UDC 502.051
The article explores the use of artificial neural networks (ANNs) to enhance the accuracy of forest fire risk forecasting in Krasnoyarsk Krai. Given the increasing frequency and scale of wildfires due to climate change, traditional prediction methods show limited effectiveness. A feedforward multilayer neural network was developed, trained on 2018-2023 data encompassing meteorological, forest pathology, and spatiotemporal parameters. The results demonstrate that the proposed model outperforms classical methods (Nesterov’s method, Canadian CFFDRS system), reducing fire area estimation errors by 1.8-2.3 times and improving fire occurrence timing prediction by 27-35%. Special emphasis is placed on analyzing the impact of extreme weather conditions on fire dynamics, revealing nonlinear relationships between factors. The practical relevance of the study is confirmed by testing the model on data from the Siberian Federal District, achieving a 30-40% reduction in response time. Future research directions include integrating satellite monitoring, applying deep learning architectures (LSTM, GRU), and developing a GIS-based decision support system
lesnye pozhary, prognozirovanie, iskusstvennye neyronnye seti, krasnoyarskiy kray, mashinnoe obuchenie, risk-orientirovannyy podhod
1. Caregorodcev V.G., Gorban' A.N. Neyroimitator NeuroPro 0.25: rukovodstvo pol'zovatelya. - Krasnoyarsk: IVM SO RAN, 2020. - 45 s.
2. Nesterov V.G. Metodika ocenki pozharnoy opasnosti po usloviyam pogody. - M.: Lesnaya promyshlennost', 1949. - 87 s.
3. Rosleshoz. Statistika lesnyh pozharov v Krasnoyarskom krae za 2017-2021 gg. - M., 2022. - 134 s.
4. Klimaticheskiy monitoring Sibirskogo federal'nogo okruga / pod red. A.I. Vostokova. - Novosibirsk: Nauka, 2021. - 256 s.
5. Petrov I.V. Primenenie iskusstvennyh neyronnyh setey dlya prognozirovaniya prirodnyh katastrof // Lesnoe hozyaystvo. - 2023. - No 4. - S. 45-52.
6. Sidorov K.A. Sovremennye metody monitoringa lesnyh pozharov s ispol'zovaniem DZZ // Issledovaniya Zemli iz kosmosa. - 2022. - No 3. - S. 78-85.
7. GOST 7.82-2001. Bibliograficheskaya zapis'. Bibliograficheskoe opisanie elektronnyh resursov. - M.: Standartinform, 2008. - 24 s.
8. Ministerstvo prirodnyh resursov i lesnogo kompleksa Krasnoyarskogo kraya [Elektronnyy resurs]. - Rezhim dostupa: http://www.mlx.krskstate.ru/ (data obrascheniya: 15.04.2025).
9. Smith J.R. Neural Networks for Environmental Modeling. - N.Y.: Springer, 2021. - 312 p.
10. Global Forest Watch [Elektronnyy resurs]. - Rezhim dostupa: https://www.globalforestwatch.org (data obrascheniya: 10.04.2025).
