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, 2023, Vol. 20, No. 6, pp. 167-176

Satellite data analysis to identify forest fires in Murmansk Region using convolutional neural networks

I.O. Pochinok 1 , I.M. Lazareva 1 , O.I. Lyash 1 
1 Murmansk Arctic University, Murmansk, Russia
Accepted: 26.10.2023
DOI: 10.21046/2070-7401-2023-20-6-167-176
As the intensity of exploration in the Arctic zone of the Russian Federation increases, there is an escalating need for real-time monitoring and prediction of emergencies such as forest fires. Timely identification of fire initiation is pivotal for the preservation of both the environment and human lives. Presently, one of key tools for monitoring expansive territories is remote sensing from space. This study explores the feasibility of using convolutional neural networks to analyze satellite imagery with the objective of identifying thermal hotspots of forest fires within Murmansk Region. Satellites with suitable data were selected for solving the problem. Operational monitoring of Murmansk Region is facilitated through automated downloading, preprocessing, and analysis of satellite data. Software solutions were implemented on the basic architecture of U-Net convolutional neural networks for image segmentation. The conducted analysis results in generation of masks indicating potential fire hotspots. The paper discusses the challenges of the problem solution, particularly considering the limited availability of satellite observation data. The results and evaluation of the effectiveness of using satellite data for rapid detection of fires using machine learning methods are presented. Also, ideas for future research in the considered field are proposed.
Keywords: remote sensing of the Earth, satellite data analysis, Arctic region, wildfires, operational monitoring, convolutional neural network
Full text

References:

  1. Vik K. V., Druki A. A., Grigoriev D. S., Spitsyn V. G., Application of deep learning neural networks for solving the problem of forest fire segmentation on satellite images, Vestnik Tomskogo Gosudarstvennogo Universiteta — Upravlenie, Vychislitel’naya Tekhnika i Informatika, 2021, No. 55, pp. 18–25 (in Russian), DOI: 10.17223/19988605/55/3.
  2. Valasiuk A., Topaz A., Assessment of forest fire effects based on automated processing of Earth remote sensing imagery, J. Belarusian State University. Geography and Geology, 2022, pp. 57–70 (in Russian), DOI: 10.33581/2521-6740-2022-1-57-70.
  3. Druki A. A., Spitsyn V. G., Bolotova Yu. A., Bashlykov A. A., Semantic segmentation of earth scanning images using neural network algorithms, Bull. Tomsk Polytechnic University. Geo Assets Engineering, 2018, Vol. 329, No. 1, pp. 59–68 (in Russian).
  4. Kornilov A. A., Gaponenko L. B., Golubev A. V., On the question of ways to detect forest fires, Pozharnaya bezopasnost’: problemy i perspektivy, 2016, Vol. 1, No. 1(7), pp. 55–56 (in Russian).
  5. Kudrin A. Yu., Zaporozhetsc A. I., Podrezov Yu. V., Modern methods of forest fires detection and monitoring, Tekhnologii grazhdanskoi bezopasnosti, 2006, Vol. 3, No. 4(12), pp. 66–67 (in Russian).
  6. Podrezov Yu. V., Principal directions for prevention of emergency fire situations in forests, Bull. Higher Educational Institutions — Forestry J., 2023, No. 2(392), pp. 172–182 (in Russian), DOI: 10.37482/0536-1036-2023-2-172-182.
  7. Sergienko S. B., Tikhonenko D. V., Processing satellite images with neutron networks for the detection of natural cataclysm, Reshetnevskie chteniya, 2017, Vol. 2, pp. 282–284 (in Russian).
  8. Fedorov R. K., Popova A. K., Avramenko Yu. V., Classification of satellite images with neural networks, Materialy 9-i Mezhdunarodnoi nauchnoi konferentsii “Regional’nye problemy distantsionnogo zondirovaniya Zemli” (Proc. 9th Intern. Scientific Conf. “Regional problems of remote sensing of the Earth”), Krasnoyarsk, 13–16 Sept. 2022, Krasnoyarsk: Siberian Federal University, 2022, pp. 303–306 (in Russian).
  9. Fralenko V. P., Neural network methods for detecting fires in forests, Artificial intelligence and decision-making, 2023, No. 1, pp. 67–77 (in Russian), DOI: 10.14357/20718594230107.
  10. Avhad V., Tanna N., Govekar N. et al., Fire image detection using CNN, Intern. J. Scientific Research in Engineering and Management, 2023, Vol. 7, Issue 4, Article 19013, DOI: 10.55041/ijsrem19013, https://ijsrem.com/download/fire-image-detection-using-cnn.
  11. Bashambu D., Gupta A., Khandelwal S., Real Time Fire and Smoke Detection System, Intern. J. Research in Applied Science and Engineering Technology, 2023, Vol. 11, Issue 4, pp. 2593–2600, DOI: 10.22214/ijraset.2023.54039, https://www.ijraset.com/best-journal/real-time-fire-and-smoke-detection-system.
  12. Kumar S., Roy D., Global operational land imager Landsat-8 reflectance-based active fire detection algorithm, Intern. J. Digital Earth, 2017, Vol. 11, Issue 2, pp. 154–178, DOI: 10.1080 /17538947.2017.1391341.
  13. Meyer-Heß M. F., Pfeffer I., Juergens C., Application of Convolutional Neural Networks on Digital Terrain Models for Analyzing Spatial Relations in Archaeology, Remote Sensing, 2022, Vol. 14, Issue 11, Article 2535, DOI: 10.3390/rs14112535.
  14. Murphy S., Souza-Filho C., Wright R. et al., Hotmap: Global hot target detection at moderate spatial resolution, Remote Sensing of Environment (Elsevier), 2016, Vol. 177, pp. 78–88, DOI: 10.1016/j.rse.2016.02.027.
  15. Pereira G. H., Fusioka A. M., Tomoyuki N. B., Minetto R., Active fire detection in Landsat-8 imagery: A large-scale dataset and a deep-learning study, ISPRS J. Photogrammetry and Remote Sensing, 2021, Vol. 178, pp. 171–186, DOI: 10.1016/J.ISPRSJPRS.2021.06.002.
  16. Rostami A., Shah-Hosseini R., Asgari S. et al., Active Fire Detection from Landsat-8 Imagery Using Deep Multiple Kernel Learning, Remote Sensing, 2022, Vol. 14, Issue 4, Article 992, DOI: 10.3390/rs14040992.
  17. Schroeder W., Oliva P., Giglio L., Csiszar I., The new VIIRS 375 m active fire detection data product: Algorithm description and initial assessment, Remote Sensing of Environment (Elsevier), 2014, Vol. 143, pp. 85–96, DOI: 10.1016/j.rse.2013.12.008.
  18. Wooster M. J., Roberts G. J., Giglio L. et al., Satellite remote sensing of active fires: History and current status, applications and future requirements, Remote Sensing of Environment, 2021, Vol. 267, pp. 112694–112714, DOI: 10.1016/j.rse.2021.112694.
  19. Yang C., Pan Y., Cao Y., Lu X., CNN-Transformer Hybrid Architecture for Early Fire Detection, Artificial Neural Networks and Machine Learning — ICANN, ICANN 2022, Lecture Notes in Computer Science, Cham: Springer, 2022, Vol. 13532, pp. 570–581, DOI: 10.1007/978-3-031-15937-4_48, https://link.springer.com/chapter/10.1007/978-3-031-15937-4_48.
  20. Zhao L., Liu J., Peters S. et al., Investigating the Impact of Using IR Bands on Early Fire Smoke Detection from Landsat Imagery with a Lightweight CNN Model, Remote Sensing, 2022, Vol. 14, Issue 13, Article 3047, DOI: 10.3390/rs14133047, https://www.mdpi.com/2072-4292/14/13/3047/.