Remote Sensing-Based Deep Learning Approach for Identifying Burned Forest Areas

Öz

In this study, the burnt areas and intensity of forest fires that occurred in the Samandağ region of Hatay between September 5-10, 2020, are mapped. Analyses were carried out using deep learning, remote sensing, and satellite data from Sentinel 2. With Sentinel 2 satellite photos of the research locations, an image dataset for deep learning was constructed. Then, using deep learning approaches, a deep learning model was developed, trained using the photos in the dataset, and successfully tested. Images from Sentinel 2 were used to produce the Normalized Burn Ratio(NBR) and Burnt Area Index for Sentinel 2 (BAIS2) indices using the results of a new deep learning model. Calculating the Difference Normalized Burning Intensity (dNBR) and Burnt Area Index for Difference Sentinel-2 (dBAIS2) values for the discrepancies between these indices before and after the fire allowed for categorization and determination of the fire area. The deep learning approach burnt area indexes, and General Directorate of Forestry (GDF) fire registration slips were compared, and it was established that the new deep learning model was more effective at locating burned forest areas than the indexes. In identifying the burnt forest areas, the new model has a proportionate accuracy of 98.36% in the Samandağ study region.

Anahtar Kelimeler

• Deep learning
• Sentinel 2
• NBR-dNBR
• BAIS2-dBAIS2
• Remote sensing

Yanmış Orman Alanlarının Belirlenmesi için Uzaktan Algılama Tabanlı Derin Öğrenme Yaklaşımı

Öz

Bu çalışmada, 5-10 Eylül 2020 tarihleri arasında Hatay'ın Samandağ bölgesinde meydana gelen orman yangınlarının yanık alanları ve şiddeti haritalandırılmıştır. Derin öğrenme, uzaktan algılama ve Sentinel 2 uydu verileri kullanılarak analizler yapılmıştır. Araştırma bölgelerine ait Sentinel 2 uydu fotoğrafları ile derin öğrenme için bir görüntü veri seti oluşturulmuştur. Ardından, derin öğrenme yaklaşımları kullanılarak bir model geliştirilmiş, bu model veri setindeki fotoğraflarla eğitilmiş ve başarıyla test edilmiştir. Sentinel 2'den elde edilen görüntüler, yeni derin öğrenme modelinin sonuçları kullanılarak Normalleştirilmiş Yanma Yoğunluğu (NBR) ve Yanık Alan İndeksi (BAIS2) değerleri hesaplanmıştır. Yangın öncesi ve sonrası bu indeksler arasındaki farklılıkların hesaplanmasıyla Farklı Normalleştirilmiş Yanma Yoğunluğu (dNBR) ve Farklı Yanık Alan İndeksi (dBAIS2) değerleri elde edilerek yangın alanı kategorize edilmiş ve belirlenmiştir. Derin öğrenme yaklaşımı, yanık alan indeksleri ve Orman Genel Müdürlüğü yangın kayıt fişleri karşılaştırılmış ve yeni derin öğrenme modelinin yanmış orman alanlarını belirlemede indekslere göre daha etkili olduğu tespit edilmiştir. Samandağ çalışma bölgesinde, yanık orman alanlarının belirlenmesinde yeni modelin doğruluk oranı %98,36 olarak hesaplanmıştır.

Anahtar Kelimeler

• Derin öğrenme
• Sentinel 2
• NBR-dNBR
• BAIS2-dBAIS2
• Uzaktan algılama

Kaynakça

1. 1. Sabuncu, A. & Özener, H.A. (2019). Uzaktan algılama teknikleri ile yanmış alanların tespiti: İzmir Seferihisar orman yangını örneği. Doğal Afetler ve Çevre Dergisi, 90, 1-9.
2. 2. Özhatay, F., Kültür, Ş. & Gürdal Abamor, B. (2022). Check-list of additional taxa to the supplement of flora of Turkey X. İstanbul Journal of Pharmacy, 52, 227-250.
3. 3. Rulli, M.C. & Rosso, R. (2007). Hydrologic response of upland catchments to wildfires. Advances in Water Resources, 30, 2072-2086.
4. 4. Fidanboy, M., Adar, N. & Okyay, S. (2022). Derin öğrenmeye dayalı orman yangını tahmin modeli geliştirilmesi ve Türkiye yangın risk haritasının oluşturulması. Orman Araştırma Dergisi, 9, 206-218.
5. 5. Sunar, O.N. & Kurnaz, S. (2022). Afet yönetimi bağlamında havacılığın orman yangınlarıyla mücadeledeki rolü üzerine bir değerlendirme. International Journal of Aeronautics and Astronautics, 3, 60-70.
6. 6. Adegun, A.A., Viriri, S. & Tapamo, J.R. (2023). Review of deep learning methods for remote sensing satellite images classification: Experimental survey and comparative analysis. Journal of Big Data, 10, 93.
7. 7. Chen, X., Zhang, Y., Wang, S., Zhao, Z., Liu, C. & Wen, J. (2024). Comparative study of machine learning methods for mapping forest fire areas using Sentinel-1B and 2A imagery. Frontiers in Remote Sensing, 5, 1446641.
8. 8. Chuvieco, E., Martín, M.P. & Palacios, A. (2002). Assessment of different spectral indices in the red–near-infrared spectral domain for burned land discrimination. International Journal of Remote Sensing, 23, 5103-5110.

9. 9. Key, C.H. & Benson, N.C. (1999). Measuring and remote sensing of burn severity: The CBI and NBR. In Proceedings of the Joint Fire Science Conference and Workshop (Vol. II), 2, 284.
10. 10. Miller, J.D. & Thode, A.E. (2007). Quantifying burn severity in a heterogeneous landscape with a relative version of the delta normalized burn ratio (dNBR). Remote Sensing of Environment, 109, 66-80.
11. 11. Filipponi, F. (2018). BAIS2: Burned area index for Sentinel-2. In 2nd International Electronic Conference on Remote Sensing, 364.
12. 12. Mpakairi, K.S., Kadzunge, S.L. & Ndaimani, H. (2020). Testing the utility of the blue spectral region in burned area mapping: Insights from savanna wildfires. Remote Sensing Applications: Society and Environment, 20, 100365.
13. 13. Tanase, M.A., Belenguer-Plomer, M.A., Roteta, E., Bastarrika, A., Wheeler, J., Fernández-Carrillo, Á. et al. (2020). Burned area detection and mapping: Intercomparison of Sentinel-1 and Sentinel-2 based algorithms over tropical Africa. Remote Sensing, 12, 334.
14. 14. Llorens, R., Sobrino, J.A., Fernández, C., Fernández-Alonso, J.M. & Vega, J.A. (2021). A methodology to estimate forest fires burned areas and burn severity degrees using Sentinel-2 data. Application to the October 2017 fires in the Iberian Peninsula. International Journal of Applied Earth Observation and Geoinformation, 95, 102243.
15. 15. Wang, S., Baig, M.H.A., Liu, S., Wan, H., Wu, T. & Yang, Y. (2018). Estimating the area burned by agricultural fires from Landsat 8 data using the vegetation difference index and burn scar index. International Journal of Wildland Fire, 27, 217.
16. 16. Ramo, R., García, M., Rodríguez, D. & Chuvieco, E. (2018). A data mining approach for global burned area mapping. International Journal of Applied Earth Observation and Geoinformation, 73, 39-51.
17. 17. Arıkan, C., Tümer, İ.N., Aksoy, S. & Sertel, E. (2022). Determination of burned areas using Sentinel-2A imagery and machine learning classification algorithms. 2022 4th Intercontinental Geoinformation Days (IGD), Tabriz, 43-46.
18. 18. Seydi, S.T., Hasanlou, M. & Chanussot, J. (2021). DSMNN-net: A deep siamese morphological neural network model for burned area mapping using multispectral Sentinel-2 and hyperspectral PRISMA images. Remote Sensing, 13, 5138.
19. 19. Belenguer-Plomer, M.A., Tanase, M.A., Chuvieco, E. & Bovolo, F. (2021). CNN-based burned area mapping using radar and optical data. Remote Sensing of Environment, 260, 112468.
20. 20. Knopp, L., Wieland, M., Rättich, M. & Martinis, S. (2020). A deep learning approach for burned area segmentation with Sentinel-2 data. Remote Sensing, 12, 2422.
21. 21. Arruda, V.L.S., Piontekowski, V.J., Alencar, A., Pereira, R.S. & Matricardi, E.A.T. (2021). An alternative approach for mapping burn scars using Landsat imagery, Google Earth Engine, and deep learning in the Brazilian savanna. Remote Sensing Applications: Society and Environment, 22, 100472.
22. 22. Hu, X., Ban, Y. & Nascetti, A. (2021). Uni-temporal multispectral imagery for burned area mapping with deep learning. Remote Sensing, 13, 1509.
23. 23. Ghali, R. & Akhloufi, M.A. (2023). Deep learning approaches for wildland fires using satellite remote sensing data: Detection, mapping, and prediction. Fire, 6, 192.
24. 24. Sathishkumar, V.E., Cho, J., Subramanian, M. & Naren, O.S. (2023). Forest fire and smoke detection using deep learning-based learning without forgetting. Fire Ecology, 19, 9.
25. 25. Cocke, A.E., Fulé, P.Z. & Crouse, J.E. (2005). Comparison of burn severity assessments using differenced normalized burn ratio and ground data. International Journal of Wildland Fire, 14, 189-198.
26. 26. Roy, D.P., Huang, H., Boschetti, L., Giglio, L., Yan, L., Zhang, H.H. et al. (2019). Landsat-8 and Sentinel-2 burned area mapping – A combined sensor multi-temporal change detection approach. Remote Sensing of Environment, 231, 111254.
27. 27. Key, C.H. & Benson, N.C. (2006). Landscape assessment (LA) sampling and analysis methods. USDA Forest Service – General Technical Report RMRS-GTR.
28. 28. Lutes, D.C., Keane, R.E., Caratti, J.F., Key, C.H., Benson, N.C., Sutherland, S. et al. (2006). FIREMON: Fire effects monitoring and inventory system. Gen. Tech. Rep. USDA Forest Service, RMRS-GTR-164-CD, 1-55.
29. 29. Han, A., Qing, S., Bao, Y., Na, L., Bao, Y., Liu, X. et al. (2021). Short-term effects of fire severity on vegetation based on Sentinel-2 satellite data. Sustainability, 13, 432.
30. 30. McFeeters, S.K. (1996). The use of the normalized difference water index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17, 1425-1432.
31. 31. Fisher, A., Flood, N. & Danaher, T. (2016). Comparing Landsat water index methods for automated water classification in eastern Australia. Remote Sensing of Environment, 175, 167-182.
32. 32. Fernández-García, V., Beltrán-Marcos, D., Fernández-Guisuraga, J.M., Marcos, E. & Calvo, L. (2022). Predicting potential wildfire severity across southern Europe with global data sources. Science of the Total Environment, 829, 154729.
33. 33. Zhang, T., Su, J., Liu, C., Chen, W.H., Liu, H. & Liu, G. (2017). Band selection in Sentinel-2 satellite for agriculture applications. 2017 23rd International Conference on Automation and Computing (ICAC), Huddersfield, 1-6.