Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2022, Vol. 19, No. 3, pp. 77-87

On a model for predicting the probability of occurrence of a natural fire based on remote sensing data of the Earth

E.V. Ivanov 1 , A.V. Rybakov 1 , A.V. Dmitriev 1 , E.K. Fuks 1 
1 Civil Defence Academy EMERCOM of Russia, Khimki, Moscow Region, Russia
Accepted: 15.06.2022
DOI: 10.21046/2070-7401-2022-19-3-77-87
The article describes the main stages of constructing a model for predicting the probability of a natural fire on the data of remote sensing of the Earth. The choice of factors that affect the accuracy of the forecast is justified, their classification is given. Taking into account the identified factors, a mathematical formulation of the problem of estimating the probability of a natural fire in the conditions of the specifics of the localized area for which the forecast is carried out is proposed. A comparison of the main forecasting methods currently used has been carried out, the best one has been selected in terms of accuracy and reliability of the results obtained. On the basis of the formulated formulation of the problem of forecasting the probability of occurrence of wildfires and the proposed method of its solution, a mathematical model for estimating the probability of forecasting wildfires based on the use of big data analysis methods is constructed. In particular, the CatBoost machine learning library, which implements gradient boosting algorithms on decision trees, was used to develop a statistical model. As an example of the implementation of the proposed model based on the data of remote sensing of the Earth, the territory of the Krasnoyarsk Territory was considered. For the presented site, the significance of the contributions of factors affecting the probability of a natural fire was determined, the accuracy of the constructed model for predicting thermal points was 77 %.
Keywords: statistical model, forecasting model, wildfires, heat point, probability of occurrence of a natural fire, remote sensing, big data
Full text

References:

  1. Baranovskiy N. V., Kuznetsov G. V., Development of the Lightning-Ignited Forest Fire Forecast Unit, Gornyi informatsionno-analiticheskii byulleten’, 2009, pp. 83–86 (in Russian).
  2. Bezvesilnaya A. A., Litvin A. A., Smirnov B. P., Statement of Scientific Problem of Substantiation of the Optimal Variant of Automation of Process of Processing Data to Support Decision-Making in an Emergency Situation, Nauchnye i obrazovatel’nye problemy grazhdanskoi zashchity, 2018, No. 4(39), pp. 87–96 (in Russian).
  3. Belousov R. L., Arashtaev A. I., Vologdin V. A., Troflyanin V. V., Analysis of Factors of Natural Fire Hazard of the Forest Territory of The Republic of Tatarstan, Nauchnye i obrazovatel’nye problemy grazhdanskoi zashchity, 2018, No. 1(36), pp. 69–81 (in Russian).
  4. Grishin A. M., Filkov A. I., Prognoz vozniknoveniya i rasprostraneniya lesnykh pozharov (Forecasting the Occurrence and Spread of Forest Fires), Kemerovo: Praktika, 2005, 202 p. (in Russian).
  5. Sokolova G. V., Kogan R. M., Glagolev V. A., Pozharnaya opasnost’ territorii Srednego Priamur’ya: otsenka, prognoz, parametry monitoringa (Fire Danger of Middle Priamurje Territory: Assessment, Prognosis, Monitoring Parameters), Khabarovsk: DVO RAN, 2009, 265 p. (in Russian).
  6. Tregubov P. S., Savenkov P. A., Nebrodova I. N., Modification of the DBSCAN Algorithm: Algorithm WRAPDBSCAN: Application of the WRAPDBSCAN Algorithm in the Problem of Detecting Geolocation Anomalies, Izvestiya Tul’skogo gosudarstvennogo universiteta. Tekhnicheskie nauki, 2021, Vyp. 2, pp. 62–69 (in Russian), DOI: 10.24412/2071-6168-2021-2-62-69.
  7. Shinkarenko S. S., Berdengalieva A. N., Analysis of Steppe Fires Long-Term Dynamics in Volgograd Region, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, Vol. 16, No. 2, pp. 98–110 (in Russian), DOI: 10.21046/2070-7401-2019-16-2-98-110.
  8. Davies D., Kevin M., Helen C., Kathryn R., Beaumont B., Masuoka Ed., Vollmer B., Theobald M., Durbin P., Michael K., Boller R., Schmaltz J., Horrocks K., Ilavajhala S., Ullah A., Teague M., Thompson C., Bingham A., The Use of Nasa Lance Imagery and Data for Near Real-Time Applications, IEEE Intern. Geoscience and Remote Sensing Symp., 2012, pp. 5308–5310, DOI: 10.1109/IGARSS.2012.6352410.
  9. Glenn K. R., Jordan A., Wesley E., NOMADS: A Climate and Weather Model Archive at the National Oceanic and Atmospheric Administration, American Meteorolo gical Society, 2006, pp. 327–341, DOI: 10.1175/BAMS-87-3-327.