Developing a forest fire prediction model based on deep learning and forecast a fire risk map of Turkey

Year 2022, , 206 - 218, 15.12.2022

Mehmet Fidanboy , Nihat Adar , Savaş Okyay

https://doi.org/10.17568/ogmoad.1066557

Cited By: 3

Abstract

Forest fires are one of the main problems that cause economic losses by threatening natural life and biological ecosystem by disrupting forestry activities. Fires can cause damage to the natural sources like vegetation, water and air, or completely eradicate them. They can also cause loss of life and property by damaging the residential areas and cultivated areas around the forests. Therefore, it is important to make the right decisions and make effective planning on using these resources in order to reduce the risk of forest fires and minimize destruction. In this study, Forest Fire Analysis Forecasting (OYAT) model has created to be used in the fight against forest fires. OYAT has built based on previous fires, vegetation, climate changes and human factors datasets obtained from official sources. OYAT has created by processing these datasets with deep learning techniques. By using OYAT, forest fires can be predicted and a regional fire risk map can be forecasted with analyzed datasets. By its compatibility with geographic information systems (GIS), OYAT has a structure that is easy to use, can be updated with dynamic data, and can be visualized and stored. Forest fire data in Turkey between 2013 and 2019 has used for evaluation OYAT. The maps created with OYAT, have got 98% successful ratio. With the growth of the datasets in the following years, it has predicted that OYAT model will be more efficient and successful in planning for fire prevention.

Keywords

forest fire, risk analysis, artificial intelligence, deep learning

Derin öğrenmeye dayalı orman yangını tahmin modeli geliştirilmesi ve Türkiye yangın risk haritasının oluşturulması

Abstract

Orman yangınları; doğal hayatı, biyolojik ekosistemi tehdit eden ve ormancılık faaliyetlerini sekteye uğratarak ekonomik kayıplara neden olan ana sorunlardan birisidir. Yangınlar; bitki örtüsü, su ve hava gibi doğal kaynakların zarar görmesine veya tamamen yok olmasına neden olabilir. Ayrıca ormanların çevresinde bulunan yerleşim veya tarım alanlarına da hasar vererek can ve mal kayıplarına sebep olabilir. Bu yüzden orman yangınlarıyla mücadele edilmesi ve tahribatın asgari düzeye indirilmesi için kaynakların kullanılmasında doğru kararların verilmesi ve etkili planlamaların yapılması önem arz etmektedir. Bu çalışmada orman yangınlarıyla mücadelede kullanılmak için Orman Yangını Analiz Tahmin (OYAT) modeli oluşturulmuştur. OYAT; resmi kaynaklardan elde edilen bitki örtüsü, iklim değişiklikleri, beşeri etmenler ve daha önceki yangın verilerine dayandırılarak geliştirilmiştir. Bu veriler derin öğrenme tekniği ile işlenerek OYAT modeli oluşturulmuştur. OYAT kullanılarak, analiz edilen veriler ile orman yangını tahmini yapılır ve bölgesel yangın risk haritası elde edilir. OYAT coğrafi bilgi sistemleri (CBS) ile uyumlu çalışabilmesi sayesinde kolay kullanıma sahip, dinamik veriler ile güncellenebilen ve görselleştirilerek saklanabilen bir yapıya sahiptir. Türkiye’deki 2013-2019 yılları arasındaki orman yangını verileri OYAT modelinin değerlendirilmesinde kullanılmıştır. OYAT ile oluşturulan risk haritalarının %98 doğruluk oranına sahip olduğu gözlenmiştir. İzleyen yıllarda veri havuzunun büyümesiyle birlikte, OYAT modelinin yangın önleme için yapılacak planlamalarda daha verimli ve başarılı olacağı öngörülmektedir.

Keywords

orman yangını, risk analizi, yapay zekâ, derin öğrenme

References

• Abadi, M., Barham, P., Chen J., Chen Z., Davis A., Dean J., Devin M., Ghemawat S., Irving G., Isard M., ark. 2016. Tensorflow: A system for large-scale machine lea,rning. 12th symposium on operating systems design and implementation 16: 265–283.
• Achu, A. L., Thomas, J., Aju, C.D., Gopinath, G., Kumar, S., Reghunath, R., 2021. Machine-learning modelling of fire susceptibility in a forest-agriculture mosaic landscape of southern India. Ecological Informatics, s. 101348.
• Ajin, R.S., Loghin, A. M., Vinod, P. G., Jacob, M. K., 2016. RS and GIS-based forest fire risk zone mapping in the Periyar Tiger Reserve, Kerala, India. Journal of Wetlands Biodiversity 6:139–148.
• Ayres, M. P., Lombardero, M. J., 2000. Assessing the consequences of global change for forest disturbance from herbivores and pathogens. Science of the Total Environment 262(3):263–286.
• Burke, D. J., Knisely, C., Watson, M. L., Carrino-Kyker, S. R., Mauk, R. L., 2016. The effects of agricultural history on forest ecological integrity as determined by a rapid forest assessment method. Forest Ecology and Management 378:1–13.
• Cohen, J. D., Deeming J. E. 1985. The national fire-danger rating system: basic equations 82. US Department of Agriculture, Forest Service, Pacific Southwest Forest and Range Experiment Station.
• Cortez, P., Morais, A. D. J. R. (2007). A data mining approach to predict forest fires using meteorological data. I Associação Portuguesa para a Inteligência Artificial (APPIA)
• Dale, H.V., Joyce, L.A., McNulty, S., Neilson, R. P., Ayres, M.P., Flannigan, M.D., Hanson, J.P., Irland, L.C., Lugo, E.A., Peterson, C. J., Simberloff, D., Swanson, F.J., Stocks, B.J., Wotton, B. M., 2001. Climate change and forest disturbances: climate change can affect forests by altering the frequency, intensity, duration, and timing of fire, drought, introduced species, insect and pathogen outbreaks, hurricanes, windstorms, ice storms, or landslides. BioScience 51(9): 723–734.
• Deeming J. E., Brown J.K. 1975. Fuel models in the national fire-danger rating system. Journal of forestry 73(6):347–350.
• Didan, K., Munoz, A. B., Solano, R., & Huete, A. (2015). MODIS vegetation index user’s guide (MOD13 series). University of Arizona: Vegetation Index and Phenology Lab.
• Ekayani, M., Nurrochmat, D.R., Darusman, D., 2016. The role of scientists in forest fire media discourse and its potential influence for policy-agenda setting in Indonesia Forest Policy and Economics 68:22–29.
• FAO. 2020. FAO. 2020. Global Forest Resources Assessment 2020 – Key findings. Rome. URL: https://www.fao.org/3/CA8753EN/CA8753EN.pdf [erişim tarihi: 13-Şubat-2022]. Gai, C., Yuan, H., Weng, W., 2011. GIS-based forest fire risk assessment and mapping. 2011 Fourth International Joint Conference on Computational Sciences and Optimization. IEEE, 1240–1244.
• Grattarola D., Alippi C., 2021. Graph neural networks in tensorflow and keras with spektral. IEEE Computational Intelligence Magazine 16(1):99-106
• Gülçin, D., Deniz, B., 2020. Remote sensing and GIS-based forest fire risk zone mapping: The case of Manisa, Turkey. Turkish Journal of Forestry 21(1):15–24.
• Jaafari, A., Gholami, D. M., Zenner, E. K., 2017. A Bayesian modeling of wildfire probability in the Zagros Mountains, Iran. Ecological informatics 39:32–44.
• Jin, G., Wang, Q., Zhu, C., Feng, Y., Huang, J., Hu, X., 2020. Urban Fire Situation Forecasting: Deep sequence learning with spatio-temporal dynamics. Applied Soft Computing 97:106730.
• Karsai, I., Roland, B., Kampis, G., 2016. The effect of fire on an abstract forest ecosystem: An agent based study. Ecological Complexity 28:12–23.
• Kuang, C., Li, Y., Zhu, S., & Li, J. (2013). Influence of different low air pressure on combustion characteristics of ethanol pool fires. Procedia Engineering 62:226-233.
• Lierop, P., Lindquist, E., Sathyapala, S., Franceschini, G., 2015. Global forest area disturbance from fire, insect pests, diseases and severe weather events. Forest Ecology and Management 352:78–88.
• Martens, D., Backer, M. D., Haesen, R., Baesens, B., & Holvoet, T. (2006). Ants constructing rule-based classifiers. Swarm intelligence in data mining (pp. 21-43). Springer, Berlin, Heidelberg.
• McArthur A.G., 1958. The preparation and use of fire danger tables. Fire Weather Conference, 15–17 Temmuz Melbourne, Avustralya
• Mohajane, M., Costache, R., Karimi, F., Pham, Q. B., Essahlaoui, A., Nguyen, H., Laneve, G., Oudija, F., 2021. Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area. Ecological Indicators 129:107869.
• Mota, P. H. S., Rocha, S. J. S. S. D., Castro, N. L. M. D., Marcatti, G. E., França, L. C. J., Schettini, B. L. S., Villanova, P. H., Santos, H. T. D., Santos, A. R. D., 2019. Forest fire hazard zoning in Mato Grosso State, Brazil. Land use policy 88:104206.
• OGM., 2021. Yangın sayaçları teknik raporları (iç dağıtım) [sayı:E-41170819-622.03-706908]
• URL-1: National Geodetic Survey 2016. World Geodetic System. URL: https://en.wikipedia.org/wiki/World_Geodetic_System [erişim tarihi: 01-Ocak-2022].
• URL-2: 31.10.1985 tarih ve 3234 sayılı Orman Genel Müdürlüğü Teşkilat ve Görevleri Hakkında Kanun Hükmünde Kararnamenin Değiştirilerek Kabulü Hakkında Kanun. URL: https://www.ogm.gov.tr/tr/e-kutuphane-sitesi/mevzuat-sitesi/ [erişim tarihi: 01-Ocak-2022].
• URL-3: OGM Resmi İstatistikleri / Orman Alanları 2019 ve Yanan Alanlar 2019. URL: https://www.ogm.gov.tr/tr/e-kutuphane/resmi-istatistikler [erişim tarihi: 13-Şubat-2022].
• URL-4: NASA Earthdata 2022. URL: https://search.earthdata.nasa.gov/search [erişim tarihi: 13-Şubat-2022].
• URL-5: OGM Resmi İstatistikleri / Orman Alanları 2020 ve Yanan Alanlar 2020. URL: https://www.ogm.gov.tr/tr/e-kutuphane/resmi-istatistikler [erişim tarihi: 13-Şubat-2022].
• URL-6: Geospatial Data Abstraction Library (GDAL) 2022. URL: https://gdal.org/ [erişim tarihi: 13-Şubat-2022].
• URL-7: Quantum Geographic Information System (QGIS) 2022. URL: https://www.qgis.org/tr/site/ [erişim tarihi: 13-Şubat-2022].
• URL-8: World Geodetic System (WGS84) 2021. URL: https://gisgeography.com/wgs84-world-geodetic-system [erişim tarihi: 13-Şubat-2022].
• URL-9: National Aeronautics and Space Administration 2022. URL: https://www.nasa.gov [erişim tarihi: 13-Şubat-2022].
• URL-10: OYAT araştırma sonuçları ve örnek resimler 2022. URL: https://github.com/mfidanboy/orman-yangini [erişim tarihi: 13-Şubat-2022].
• Prasetyo, L. B., Dharmawan, A. H., Nasdian, F. T., Ramdhoni, S., 2016. Historical forest fire occurrence analysis in Jambi Province during the period of 2000–2015: its distribution & land cover trajectories. Procedia Environmental Sciences 33:450–459.
• Qin, C. Z., Zhan, L. J., & Zhu, A. X. (2014). How to apply the geospatial data abstraction library (GDAL) properly to parallel geospatial raster I/O?. Transactions in GIS, 18(6):950-957.
• Román M.O., Wang Z., Shrestha R., Yao T., Kalb V., 2019. Black marble user guide version 1.0. NASA: Washington, DC, USA.
• Ronneberger, O., Fischer, P., Brox, T., 2015. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention. Springer, 234–241.
• Sulla-Menashe, D., & Friedl, M. A. (2018). User guide to collection 6 MODIS land cover (MCD12Q1 and MCD12C1) product. USGS: Reston, VA, USA, 1, 18.
• Tuyen, T. T., Jaafari, A., Yen, H. P. H., Nguyen-Thoi, T., Phong, T. V., Nguyen, H. D., Le, H. V., Phuong, T. T. M., Nguyen, S. H., Prakash, I., Pham, B. T., 2021. Mapping forest fire susceptibility using spatially explicit ensemble models based on the locally weighted learning algorithm. Ecological Informatics 63: 101292.
• Van Wagner C.E., Forest P., ark., 1987. Development and structure of the Canadian forest fireweather index system. Can. For. Serv., Forestry Tech. Rep. Citeseer.
• Yin, H., Kong, F., Li, X., 2004. RS and GIS-based forest fire risk zone mapping in da hinggan mountains. Chinese geographical science 14(3):251–257.
• Yoram J.K., Herring D.D., Ranson K.J., Collatz G.J., 1998. Earth Observing System AM1 mission to earth. IEEE Transactions on Geoscience and Remote Sensing 36(4):1045–1055.
• You, W., Lin, L., Wu, L., Ji, Z., Yu, J., Zhu, J., Fan, Y., He, D., 2017. Geographical information system-based forest fire risk assessment integrating national forest inventory data and analysis of its spatiotemporal variability. Ecological Indicators 77:176–184.
• Zheng, Z., Gao, Y., Yang, Q., Zou, B., Xu, Y., Chen, Y., Yang, S., Wang, Y., Wang, Z., 2020. Predicting forest fire risk based on mining rules with ant-miner algorithm in cloud-rich areas. Ecological Indicators 118: 106772.