Evaluation of Earthquake Impacts on Land Use and Land Cover (LU/LC) Using Google Earth Engine (GEE), Sentinel-2 Imageries, and Machine Learning: Case Study of Antakya

Year 2023, Volume: 8 Issue: 4, 642 - 650, 31.12.2023

Neslişah Civelek Melis İnalpulat Levent Genç

https://doi.org/10.35229/jaes.1349826

Abstract

Natural disasters, especially earthquakes, known to be the most devastating process that threating human life, ecosystems, and land properties including land use and land cover (LULC). Understanding of such changes may help for rehabilitation processes, as well as presentation of baseline to develop management strategies for further steps. Remote sensing technologies have long been used for determination of change directions and magnitudes after earthquakes while development in cloud-based platforms provided users to avoid issues in storage and processing costs, effectively. In present study, it was aimed to determine LULC changes occurred around Antakya city of Hatay after February 06, 2023 and February 20, 2023 earthquakes, which caused serious losses. Moreover changes within 5 km zone from central coordinates were also investigated by considering individual subzones with 1 km width. One of the most widely used machine learning algorithm, random forest (RF), was used classify Sentinel-2 imageries via Google Earth Engine (GEE) platform. Accuracy assessment procedures were implemented to determine reliabilities of LULC2022 and LULC2023, and accuracies were found over 0.85. Investigation of overall changes have revealed that areas of forest (F) and cultivated fields (CF) were considerably decreased while concrete (C), natural vegetation (N) and water (W) areas have increased. Dispersal of collapse buildings resulted in increase of C class not only at city level, but also within each subzone of 5 km buffer zone. Classification of Sentinel-2 imageries through RF algorithm in GEE provided rapid and reliable results for determining changes in Antakya, whereby periodically monitoring of further changes strongly suggested.

Keywords

Antakya, Earthquake, GEE, LULC, Machine Learning, Sentinel-2

Depremin Arazi Kullanım ve Arazi Örtüsü (AKAÖ) Üzerine Etkilerinin Google Earth Engine (GEE), Sentinel-2 Görüntüleri ve Makine Öğrenmesi Kullanılarak Değerlendirilmesi: Antakya Örneği

Abstract

Doğal afetler, özellikle depremler, insan hayatını, ekosistemleri, arazi kullanımı ve arazi örtüsü gibi arazi (AKAÖ) özelliklerini tehdit eden en tahripkar süreçlerden biridir. Buna benzer değişimlerin anlaşılması rehabilitasyon süreçlerine yardımcı olmanın yanında sonraki aşamalar için yönetim stratejileri geliştirilmesi açısından bir başlangıç noktası sağlar. Depremler sonrasında değişimin yönü ve büyülüğünün belirlenmesinde uzaktan algılama teknolojileri uzun zamandır kullanılmakta olup, buluta dayalı platformların geliştirilmesi bu anlamda kullanıcıların depolama ve işleme maliyeti sorunlarından kaçınmasını etkili bir şekilde sağlamıştır. Bu çalışmada, ciddi kayıplara yol açan 6 Şubat 2023 ve 20 Şubat 2023 depremlerinden sonra Hatay iline bağlı Antakya’ da meydana gelen AKAÖ değişimlerinin belirlenmesi amaçlanmıştır. Bunun yanında, merkez koordinatlarından 5 km uzağı kapsayan zon içerisinde meydana gelen değişimler 1 km genişliğindeki alt zonlar gözetilerek incelenmiştir. Sentinel-2 görüntülerinin Google Earth Engine (GEE) ile sınıflandırılmasında en çok kullanılan makine öğrenmesi algoritmalarından bir olan rassal orman (RO) algoritması kullanılmıştır. AKAÖ2022 ve AKAÖ2023 güvenilirliklerinin belirlenmesi için doğruluk analizi prosedürleri uygulanmış, ve doğruluklar 0.85’ in üzerinde bulunmuştur. Genel değişimlerin incelenmesi betonarme (B), doğal vejetasyon (D) ve su (S) alanların artarkenorman (O) ve tarım (T) alanlarının dikkate değer şekilde azaldığını göstermiştir. Çöken binaların dağılışı yalnızca şehir düzeyinde değil, 5 km tampon zor içerisindeki herbir alt zon içerisinde B sınıf artışı ile sonuçlanmıştır. Sentinel-2 görüntülerinin RO algoritması ile GEE’ nda sınıflandırılması Antakya’ da meydana gelen değişimlerin belirlenmesinde hızlı ve güvenilir sonuçları vermiş olup, gelecekteki değişimlerin periyodik olarak izlenmesi şiddetle önerilmiştir.

Keywords

AKAÖ, Antakya, Deprem, GEE, Makine Öğrenmesi, Sentinel-2

References

• Amani, M., Ghorbanian, A., Ahmadi, S.A., Kakooei, M., Moghimi, A., Mirmazloumi, S.M., Moghaddam, S.H.A., Mahdavi, S., Ghahremanloo, M., Parsian, S., Wu, Q. & Brisco, B. (2020). Google Earth Engine cloud computing platform for remote sensing big data applications: A comprehensive review. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 13, 5326-5350.
• An, Q., Feng, G., He, L., Xiong, Z., Lu, H., Wang, X. & Wei, J. (2023). Three-dimensional deformation of the 2023 Turkey Mw 7.8 and Mw 7.7 earthquake sequence obtained by fusing optical and SAR images. Remote Sensing, 15, 2656.
• Balamurugan, G. & Aravind, S.M. (2015). Land use land cover changes in pre- and post-earthquake affected area using Geoinformatics-Western Coast of Gujarat, India. Disaster Advances, 8(4), 8313.
• Bharatkar, P.S. & Patel, R. (2013). Approach to accuracy assessment tor RS image classification techniques. International Journal of Scientific & Engineering Research, 4(12), 79-86.
• Breiman, L. (2001). Random forests. Mach. Learn., 45, 5- 32.
• Chen, Y. & Makoto, N. (2021). Analysis of changes in land use/land cover and hydrological processes caused by earthquakes in the Atsuma River Basin in Japan. Remote Sensing, 13, 13041.
• Cohen, J. (1960). A Coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20, 37-46.
• Demirkesen, A.C. (2012). Multi-risk interpretation of natural hazards for settlements of the Hatay province in the east Mediterranean Region,Turkey using SRTM DEM. Environ. Earth Sci., 65, 1895-1907.
• Gkougkoustamos, J., Krassakis, P., Kalogeropoulou, G. & Parcharidis, I. (2023). Correlation of ground deformation induced by the 6 February 2023 M7.8 and M7.5 earthquakes in Turkey inferred by Sentinel-2 and critical exposure in Gaziantep and Kahramanmaras cities. GeoHazards, 4, 267-285.
• Gokceoglu, C. (2023). 6 February 2023 Kahramanmaraş - Türkiye earthquakes : A general overview. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLVIII-M-1-2023 39th International Symposium on Remote Sensing of Environment (ISRSE-39) “From Human Needs to SDGs”, 24-28 April 2023, Antalya, Türkiye, 417- 424.
• Gou, Y., Li, H., Liang, P., Xiong, R., Chaozhong, H. & Xu, Y. (2023). Preliminary report of coseismic surface rupture (part) of Turkey's MW7.8 earthquake by remote sensing interpretation. Earthquake Research Advances, 100219. DOI: 10.1016/j.eqrea.2023.100219
• Guner, B. (2020). A periodical approach to earthquake damages in Turkey; 3 periods, 3 earthquakes. Eastern Geographical Review, 25(43), 139-152.
• Joshi, G., Natsuaki, R. & Hirose A. (2021). Multi-sensor satellite-imaging data fusion for earthquake damage assessment and the significant features. 7th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR). 1 November 2021, 1-6.
• Landis, J.R. & Koch, G.G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33(1), 159-174.
• Lee, C.S., You, Y.H. & Robinson, G.R. (2002). Secondary succession and natural habitat restoration in abandoned rice fields of central Korea. Restor. Ecol., 10, 306-314.
• Levin, N. (2023). Using night lights from Space to assess areas impacted by the 2023 Turkey earthquake. Remote Sensing, 15, 2120.
• Loukika, K.N., Keesara, V.R. & Sridhar, V. (2021). Analysis of land use and land cover using machine learning algorithms on Google Earth Engine for Munneru River Basin, India. Sustainability, 13, 13758.
• Ozcelik, A.E., Corbaci, O.L. & Yuksek, T. (2023). Spatial analysis of green areas located in affected cities by the Kahramanmaras centered earthquake according to earthquake susceptibility with Geographical Information Systems. Journal of Anatolian Environmental and Animal Sciences, 8(3), 273-282.
• Ozyavuz, M., Donmez, Y. & Corbaci, O.L. (2016). Natural disaster management availability of open and green areas; example of earthquake park. Doğal Afet ve Afet Yönetimi Sempozyumu (DAAYS’16), 2-4 Mart 2016, Karabük, Türkiye.
• Portillo, A. & Moya, L. (2023). Seismic risk regularization for urban changes due to earthquakes: A case of study of the 2023 Turkey earthquake sequence. Remote Sens., 15, 2754.
• Roy, K., Sasada, K. & Kohno, E. (2014). Salinity status of the 2011 Tohoku-oki tsunami affected agricultural lands in Northeast Japan. International Soil and Water Conservation Research, 2(2), 40-50.
• Velastegui Montoya, A., Rivera Torres, H., Herrera Matamoros, V., Sades, L. & Pacheco Quevedo, R. (2022). Application of Google Earth Engine for land cover classification in Yasuni National Park, Ecuador. International Geoscience and Remote Sensing Symposium, 17-22 July 2022, Kuala-Lumpur, Malaysia, 6376-6379.
• Vizzari, M. (2022). Planetscope, Sentinel-2, and Sentinel1 data integration for object-based land cover classification in Google Earth Engine. Remote Sensing, 14(11), 2628.
• Yan, Z., Huazhong, R. & Desheng, C. (2018). The research of building earthquake damage objectoriented change detection based on ensemble classifier with remote sensing image. Geoscience and Remote Sensing Symposium, 22-27 July 2018, Valencia, Spain, 4950-4953.
• Yavasoglu, F. & Varol Ozden C.(2017). Using geographic information systems (GIS) BASED analytic hierarchy process (AHP) earthquake damage risk analysis: Kadikoy case. Turkish Science Research Foundation, 10(3), 28-38.
• Yuan, Y., Wang, C., Liu, S., Chen, Z., Ma, X., Li, W., Zhang, L. & Yu, B. (2023). The changes in nighttime lights caused by the Turkey–Syria earthquake using NOAA-20 VIIRS Day/Night band data. Remote Sensing, 15, 3438.
• Yoshii, T., Imamura, M., Matsuyama, M., Koshimura, S., Matsuoka, M., Mas, E. & Jimenez, C. (2012). Salinity in soils and tsunami deposits in areas affected by the 2010 Chile and 2011 Japan Tsunamis. Pure and Applied Geophysics, 170(6- 8), 1047-1066.