Producing land use maps with Google Earth Engine

Yıl 2021, Cilt: 10 Sayı: 1, 38 - 47, 15.01.2021

Majid Aghlmand , Kaan Kalkan , Mehmet İnanç Onur , Gürkan Öztürk , Ecem Ulutak

https://doi.org/10.28948/ngumuh.795977

Cited By: 9

Öz

Land use are changing due to negative factors occurring in the ecosystem such as continuously developing cities, population growth, and climatic conditions. Data produced by remote sensing satellites play an essential role in ground-based research. Land cover maps are prepared using this data. Land cover maps help us better understand environmental processes such as water and biogeochemical cycles, energy changes, or biodiversity changes. This study was carried out to test the producibility of land use maps on the Google Earth Engine cloud platform. All images acquired between 01/01/2019 and 01/01/2020 from Landsat 8, Sentinel 1, and Sentinel 2 were used in this study. Then 5 different indices NDVI, NDWI, NDBI, Ui, and EVI were calculated, and 19 different combinations of data were considered. Then, for each of these combinations, classification was performed by the LibSVM method in 5 classes: Urban Roads, Water, Forest-Grove, Non-agricultural Lands, and Agricultural Lands. Overall Accuracy and Kappa Coefficient were calculated for each classification, and results were compared. The best classification with Overall Accuracy 96.62 and Kappa Coefficient 95.76 belongs to the data combination of Landsat 8, Sentinel-1(VV), Sentinel-2, NDVI, NDBI, UI and NDWI from Sentinel-2 and NDVI from Landsat 8.

Anahtar Kelimeler

Land use maps, Eskişehir, Google Earth Engine, Supervised classification, Remote sensing

Google Earth Engine ile arazi kullanımı haritalarının üretimi

Öz

Sürekli gelişen şehirler, nüfus artışı ve iklimsel koşullar gibi ekosistem de meydana gelen olumsuz etkenler ile arazi kullanımı değişime uğramaktadır. Uzaktan algılama uyduları tarafından üretilen veriler, yeryüzü araştırmalarda önemli bir rol oynamaktadır. Arazi örtüsü/kullanımı haritaları bu veriler kullanılarak hazırlanmaktadır. Arazi örtüsü haritaları, su ve biyokimyasal döngüler, enerji değişimleri veya biyolojik çeşitlilik değişiklikleri gibi çevresel süreçleri daha iyi anlamamıza yardımcı olur. Bu çalışma, Google Earth Engine bulut platformunda arazi kullanım haritalarının üretilebilirliğini test etmek amacıyla gerçekleştirilmiştir. Bu amaçla 01/01/2019 ve 01/01/2020 tarihleri arasında Landsat 8, Sentinel 1 ve Sentinel 2 uyduları tarafından çekilen tüm görüntüler kullanılmıştır. Daha sonra 5 farklı endeks; NDVI (Normalleştirilmiş fark bitki örtüsü endeksi), EVI(Gelişmiş Bitki Örtüsü Endeksi), NDWI (Normalleştirilmiş fark su endeksi), NDBI (Normalleştirilmiş fark oluşturma indeksi) ve UI (Kentsel indeks) hesaplanmış ve 19 farklı veri kombinasyonu dikkate alınmıştır. Daha sonra bu kombinasyonların her biri Destek Vektör Makineleri yöntemi(LibSVM) kullanılarak 5 sınıfa (Şehir alanı-yollar, su, ormanlık-koruluk, tarım dışı araziler ve tarım arazileri) ayrılmıştır. Her sınıflandırma için genel doğruluk ve Kappa Katsayısı hesaplanmış ve sonuçlar karşılaştırılmıştır. En iyi sınıflandırma, Landsat8, Sentinel-2, Sentinel-1 (VV), Landsat 8'den NDVI, Sentinel-2'den NDVI, NDBI, UI ve NDWI veri kombinasyonuna aittir. Bu kombinasyonda toplam doğruluk 96.62 ve kappa katsayısı 95.76 olmuştur.

Anahtar Kelimeler

Arazi kullanım haritaları, Eskişehir, Google Earth Engine, kontrollü sınıflandırma, uzaktan algılama

Kaynakça

• J. Liu, C. Zhang, L. Kou, and Q. Zhou, Effects of climate and land use changes on water resources in the Taoer river. Advances in Meteorology, 2017, Article ID 1031854, 13 pages 2017. https://doi.org/10.1155/ 2017/1031854
• G. Cai, H. Ren, L. Yang, N. Zhang, M. Du, and C. Wu, Detailed urban land use land cover classification at the metropolitan scale using a three-layer classification scheme. Sensors, 19(14), 3120, 2019. https://doi.org/ 10.3390/s19143120
• A. A. Vaighan, N. Talebbeydokhti, and A. M. Bavani, Assessing the impacts of climate and land use change on streamflow, water quality and suspended sediment in the Kor River Basin, Southwest of Iran. Environ Earth Sci, 76(15), 543, 2017. https://doi.org/10.1007 /s12665-017-6880-6
• L. Li, Y. Chen, X. Yu, R. Liu, and C. Huang, Sub-pixel flood inundation mapping from multispectral remotely sensed images based on discrete particle swarm optimization. ISPRS J. Photogramm. Remote Sens., 101, 10–21, 2015. https://doi.org/10.1016/j.isprsjprs. 2014.11.006
• X. Zhang, L. Han, L. Han, and L. Zhu, How well do deep learning-based methods for land cover classification and object detection perform on high resolution remote sensing imagery?. Remote Sens., 12(3), 417, 2020. https://doi.org/10.3390/rs12030417
• C. Zhang, P. A. Harrison, X. Pan, H. Li, I. Sargent, and P. M. Atkinson, Scale Sequence Joint Deep Learning (SS-JDL) for land use and land cover classification. Remote Sens. Environ., 237:111593, 2020. https://doi.org/10.1016/j.rse.2019.111593
• C. Zhang, S. Wei, S. Ji, and M. Lu, Detecting large-scale urban land cover changes from very high resolution remote sensing images using cnn-based classification. ISPRS Int J Geo-Information, 8(4), 189, 2019. https://doi.org/10.3390/ijgi8040189
• K. Hussein, K. Alkaabi, D. Ghebreyesus, M. U. Liaqat, and H. O. Sharif, Land use/land cover change along the Eastern Coast of the UAE and its impact on flooding risk. Geomatics, Nat Hazards Risk, 11(1), 112–30, 2020. https://doi.org/10.1080/19475705.2019.1707718
• E. F. Lambin, H. J. Geist, and E. Lepers, Dynamics of land-use and land-cover change in tropical regions. Annu. Rev. Environ. Resour., 28(1), 205–41, 2003. https://doi.org/10.1146/annurev.energy.28.050302.105459
• Essential Climate Variables, World Meteorological Organization (WMO). https://public.wmo.int/en/ programmes/global-climate-observing-system/essential-climate-variables Accessed: Jan. 05, 2021.
• N. Pettorelli et al., Framing the concept of satellite remote sensing essential biodiversity variables: challenges and future directions. Remote Sens. Ecol. Conserv., 2(3), 122–31, 2016. https://doi.org/10.1002/ rse2.15
• E. F. Lambin and H. J. Geist, Land-Use and Land-Cover Change: Local Processes and Global Impacts. Springer Science & Business Media, 2008.
• L. Carrasco, A. W. O’Neil, R. D. Morton, and C. S. Rowland, Evaluating combinations of temporally aggregated Sentinel-1, Sentinel-2 and Landsat 8 for land cover mapping with Google Earth Engine. Remote Sens., 11(3), 288, 2019. https://doi.org/10.3390 /rs11030288
• J. R. Jensen, Introductory Digital Image Processing: A Remote Sensing Perspective. Prentice-Hall Inc., 1996.
• The Copernicus Open Access Hub, European Space Agency. https://scihub.copernicus.eu/ Accessed: Jan. 05, 2021
• Sentinel-1, European Space Agency. https://sentinel. esa.int/web/sentinel/missions/sentinel-1 Accessed: Jan. 05, 2021.
• Sentinel-2, European Space Agency. https://sentinel .esa.int/web/sentinel/missions/sentinel-2 Accessed: Jan. 05, 2021.
• Landsat 8, U.S. Geological Survey. https://www. usgs.gov/land-resources/nli/landsat/landsat-8 Accessed: Jan. 05, 2021.
• N. Gorelick, M. Hancher, M. Dixon, S. Ilyushchenko, D. Thau, and R. Moore, Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sens. Environ., 202, 18–27, 2017. https://doi.org/10.1016/j.rse.2017.06.031
• X. Wang et al., Tracking annual changes of coastal tidal flats in China during 1986–2016 through analyses of Landsat images with Google Earth Engine. Remote Sens. Environ., 238, 110987, 2020. https://doi.org/ 10.1016/j.rse.2018.11.030
• N. You and J. Dong, Examining earliest identifiable timing of crops using all available Sentinel 1/2 imagery and Google Earth Engine. ISPRS J. Photogramm. Remote Sens., 161, 109–23, 2020. https://doi.org/ 10.1016/j.isprsjprs.2020.01.001
• G. Mateo-García, L. Gómez-Chova, J. Amorós-López, J. Muñoz-Marí, and G. Camps-Valls, Multitemporal cloud masking in the Google Earth Engine. Remote Sens., 10(7), 1079, 2018. https://doi.org/10.3390/ rs10071079
• Q. Weng, Z. Mao, J. Lin, and W. Guo, Land-use classification via extreme learning classifier based on deep convolutional features. IEEE Geosci Remote Sens Lett, 14(5), 704–8, 2017. https://doi.org/10.1109 /LGRS.2017.2672643
• K. Islam, M. Jashimuddin, B. Nath, and T. K. Nath, Land use classification and change detection by using multi-temporal remotely sensed imagery: The case of Chunati wildlife sanctuary, Bangladesh. Egypt J Remote Sens Sp Sci, 21(1), 37–47, 2018. https://doi.org/10.1016/j.ejrs.2016.12.005
• J. R. B. Fisher, E. A. Acosta, P. J. Dennedy‐Frank, T. Kroeger, and T. M. Boucher, Impact of satellite imagery spatial resolution on land use classification accuracy and modeled water quality. Remote Sens Ecol Conserv, 4(2), 137–49, 2018. https://doi.org/ 10.1002/rse2.61
• T. Hu, J. Yang, X. Li, and P. Gong, Mapping urban land use by using landsat images and open social data. Remote Sens., 8(2), 151, 2016. https://doi.org/ 10.3390/rs8020151
• B. Matsushita, W. Yang, J. Chen, Y. Onda, and G. Qiu, Sensitivity of the enhanced vegetation index (EVI) and normalized difference vegetation index (NDVI) to topographic effects: A case study in high-density cypress forest. Sensors, 7(11), 2636–51, 2007. https://doi.org/10.3390/s7112636
• W. Li et al., A comparison of land surface water mapping using the normalized difference water index from TM, ETM+ and ALI. Remote Sens., 5(11), 5530–49, 2013. https://doi.org/10.3390/rs5115530
• T. L. Dammalage and N. T. Jayasinghe, Land-use change and its impact on urban flooding: A case study on Colombo district flood on May 2016. Eng. Technol. Appl. Sci. Res., 9(2), 3887–91, 2019. https://doi.org/ 10.48084/etasr.2578
• H. Li et al., Mapping urban bare land automatically from Landsat imagery with a simple index. Remote Sens., 9(3), 249, 2017. https://doi.org/10.3390/ rs9030249
• S. Ergen, A. Çelik, N. Çalişkan ve V. Yıldırım, Eskişehir istatistikleri. Eskişehir Büyükşehir Belediyesi Yayını, Eskişehir, 2018. http://www. eskisehir.bel.tr/dosyalar/istatisliklerle_eskisehir/2018.pdf
• J. Koskinen et al., Participatory mapping of forest plantations with Open Foris and Google Earth Engine. ISPRS J. Photogramm. Remote Sens., 148, 63–74, 2019. https://doi.org/10.1016/j.isprsjprs.2018.12.011
• Y. Wang, J. Ma, X. Xiao, X. Wang, S. Dai, and B. Zhao, Long-term dynamic of Poyang Lake surface water: A mapping work based on the Google Earth Engine cloud platform. Remote Sens., 11(3), 313, 2019. https://doi.org/10.3390/rs11030313
• M. Venkatappa, N. Sasaki, R. P. Shrestha, N. K. Tripathi, and H.-O. Ma, Determination of vegetation thresholds for assessing land use and land use changes in Cambodia using the Google Earth Engine cloud-computing platform. Remote Sens., 11(13), 1514, 2019. https://doi.org/10.3390/rs11131514
• P. R. Mirelva and R. Nagasawa, Application of Sentinel-1 data for classifying croplands using Google Earth Engine. Int. J. Geoinformatics, 15(3), 2019.
• Earth Engine Data Catalog. Google. https://developers. google.com/earth-engine/datasets Accessed: January 2021.
• D. Poursanidis, N. Chrysoulakis, and Z. Mitraka, Landsat 8 vs. Landsat 5: A comparison based on urban and peri-urban land cover mapping. Int. J. Appl. Earth Obs. Geoinf., 35, 259–69, 2015. https://doi.org/ 10.1016/j.jag.2014.09.010
• G. M. Foody and A. Mathur, Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification. Remote Sens. Environ., 93(1–2), 107–17, 2004. https://doi.org/10.1016/j.rse.2004.06.017
• M. Pal and P. M. Mather, Support vector machines for classification in remote sensing. Int. J. Remote Sens., 26(5), 1007–11, 2005. https://doi.org/10.1080/ 01431160512331314083
• W. Li, R. Dong, H. Fu, J. Wang, L. Yu, and P. Gong, Integrating Google Earth imagery with Landsat data to improve 30-m resolution land cover mapping. Remote Sens. Environ., 237, 111563, 2020. https://doi.org/ 10.1016/j.rse.2019.111563
• P. Mantero, G. Moser, and S. B. Serpico, Partially supervised classification of remote sensing images through SVM-based probability density estimation. IEEE Trans. Geosci. Remote Sens., 43(3), 559–70, 2005. https://doi.org/10.1109/TGRS.2004.842022
• G. Mountrakis, J. Im, and C. Ogole, Support vector machines in remote sensing: A review. ISPRS J. Photogramm. Remote Sens., 66(3), 247–59, 2011. https://doi.org/10.1016/j.isprsjprs.2010.11.001
• S. Park, J. Im, S. Park, C. Yoo, H. Han, and J. Rhee, Classification and mapping of paddy rice by combining Landsat and SAR time series data. Remote Sens., 10(3), 447, 2018. https://doi.org/10.3390/rs10030447
• C.-C. Chang, LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2, 3, article:27: 1--27, 2011. https://doi.org/10.1145/1961189.1961199