Model Based on SVM and Random Forest in Forest Fire Susceptibility Assessment and Its Mapping in Serbia’s Tara National Park. Forests, 2019, vol. 10, iss. 5, art. 408. DOI: 10.3390/f10050408

Guo F., Selvaraj S., Lin F., Wang G., Wang W., Su Z., Liu A. Geospatial Information on Geographical and Human Factors Improved Anthropogenic Fire Occurrence Modeling in the Chinese Boreal Forest. Canadian Journal of Forest Research, 2016, vol. 46, no. 4, pp. 582–594. DOI: 10.1139/cjfr-2015-0373

Land Cover Map ESA/CCI. Available at: http://maps.elie.ucl.ac.be/CCI/viewer/(accessed 06.11.19).

Maeda E.E., Formaggio A.R., Shimabukuro Y.E., Arcoverde G.F.B, Hansen M.C. Predicting Forest Fire in the Brazilian Amazon Using MODIS Imagery and Artificial Neural Networks. International Journal of Applied Earth Observation and Geoinformation, 2009, vol. 11, iss. 4, pp. 265–272. DOI: 10.1016/j.jag.2009.03.003

Martínez J., Vega-García C., Chuvieco E. Human-Caused Wildfire Risk Rating for Prevention Planning in Spain. Journal of Environmental Management, 2009, vol. 90(2), pp. 1241–1252. DOI: 10.1016/j.jenvman.2008.07.005

Mavsar R., Cabán A.G., Varela E. The State of Development of Fire Management Decision Support Systems in America and Europe. Forest Policy and Economics, 2013, vol. 29, pp. 45–55. DOI: 10.1016/j.forpol.2012.11.009

NASA’s Fire Information for Resource Management System (FIRMS). Available at: https://firms.modaps.eosdis.nasa.gov/map/#z:3.0;c:44.286,17.596 (accessed 06.11.19).

Perminov V., Goudov A. Mathematical Modeling of Forest Fires Initiation, Spread and Impact on Environment. International Journal of GEOMATE, 2017, vol. 13, iss. 35, pp. 93–99. DOI: 10.21660/2017.35.6704

Prometheus. Canadian Wildland Fire Growth Simulation Model. Available at: http://www.firegrowthmodel.ca/prometheus/overview_e.php (accessed 06.11.19).

Rodríguez y Silva F., Martínez J.R.M., Machuca M.Á.H., Leal J.M.R. VISUALSEVEIF, a Tool for Integrating the Behavior Simulation and Economic Evaluation of the Impacts of Wildfires. Proceedings of the Fourth International Symposium on Fire Economics, Planning, and Policy: Climate Change and Wildfires. General Technical Report 245. Albany, CA, USDA, 2013, pp. 163–178. DOI: 10.2737/PSW-GTR-245

Rothermel R.C. Predicting Behavior and Size of Crown Fires in the Northern Rocky Mountains. Research Paper INT-438. Ogden, UT, Intermountain Forest Experiment Station, 1991. 46 p. DOI: 10.2737/INT-RP-438

Safi Y., Bouroumi A. Prediction of Forest Fires Using Artificial Neural Networks. Applied Mathematical Sciences, 2013, vol. 7, no. 5-8, pp. 271–286. DOI: 10.12988/ams.2013.13025

Satir O., Berberoglu S., Donmez C. Mapping Regional Forest Fire Probability Using Artificial Neural Network Model in a Mediterranean Forest Ecosystem. Geomatics, Natural Hazards and Risk, 2016, vol. 7, iss. 5, pp. 1645–1658. DOI: 10.1080/19475705.2015.1084541

Sánchez J. Los incendios forestales y las prioridades de investigaciónen México. Tomo II. México, Congreso Forestal Mexicano, 1989, pp. 719–723.

US Wildfires. NOAA’s National Centers for Environmental Information (NCEI). Available at: https://www.ncdc.noaa.gov (accessed 06.11.19).

Van Wagner C.E. Conditions for the Start and Spread of Crown Fire. Canadian Journal of Forest Research, 1977, vol. 7, no. 1, pp. 23–34. DOI: 10.1139/x77-004

Ventusky Aplication. InMeteo. Available at: https://www.ventusky.com (accessed 06.11.19).

Wildfire Analyst Software. Available at: https://www.wildfireanalyst.com/(accessed 06.11.19).

Published

2021-02-25

How to Cite

Станкевич, Т. С. “Forecasting the Spatial Behavior of a Forest Fire at Uncertainty and Instability of the Process”. Lesnoy Zhurnal (Forestry Journal), no. 1, Feb. 2021, pp. 20-34, doi:10.37482/0536-1036-2021-1-20-34.