Abstract
Today, there is an acute issue of prompt provision of up-to-date and most complete spatial information for making optimal management decisions in the forestry industry. The most effective tool for solving many problems in this area is using satellite data. The advent of optical satellites of high spatial resolution (Sentinel-2, Worldview-2,3) makes it possible to use modern methods of operational mapping to solve forestry problems (in particular, identifying burnt areas after a fire). As the monitoring area increases, and the number of images increases, the need for automatic data processing. Thereof to improve the accuracy of recognition of such objects in images is to use deep learning algorithms based on convolutional neural networks. This paper presents a description of the “traditional” methods for burned area detection (vegetation indices, multi-channel, and single-channel change detection, etc.), convolutional neural networks, and their main principles, and limitations. We also present a new method for operational mapping of a burned area using convolutional neural networks and provide an increase in the accuracy of forest fire recognition by more than two times in comparison with traditional methods based on raster arithmetic. The accuracy, estimated by the F-measure, is 0.80 for Haciveliler, 0.93 - Mugla, and 0.95 - Kavaklidere.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abate, N., Elfadaly, A., Masini, N., Lasaponara, R.: Multitemporal 2016–2018 Sentinel-2 data enhancement for landscape archaeology: the case study of the Foggia Province, Southern Italy. Remote Sensing 12(8), 1309 (2020). https://doi.org/10.3390/rs12081309
Al-hasn, R., Almuhammad, R.: Burned area determination using Sentinel-2 satellite images and the impact of fire on the availability of soil nutrients in Syria. J. Forest Sci. 68, 96-106 (2022). https://doi.org/10.17221/122/2021-JFS
Almeida, O., et al.: Validation of normalized difference infrared index (NDII) to estimate soil moisture in traditional olive cultivation systems, Tunisia. In: EGU General Assembly Conference Abstracts, p. 14209. EGU General Assembly Conference Abstracts (2019)
Alzubaidi, L., et al.: Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J. Big Data 8(53), 1–74 (2021). https://doi.org/10.1186/s40537-021-00444-8
Asifullah, K., Anabia, S., Umme, Z., Aqsa, S.: A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 53, 1–62 (2020)
Dimitrios, G., Anastasios, A., Sotirios, K.: Land cover of Greece, 2010: a semi-automated classification using Random Forests. J. Maps 12, 1055–1062 (2016). https://doi.org/10.1080/17445647.2015.1123656
Ding, C., et al.: Boosting few-shot hyperspectral image classification using pseudo-label learning. Remote Sens. 13(17), 3539 (2021). https://doi.org/10.3390/rs13173539
Fragou, S., Kalogeropoulos, K., Stathopoulos, N., Louka, P., Srivastava, P., Karpouzas, E.: Quantifying land cover changes in a mediterranean environment using landsat TM and support vector machines. Forests 11(7), 750 (2020). https://doi.org/10.3390/f11070750
Gao, H., Hrachowitz, M., Sriwongsitanon, N., Fenicia, F., Gharari, S., Savenije, H.: Accounting for the influence of vegetation and landscape improves model transferability in a tropical savannah region. Delft University of Technology (2016). https://doi.org/10.1002/2016wr019574
Garkusha, I., Hnatushenko, V., Vasyliev, V.: Research of influence of atmosphere and humidity on the data of radar imaging by Sentinel-1. In: 2017 IEEE 37th International Conference on Electronics and Nanotechnology (ELNANO), pp. 405–408 (2017). https://doi.org/10.1109/ELNANO.2017.7939787
Giorgos, M., Ioannsi, M., Irene, C.: Evaluating and comparing Sentinel 2a and Landsat-8 operational land imager (OLI) spectral indices for estimating fire severity in a Mediterranean pine ecosystem of Greece. GIsci. Remote Sens. 55, 1–18 (2018). https://doi.org/10.1080/15481603.2017.1354803
Goswami, A., et al.: Change detection in remote sensing image data comparing algebraic and Machine Learning methods. Electronics 11(3), 431 (2022). https://doi.org/10.3390/electronics11030431
Hammadi, A., Ahmed, T., Hichem, T., Wahbi, J.: Evaluation and comparsion of Sentinel-2 MSI, Landsat 8 OLI, and EFFis data for forest fires mapping. illustrations from the summer 2017 fires in Tunisia. In: Geocarto International, pp. 1–20 (2021). https://doi.org/10.1080/10106049.2021.1980118
Hethcoat, M., Edwards, D., Carreiras, J., Bryant, R., França, F., Quegan, S.: A machine learning approach to map tropical selective logging. Remote Sens. Environ. 221, 569–582 (2019). https://doi.org/10.1016/j.rse.2018.11.044
Hnatushenko, V., Hnatushenko, V., Mozgovyi, D., Vasyliev, V., Kavats, O.: Satellite monitoring of consequences of illegal extraction of Amber in Ukraine. Sci. Bull. Natl. Min. Univ. State High. Educ. Inst. “Natl. Min. Univ.” 2(158), 99–105 (2017)
Hordiiuk, D., Hnatushenko, V.: Neural network and local laplace filter methods applied to very high resolution remote sensing imagery in urban damage detection. In: 2017 IEEE International Young Scientists Forum on Applied Physics and Engineering (YSF), pp. 1984–1988 (2017). https://doi.org/10.1109/ysf.2017.8126648
Huo, L., Boschetti, L., Sparks, A.: Object-based classification of forest disturbance types in the Conterminous United States. Remote Sens. 11(5), 477 (2019). https://doi.org/10.3390/rs11050477
Jérôme, L., et al.: Sentinel-2 sen2cor: L2A processor for users. In: ESA Living Planet Symposium 2016, vol. SP-740, pp. 1–8 (2016)
Kashtan, V., Hnatushenko, V.: A Wavelet and HSV Pansharpening Technology of High Resolution Satellite Images. In: 1st International Workshop on Intelligent Information Technologies and Systems of Information Security (IntelITSsi-2020), pp. 67–76 (2020). http://ceur-ws.org/Vol-2623/paper7.pdf
Kashtan, V., Hnatushenko, V., Shedlovska, Y.: Processing technology of multsipectral remote sensing images. 2017 IEEE International Young Scientists Forum on Applied Physics and Engineering (YSF), pp. 355–358 (2017). https://doi.org/10.1109/ysf.2017.8126647
Kostiantyn, I., Mykhailo, Y., Seliverstov, V.: Deep learning for regular change detection in Ukrainian forest ecosystem with sentinel-2. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 14, 364–376 (2021)
Liming, Z., Jinming, L., Chen, L.: Vehicle detection based on remote sensing image of YOLOV3. In: 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) (2020). https://doi.org/10.1109/ITNEC48623.2020.9084975
Liu, J., Maeda, E., Wang, D., Hesikanen, J.: Sensitivity of spectral indices on burned area detection using landsat time series in Savannas of Southern Burkina Faso. Remote Sens. 13(13), 2492 (2021). https://doi.org/10.3390/rs13132492
Liu, Y., Zhong, Y., Qin, Q.: Scene classification based on multiscale Convolutional Neural Network. IEEE Trans. Geosci. Remote Sens 56, 7109–7121 (2018). https://doi.org/10.1109/TGRS.2018.2848473
Miranda, M.S., de Santiago, V.A., Körting, T.S., Leonardi, R., de Freitas, M.L.: Deep convolutional neural network for classifying satellite images with heterogeneous spatial resolutions. In: Gervasi, O., et al. (eds.) ICCSA 2021. LNCS, vol. 12955, pp. 519–530. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87007-2_37
Mohamed, A., Anders, J., Schneider, C.: Monitoring of changes in land use/land cover in Syria from 2010 to 2018 using multitemporal landsat imagery and GSI. Land 9(7), 226 (2020). https://doi.org/10.3390/land9070226
Prati, A., Shan, C., Wang, K.I.K.: Sensors, vision and networks: from video surveillance to activity recognition and health monitoring. J. Ambient Intell. Smart Environ. 11(1), 5–22 (2019). https://doi.org/10.3233/Ais-180510
Quintano, C., Fernández-Manso, A., Fernández-Manso, O.: Combination of landsat and Sentinel-2 MSI data for initial assessing of burn severity. Int. J. Appl. Earth Obs. Geoinf. 64, 221–225 (2018). https://doi.org/10.1016/j.jag.2017.09.014
Rahman, S., Chang, H., Magill, C., Tomkins, K., Hehir: W.: Spatio-temporal assessment of fire severity and vegetation recovery utilising Sentinel-2 imagery in New South Wales, Australia. In: International Geoscience Remote Sensing Symposium, pp. 9960–9963 (2019)
Rauf, H., Saleem, B., Lali, M., Khan, M., Sharif, M., Bukhari, D.: A citrus fruits and leaves dataset for detection and classification of citrus diseases through Machine Learning. Data Brief 26, 104–340 (2019). https://doi.org/10.1016/j.dib.2019.104340
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 779–788 (2016)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. MIT Press, pp. 91-99 (2015)
Rogers, T.W., Jzccard, N., Griffin, L.D.: Automated X-ray image analysis for cargo security: critical review and future promise. J. X-ray Sci. Technol. 25, 33–56 (2017)
Scharvogel, D., Brandmeier, M., Wesi, M.: A deep learning approach for calamity assessment using Sentinel-2 Data. Forests 11(12), 1239 (2020). https://doi.org/10.3390/f11121239
Sriwongsitanon, N., Gao, H., Savenije, H., Maekan, E., Saengsawang, S., Thianpopirug, S.: Comparing the normalized difference infrared index (NDII) with root zone storage in a lumped conceptual model. Hydrol. Earth Syst. Sci. 20, 3361–3377 (2016). https://doi.org/10.5194/hess-20-3361-2016
Tahir, A., et al.: Automatic target detection from satellite imagery using machine learning. Sensors 22(3), 1147 (2022). https://doi.org/10.3390/s22031147
Walter, S., Michele, M., Valter, C., Giorgia, F., Frattaroli, A.: The potentiality of Sentinel-2 to assess the effect of fire events on mediterranean mountain vegetation. Plant Sociol. 57, 11–22 (2020). https://doi.org/10.3897/pls2020571/02
Yulang, C., Jingmin, G., Kebei, Z.: R-CNN-based Satellite components detection in optical images. Int. J. Aeros. Eng., 10 (2020). https://doi.org/10.1155/2020/8816187
Zhu, Q., Zhong, Y., Li, D., Zhang, L.: Adaptive deep sparse semantic modeling framework for high spatial resolution image scene classification. IEEE Trans. Geosci. Remote Sens 56, 6180–6195 (2018)
Acknowledgments
We thank the European Union Copernicus program for providing Sentinel data accessible via the Copernicus Open Access Hub.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kashtan, V., Hnatushenko, V. (2023). Deep Learning Technology for Automatic Burned Area Extraction Using Satellite High Spatial Resolution Images. In: Babichev, S., Lytvynenko, V. (eds) Lecture Notes in Data Engineering, Computational Intelligence, and Decision Making. ISDMCI 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 149. Springer, Cham. https://doi.org/10.1007/978-3-031-16203-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-16203-9_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16202-2
Online ISBN: 978-3-031-16203-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)