Russian Federation
Voroneg, Voronezh, Russian Federation
Russian Federation
The issue of forest fires is becoming increasingly relevant in the context of climate change and the growing frequency of extreme weather events. Fire prediction based on meteorological data, such as temperature, humidity, wind speed, and precipitation, plays a crucial role in risk management and minimizing damage. This article discusses the application of logistic regression (LR) for assessing the probability of forest fires. LR is an effective tool with advantages in terms of interpretability, computational efficiency, and flexibility in handling various data types. Despite the existence of more complex machine learning models, such as random forests, LR remains a valuable method for initial data analysis and modeling. Research results demonstrate high prediction accuracy, making logistic regression a sought-after tool in both scientific research and practical applications.
forest fires, fire prediction, logistic regression, meteorological data, machine learning, climate change, risk management, temperature, humidity, modeling
1. Comparing machine learning algorithms to predict vegetation fire detections in Pakistan: sayt URL: https://fireecology.springeropen.com/articles/10.1186/s42408-024-00289-5 (data obrascheniya 23.10.2024).
2. Daily prediction modeling of forest fire ignition using meteorological drought indices in the Mexican highlands: sayt URL: https://iforest.sisef.org/contents/?id=ifor3623-014 (data obrascheniya 23.10.2024).
3. A Survey of the Machine Learning Models for Forest Fire Prediction and Detection: sayt URL: https://www.scirp.org/journal/paperinformation?paperid=126584 (data obrascheniya 23.10.2024).
4. Logistic regression versus XGBoost for detecting burned areas using satellite images: sayt URL: https://link.springer.com/article/10.1007/s10651-023-00590-7 (data obrascheniya 23.10.2024).
5. Primenenie modeli logisticheskoy regressii pri prinyatii resheniy po opredeleniyu kolichestva privlekaemyh sil na likvidaciyu lesnyh pozharov: sayt URL: https://www.fire-smi.ru/jour/article/view/1408 (data obrascheniya 23.10.2024).
6. Formalizaciya verifikacii topologii i elektricheskoy shemy dlya sistem avtomatizirovannogo proektirovaniya / T. V. Skvorcova, K. V. Zol'nikov, A. M. Plotnikov, I. V. Skorkin // Modelirovanie sistem i processov. – 2024. – T. 17, № 3. – S. 61-70. – DOIhttps://doi.org/10.12737/2219-0767-2024-59-68. – EDN DUYQHJ.
7. Paramonov, A. A. Issledovanie struktury tropicheskogo ciklona na osnove analiza dannyh sputnikovogo videoryada s primeneniem metoda pochti periodicheskogo analiza / A. A. Paramonov, A. V. Kalach, A. S. Kravchenko // Modelirovanie sistem i processov. – 2024. – T. 17, № 4. – S. 67-76. – DOIhttps://doi.org/10.12737/2219-0767-2024-17-4-67-76. – EDN BOGSTY.
8. Asadov, H. G. Modelirovanie temperaturnogo polya pri lesnyh pozharah / H. G. Asadov, G. Z. Bayramov // Modelirovanie sistem i processov. – 2024. – T. 17, № 4. – S. 7-15. – DOIhttps://doi.org/10.12737/2219-0767-2024-17-4-7-15. – EDN ECSUWP.
9. Sumin, V. I. Osobennosti vybora chlenov ekspertnoy gruppy dlya analiza funkcionirovaniya slozhnoy organizacionnoy sistemy silovyh struktur / V. I. Sumin, A. S. Dubrovin, I. S. Kuscheva // Modelirovanie sistem i processov. – 2024. – T. 17, № 4. – S. 77-83. – DOIhttps://doi.org/10.12737/2219-0767-2024-17-4-77-83. – EDN ISTAML.
10. Yurchishina, M. V. Algoritmicheskaya model' SPPR «Optimal'nyy uchebnyy plan» / M. V. Yurchishina, K. I. Bushmeleva // Modelirovanie sistem i processov. – 2024. – T. 17, № 4. – S. 84-95. – DOIhttps://doi.org/10.12737/2219-0767-2024-17-4-84-95. – EDN OJFBGD.
11. Realizaciya optimal'nogo postroeniya kombinacionnogo ustroystva i ocenka nadezhnosti po vyhodnomu napryazheniyu / F.V. Makarenko, A.S. Yagodkin, K.V. Zol'nikov, O.A. Denisova // Modelirovanie sistem i processov. – 2021. – T. 14, № 4. – S. 130-139. – DOI:https://doi.org/10.12737/2219-0767-2021-14-4-130-139. EDN: https://elibrary.ru/DWSAIO
