Google Earth Engine kullanılarak makine öğrenmesi tabanlı iyileştirilmiş arazi örtüsü sınıflandırması: Atakum, Samsun örneği

Yıl 2024, , 375 - 390, 02.12.2024

Zelalem Ayalke , Aziz Şişman

https://doi.org/10.29128/geomatik.1472160

Öz

Uzaktan algılama görüntüleri kullanılarak üretilen arazi örtüsü (AÖ) haritaları çevre yönetimi, kentsel planlama, ekolojik araştırmalar vb. çalışmalarda önemli bir temel bileşendir. Bu çalışmada, Google Earth Engine (GEE) ortamında makine öğrenmesi yöntemleri kullanarak Atakum ilçesi sınıflandırılmış arazi örtüsü haritası üretilmesi amaçlanmıştır. Çalışmada, Rastgele Orman (RO) ve Gradyan Ağaç Hızlandırma (GTB) yöntemleri kullanılmıştır. Veri seti olarak Landsat 8 uydu görüntüleri ve ALOS DEM kullanılmıştır. Sınıflandırmayı geliştirmek için; Normalleştirilmiş Fark Bitki Örtüsü İndeksi (NDVI), Normalleştirilmiş Fark Yapılaşma İndeksi (NDBI), Normalleştirilmiş Fark Su İndeksi (NDWI), Çıplak Toprak İndeksi (BSI), Toprağa Göre Ayarlanmış Bitki Örtüsü İndeksi (SAVI) ve Geliştirilmiş Bitki Örtüsü İndeksi (EVI) kullanılmıştır. Çalışma alanında arazi örtüsü; kentsel alanlar, bitki örtüsü, tarım arazisi, çıplak arazi ve su kütleleri olarak sınıflandırılmıştır. Kullanılan modelin performansını optimize etmek için tüm girdi değişkenleri normalize edilmiştir. Modelin performansı, kullanıcı doğruluğu, üretici doğruluğu, genel doğruluk ve kappa katsayısı doğruluk değerlendirme teknikleri ile değerlendirilmiştir. Bu çalışmada, hazırlanan arazi örtüsü için RO ve GTB'nin hesaplanan kappa katsayıları sırasıyla %95,6 ve %96,0, ortalama genel doğruluk ise %96,8 ve %97,1'dır. Çalışmada kullanılan iki makine öğrenmesi yönteminden, GTB'nin RO'dan daha iyi performans gösterdiği gözlemlenmiştir.

Anahtar Kelimeler

Arazi örtüsü sınıflandırması, Makine öğrenmesi, Landsat görüntüleri, Google Earth Engine

Kaynakça

• Adali, T. (2009). Machine Learning for Signal Processing XIX : Proceedings of the 2009 IEEE Signal Processing Society Workshop : MLSP 2009 : Nineteenth in a Series of Workshops. IEEE.
• Alexander, C. (2020). Normalised difference spectral indices and urban land cover as indicators of land surface temperature (LST). International Journal of Applied Earth Observation and Geoinformation 86. Elsevier B.V.
• Arpitha, M., Ahmed, SA. & Harishnaika, N. (2023). Land use and land cover classification using machine learning algorithms in google earth engine. Earth Science Informatics. Springer Science and Business Media Deutschland GmbH.
• Avcı, C. Budak, M. Yagmur, N., & Balcık, F. B. (2023). Comparison between random forest and support vector machine algorithms for LULC classification. International Journal of Engineering and Geosciences, 8(1), 01-10
• Basheer, S., Wang, X., Farooque, AA., Nawaz, RA., Liu, K., Adekanmbi, T., & Liu, S. (2022). Comparison of Land Use Land Cover Classifiers Using Different Satellite Imagery and Machine Learning Techniques. Remote Sensing 14(19): 1–18.
• Belgiu, M., & Drăgu, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing. Elsevier B.V.
• Billah, M., Islam, AKMS., Mamoon, W.B., Rahman, M.R. (2023). Random forest classifications for landuse mapping to assess rapid flood damage using Sentinel-1 and Sentinel-2 data. Remote Sensing Applications: Society and Environment 30. Elsevier B.V.
• Birhanu, L., Hailu, BT., Bekele, T., & Demissew, S. (2019). Land use/land cover change along elevation and slope gradient in highlands of Ethiopia. Remote Sensing Applications: Society and Environment 16. Elsevier B.V.
• Breiman, L. (2001). Random forests. Statistics Department University of California Berkeley. Epub ahead of print 2001.
• Breiman, L., Friedman, JH., Olshen, RA., & Stone, C. J. (1984). Classifications and Regression Trees. Chapman & Hall/CRC.
• Butler, K. (2013). Band Combinations for Landsat 8. Available at: https://www.esri.com/arcgis-blog/products/product/imagery/band-combinations-for-landsat-8/ (accessed 4 December 2023).
• Calvo-Zaragoza, J., Valero-Mas, JJ., & Rico-Juan, JR. (2015). Improving kNN multi-label classification in Prototype Selection scenarios using class proposals. Pattern Recognition 48(5). Elsevier Ltd: 1608–1622.
• Cao, W., Zhou Y., Li, R., & Li, X. (2020). Mapping changes in coastlines and tidal flats in developing islands using the full time series of Landsat images. Remote Sensing of Environment 239. Elsevier Inc.
• Chen ,W,. Wang, H., Zhao, H., & Qin, K. (2020). Google Earth Engine–assisted black carbon radiative forcing calculation over a heavy industrial city in China. Air Quality, Atmosphere and Health 13(3). Springer: 329–338.
• Cohen warren, B. & Goward, SN. (2004). Landsat’s Role in Ecological Applications of Remote Sensing WARREN. BioScience 54.
• Cortes, C., Vapnik, V., & Saitta, L. (1995). Support-Vector Networks Editor. Machine Leaming. Kluwer Academic Publishers.
• Dabija, A., Kluczek, M., Zagajewski, B,, Raczko, E., Kycko, M., Al-Sulttani, A. H., Tardà, A., Pineda, L., & Corbera, J. (2021). Comparison of support vector machines and random forests for corine land cover mapping. Remote Sensing 13(4). MDPI AG: 1–35.
• DeFries, RS., Foley, JA., & Asner, GP. (2004). Land-use choices: Balancing human needs and ecosystem function. Frontiers in Ecology and the Environment. Ecological Society of America.
• Demuzere, M., Bechtel, B., & Mills, G. (2019). Global transferability of local climate zone models. Urban Climate 27. Elsevier B.V.: 46–63.
• Desai, GT., & Gaikwad, AN. (2022). Automatic land cover classification with SAR imagery and Machine learning using Google Earth Engine. International Journal of Electrical and Computer Engineering Systems 13(10): 909–916.
• Disperati, L., & Virdis, SGP. (2015). Assessment of land-use and land-cover changes from 1965 to 2014 in Tam Giang-Cau Hai Lagoon, central Vietnam. Applied Geography 58. Elsevier Ltd: 48–64.
• Efe, E., & Algancı, U. (2023). Çok zamanlı Sentinel 2 uydu görüntüleri ve makine öğrenmesi tabanlı algoritmalar ile arazi örtüsü değişiminin belirlenmesi. Geomatik, 8(1), 27-34
• Elith, J., Leathwick, JR., & Hastie, T. (2008). A working guide to boosted regression trees. Journal of Animal Ecology.
• Elmes, A., Alemohammad, H., Avery, R., Caylor, K., Eastman, J. R., Fishgold, L.,… & Estes, L. (2020). Accounting for training data error in machine learning applied to earth observations. Remote Sensing. MDPI AG.
• Embury, O., Merchant. CJ., & Filipiak, MJ. (2012). A reprocessing for climate of sea surface temperature from the along-track scanning radiometers: Basis in radiative transfer. Remote Sensing of Environment 116: 32–46.
• Foody, GM. (2001). Status of land cover classification accuracy assessment. Remote Sensing of Environment. Epub ahead of print 2001.
• Foody, GM., Pal, M., Rocchini, D., Garzon-Lopez, C.X., & Bastin, L. (2016). The sensitivity of mapping methods to reference data quality: Training supervised image classifications with imperfect reference data. ISPRS International Journal of Geo-Information 5(11). MDPI AG.
• Friedman, JH. (2001). 999 Reıtz Lecture Greedy Functıon Approxımatıon: A Gradıent Boostıng Machıne 1. The Annals of Statistics.
• Friedman, JH. (2002). Stochastic gradient boosting. Computational Statistics & Data Analysis. Available at: www.elsevier.com/locate/csda.
• Gandhi, U. (2021). End-to-End Google Earth Engine (Full Course Material). Available at: https://courses.spatialthoughts.com/end-to-end-gee.html#accuracy-assessment (accessed 17 December 2023).
• Gao, B.-C. (1996). NDWI- A Normalized Difference Water Index for Remote Sensing of Vegetation Liquid Water From Space. REMOTE SENS. ENVIRON, 7212, 257–266.
• Ge, Y., Hu, S., Ren, Z., Jia, Y., Wang, J., Liu, M., …& Chen, Y. (2019). Mapping annual land use changes in China’s poverty-stricken areas from 2013 to 2018. Remote Sensing of Environment 232. Elsevier Inc.
• Gebhardt, S., Wehrmann, T., Ruiz, MAM., Maeda, P., Bishop, J., Schramm, M., … & Schmidt, M. (2014). MAD-MEX: Automatic wall-to-wall land cover monitoring for the mexican REDD-MRV program using all landsat data. Remote Sensing 6(5). MDPI AG: 3923–3943.
• Ghazaryan, G., Dubovyk, O., Löw, F., Lavreniuk, M., Kolotii, A., Schellberg, J., & Kussul, N. (2018). A rule-based approach for crop identification using multi-temporal and multi-sensor phenological metrics. European Journal of Remote Sensing 51(1). Taylor and Francis Ltd.: 511–524.
• Gislason, PO., Benediktsson. JA., & Sveinsson, JR. (2006). Random forests for land cover classification. In: Pattern Recognition Letters, March 2006, pp. 294–300.
• Gu, Y., Liu, T., Gao, G., Ren, G., Ma, Y., Chanussot, J., & Jia, X. (2021). Multimodal hyperspectral remote sensing: an overview and perspective. Science China Information Sciences. Science in China Press.
• Hansen, MC., & Loveland, TR. (2012). A review of large area monitoring of land cover change using Landsat data. Remote Sensing of Environment.
• Huang, C., Davis, LS., & Townshend, JRG. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing 23(4): 725–749.
• Huang, C., Yang, J., & Jiang, P. (2018). Assessing impacts of urban form on landscape structure of urban green spaces in China using Landsat images based on Google Earth Engine. Remote Sensing 10(10). MDPI AG.
• Huete, A. R. (1988). A soil-adjusted vegetation index (SAVI). Remote Sensing of Environment, 25(3), 295–309.
• Huete, A., Didan, K., Miura, T., Rodriguez, E. P., Gao, X., & Ferreira, L. G. (2002). Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Enviroment, 83, 195–213.
• Huntington, JL., Hegewisch, KC., Daudert B., Morton, CG.,Abatzoglou, JT., McEvoy, DJ., & Erickson, T. (2017). Climate engine: Cloud computing and visualization of climate and remote sensing data for advanced natural resource monitoring and process understanding. Bulletin of the American Meteorological Society 98(11) 2397–2409.
• Karip, A.G.B., & Göksel, Ç. (2017). İğneada Koruma Alanının Arazi Örtüsü/Arazi Kullanımının Zamana Bağlı Değişiminin Markov Zincirleri İle Modellenmesi. Geomatik, 2(2); 94-105.
• Kanevski M (2009). Machine Learning for Spatial Environmental Data.
• Khan, R., Gilani, H., Iqbal, N., & Shahid, I. (2020). Satellite-based (2000–2015) drought hazard assessment with indices, mapping, and monitoring of Potohar plateau, Punjab, Pakistan. Environmental Earth Sciences 79(1). Springer.
• Kussul, N., Lemoine, G., Gallego. FJ., Skakun, SV., Lavreniuk, M., & Shelestov, AY. (2016). Parcel-Based Crop Classification in Ukraine Using Landsat-8 Data and Sentinel-1A Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 9(6) 2500–2508.
• Lam, NS-N. (2008). Advances in Land Remote Sensing System, Modeling, Inversion and Application (S Lianged. ). Springer Scnce+Business Media B.V.
• Lary, DJ., Alavi, AH., & Gandomi, AH. (2016). Machine learning in geosciences and remote sensing. Geoscience Frontiieers 7(1) 3–10.
• Li, Y., Liu, C., Zhao, W., & Huang, Y. (2020). Multi-spectral remote sensing images feature coverage classification based on improved convolutional neural network. Mathematical Biosciences and Engineering 17(5) 4443–4456.
• Liang, L., Runkle, BRK., Sapkota, BB., & Reba, M.. (2019). Automated mapping of rice fields using multi-year training sample normalization. International Journal of Remote Sensing 40(18) 7252–7271.
• Liu, D., Chen, N., Zhang, X., Wang, C., & Du, W. (2020). Annual large-scale urban land mapping based on Landsat time series in Google Earth Engine and OpenStreetMap data: A case study in the middle Yangtze River basin. ISPRS Journal of Photogrammetry and Remote Sensing 159 337–351.
• Loveland, TR. (2016). History of land-cover mapping. USGS Publications Warehouse. CRC Press: 13–22.
• Lu, D., & Weng, Q. (2007). A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing. Taylor and Francis Ltd.
• Mahdianpari, M., Salehi, B., Mohammadimanesh, F., Homayouni, S., & Gill, E. (2019). The first wetland inventory map of newfoundland at a spatial resolution of 10 m using sentinel-1 and sentinel-2 data on the Google Earth Engine cloud computing platform. Remote Sensing 11(1).
• Mangkhaseum, S., & Hanazawa, A. (2021). Comparison of Machine Learning Classifiers for Land Cover Changes using Google Earth Engine. Proceedings of the 2021 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2021. IEEE: 1–7.
• Mardani, M., Mardani, H., De Simone, L., Varas, S., Kita, N., & Saito, T. (2019). Integration of machine learning and open access geospatial data for land cover mapping. Remote Sensing 11(16).
• Mas, JF., & Flores JJ (2008). The application of artificial neural networks to the analysis of remotely sensed data. International Journal of Remote Sensing. Taylor and Francis Ltd.
• Mateo-García, G., Gómez-Chova, L., Amorós-López, J., Muñoz-Marí, J., & Camps-Valls, G. (2018). Multitemporal cloud masking in the Google Earth Engine. Remote Sensing 10(7).
• Maxwell, AE., Warner, TA., & Fang, F. (2018). Implementation of machine-learning classification in remote sensing: An applied review. International Journal of Remote Sensing. Taylor and Francis Ltd.
• Mhanna, S., Halloran, LJS., Zwahlen, F., Asaad, AH., &Brunner, P. (2023). Using machine learning and remote sensing to track land use/land cover changes due to armed conflict. Science of the Total Environment 898. Elsevier B.V.
• Middel, A., Lukasczyk, J., Maciejewski, R., Demuzere, M., & Roth, M. (2018). Sky View Factor footprints for urban climate modeling. Urban Climate 25 120–134.
• Midekisa, A., Holl, F., Savory, DJ., Andrade-Pacheco, R., Gething, PW., Bennett, A., & Sturrock, H.J.W. (2017). Mapping land cover change over continental Africa using Landsat and Google Earth Engine cloud computing. PLoS ONE 12(9).
• Mountrakis, G., Im, J., & Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing.
• Murray, NJ., Keith, DA., Simpson, D., Wilshire, JH., & Lucas, RM. (2018). Remap: An online remote sensing application for land cover classification and monitoring. Methods in Ecology and Evolution 9(9) 2019–2027.
• Nguyen, UNT., Pham, LTH., & Dang, TD. (2019). An automatic water detection approach using Landsat 8 OLI and Google Earth Engine cloud computing to map lakes and reservoirs in New Zealand. Environmental Monitoring and Assessment 191(4).
• Noi Phan, T., Kuch, V., & Lehnert, LW. (2020). Land cover classification using google earth engine and random forest classifier-the role of image composition. Remote Sensing 12(15).
• Oo, TK., Arunrat, N., Sereenonchai, S., Ussawarujikulchai, A., Chareonwong, U., & Nutmagul, W. (2022). Comparing Four Machine Learning Algorithms for Land Cover Classification in Gold Mining: A Case Study of Kyaukpahto Gold Mine, Northern Myanmar. Sustainability 14(17).
• Pal, M., & Mather, PM. (2003). An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment 86(4) 554–565.
• Poortinga, A., Tenneson, K., Shapiro, A., Nquyen, Q., Aung, KS., Chishtie, F., & Saah, D. (2019). Mapping plantations in Myanmar by fusing Landsat-8, Sentinel-2 and Sentinel-1 data along with systematic error quantification. Remote Sensing 11(7).
• Quinn, JW. (2001). Band Combinations. Available at: https://web.pdx.edu/~nauna/resources/10_BandCombinations.htm (accessed 4 December 2023).
• Rikimaru, A., Roy, P., & Miyatake, S. (2002). Tropical Forest cover density mapping. Tropical ecology, 43(1), 39-47.
• Rimal, B., Keshtkar, H., Sharma, R., Stork, N., Rijal, S., & Kunwar, R. (2019). Simulating urban expansion in a rapidly changing landscape in eastern Tarai, Nepal. Environmental Monitoring and Assessment 191(4).
• Rogan, J., & Chen, DM. (2004). Remote sensing technology for mapping and monitoring land-cover and land-use change. Progress in Planning.
• Rouse, R. W. H., Haas, J. A. W., & Deering, D. W. (1974). Monitoring Vegetation Systems in the Great Plains with ERTS. Third ERTS-1 Symposium NASA, NASA SP-351, 309–317
• Rwanga, SS., & Ndambuki, JM. (2017). Accuracy Assessment of Land Use/Land Cover Classification Using Remote Sensing and GIS. International Journal of Geosciences 08(04) 611–622.
• Sellami, EM., & Rhinane, H. (2023). A New Approach for Mapping Land Use / Land Cover Using Google Earth Engine: a Comparison of Composition Images. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - 48(4) 343–349.
• Shetty, S., Gupta, PK., Belgiu, M., & Srivastav, S. K. (2021). Assessing the effect of training sampling design on the performance of machine learning classifiers for land cover mapping using multi-temporal remote sensing data and google earth engine. Remote Sensing 13(8).
• Sinha, S., Sharma, LK., & Nathawat, MS. (2015). Improved Land-use/Land-cover classification of semi-arid deciduous forest landscape using thermal remote sensing. Egyptian Journal of Remote Sensing and Space Science 18(2) 217–233.
• Siraj, M.,Mahmood, S.,& Habib, W. (2023). Geo-spatial assessmentof land cover change in District Dera Ismail Khan, Khyber Pakhtunkhwa, Pakistan. Advanced Remote Sensing, 3(1),1-9.
• Sulova, A., & Arsanjani, JJ. (2021). Exploratory analysis of driving force of wildfires in australia: An application of machine learning within google earth engine. Remote Sensing 13(1) 1–23.
• Tırmanoğlu, B., İsmailoğlu, İ., Kokal, A. T., & Musaoğlu, N. (2023). Yeni nesil multispektral ve hiperspektral uydu görüntülerinin arazi örtüsü / arazi kullanımı sınıflandırma performanslarının karşılaştırılması: Sentinel-2 ve PRISMA Uydusu. Geomatik, 8(1), 79-90
• Tso, B., & Mather, Paul. (2009). Classification Methods for Remotely Sensed Data. Taylor & Francis Group, LLC.
• TÜİK, (2024). Adrese dayalı nüfus kayıt sistemi, https://biruni.tuik.gov.tr/medas/?locale=tr (Erişim Tarihi; 10.02.2024)
• Tumer, K., & Ghosht, J. (1996). Analysis of Decision Boundaries in Linearly Combined Neural Classifiers. Pattern Recognition.
• Uddin, K., Matin, MA., & Meyer, FJ. (2019). Operational flood mapping using multi-temporal Sentinel-1 SAR images: A case study from Bangladesh. Remote Sensing 11(13).
• Wulder, MA., Masek, JG., Cohen, WB., Loveland, TR., & Woodcock, CE. (2012). Opening the archive: How free data has enabled the science and monitoring promise of Landsat. Remote Sensing of Environment 122: 2–10.
• Xie, Z., Phinn, SR., Game, ET., Pannell, DJ., Hobbs, RJ., Briggs, PR., & McDonald-Madden, E. (2019). Using Landsat observations (1988–2017) and Google Earth Engine to detect vegetation cover changes in rangelands - A first step towards identifying degraded lands for conservation. Remote Sensing of Environment 232.
• Yuh, YG., Tracz, W., Matthews, HD., & Turner, SE. (2023). Application of machine learning approaches for land cover monitoring in northern Cameroon. Ecological Informatics 74. Elsevier B.V.
• Zha, Y., Gao, J., & Ni, S. (2003). Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. International Journal of Remote Sensing, 24(3), 583–594.
• Zhang, C., & Li, X. (2022). Land Use and Land Cover Mapping in the Era of Big Data. Land.
• Zhang, M., Gong, P., Qi, S., Liu, C., & Xiong, T. (2019). Mapping bamboo with regional phenological characteristics derived from dense Landsat time series using Google Earth Engine. International Journal of Remote Sensing 40(24) 9541–9555.
• Zhang, Z., Wei, M., Pu, D., He, G., Wang, G., & Long, T. (2021). Assessment of annual composite images obtained by google earth engine for urban areas mapping using random forest. Remote Sensing 13(4) 1–21.
• Zhu, Z., & Woodcock, CE. (2014). Continuous change detection and classification of land cover using all available Landsat data. Remote Sensing of Environment 144: 152–171.