Güzelhisar Havzasında Endüstriyel Gelişmenin Arazi Kullanımı ve Arazi Örtüsü Özellikleri Üzerindeki Etkisinin Bulut Tabanlı Makine Öğrenme Teknikleri ile Değerlendirilmesi

Öz

Endüstriyel faaliyetin varlığı, kentsel büyümenin ana itici gücüdür ve istihdam fırsatları yaratarak bölgenin sosyoekonomik durumunu etkilemektedir. Arazi Örtüsü ve Arazi Kullanımı (AÖAK), ekolojik koşullar, jeolojik ve jeomorfolojik özellikler, bitki örtüsü özellikleri gibi biyotik ve abiyotik faktörler ile sosyoekonomik yapı tarafından etkilenmektedir. AÖAK değişimlerini, bunların yoğunluğunu, değişim yönünü, etkenlerini ve izlemek, sürdürülebilir kalkınma planlaması için önemli bilgiler sağlamaktadır. Uzaktan Algılama (UA), bölgesel ve küresel AÖAK bilgisi elde etmek için en ekonomik ve uygulanabilir yaklaşım olarak kabul edilmektedir.. Çalışmanın amacı Güzelhisar Havzasında sanayi faaliyetlerinin AÖAK durumu üzerindeki etkisini araştırmaktır. Bu bağlamda uydu görüntüleri kullanarak makine öğrenme algoritması ile 1995-2022 yıllarına ait AÖAK durumu tespit edilmiştir. Sınıflandırmada AÖAK sınıfları ‘Su Yüzeyi’, ‘Orman Alanı’, ‘Tarım Alanı’, ‘Açık Yüzey’ ve ‘Beşeri Yüzey’ olarak belirlenmiştir. Araştırmada 30 m çözünürlüğü ile LANDSAT uydu görüntüleri kullanılmıştır. Normalize Edilmiş Fark Bitki Örtüsü İndeksi (NDVI), Toprakla Düzeltilmiş Bitki Örtüsü İndeksi (SAVI), Normalize Edilmiş Fark Su İndeksi (NDWI), Normalize Edilmiş Açık Yüzey İndeksi (NBLI), Çıplak Toprak İndeksi (BSI), Normalize Edilmiş Fark Yerleşim Alanı İndeksi (NDBI) indeksleri 1995 ve 2022 yılları için hesaplanarak doğruluğu artırmak amacıyla kullanılmıştır. Uydu görüntülerinin sınıflandırmasında Rastgele Orman (RF) makine öğrenme algoritması tercih edilmiştir. Görüntülerin elde edilmesinde ve sınıflandırma işlemlerinde Google Earth Engine (GEE) platformu kullanılmıştır. Sınıflandırma doğruluğu hata matrisi, kullanıcı doğruluğu, üretici doğruluğu, genel doğruluk ve Kappa Katsayısı ile hesaplanmıştır. Sonuç olarak araştırma sahasında beşeri yüzeylerde önemli miktarda artış meydana gelirken, tarım alanlarında ve açık yüzeylerde azalma olduğu tespit edilmiştir. Beşerî yüzeylerdeki artış miktarı dikkate alındığında bölgede sanayi faaliyetlerine bağlı istihdam potansiyelinin kentleşme üzerindeki etkisini göstermektedir. Araştırma kapsamında GEE platformunun yetenekleri, makine öğrenmesine dayalı sınıflandırma algoritması, sınıflandırma süreçleri ve elde edilen bulguların değerlendirilmesine kadar olan tüm süreç performansları değerlendirilmiştir. Bu açıdan çalışmanın tüm sonuçları, gelecekte yapılacak çalışmaların geliştirilmesi, ayrıca UA ve Coğrafi Bilgi Sistemleri araştırmalarında açık veri kaynaklarının ve bulut tabanlı platformların yaygınlaşması açısından önem arz etmektedir.

Anahtar Kelimeler

• Güzehisar Havzası
• Uzaktan Algılama
• Google Earth Engine
• Arazi Kullanımı ve Arazi Örtüsü
• Makine Öğrenmesi

Assessing Industrial Development Influence on Land Use and Land Cover Change Detection in Güzelhisar Basin with Cloud-Based Machine Learning Techniques

Öz

Industrial activity is the main driving force behind urban growth, influencing the socioeconomic status of an area by creating employment opportunities. Land use and land cover (LULC) are influenced by various factors such as ecological conditions, geological and geomorphological features, vegetation characteristics, and socioeconomic structure. Monitoring LULC changes, their intensity, direction, and underlying causes provides valuable knowledge for sustainable development planning. Remote sensing (RS) is widely considered the most cost-effective and practical approach for obtaining regional and global LULC information. The aim of this study is to investigate the impact of industrial activity on LULC in the Güzelhisar Basin. Using satellite imagery and machine learning algorithms, the LULC status from 1995 to 2022 was determined. The LULC classes were classified as 'Water Surface', 'Forest Area', 'Agricultural Area', 'Bare Surface', and 'Built-Up Area'. The research utilized LANDSAT satellite images with a 30-meter resolution. To enhance accuracy, various indices including the NDVI, SAVI, NDWI, NBLI, BSI, and NDBI were calculated for the years 1995 and 2022. The Random Forest (RF) machine learning algorithm was employed for satellite image classification. The Google Earth Engine (GEE) platform was utilized for image acquisition and classification. Classification accuracy was evaluated using the Error Matrix, User's Accuracy, Producer's Accuracy, Overall Accuracy, and Kappa Coefficient. The findings indicate a significant increase in built-up areas and a decrease in agricultural and bare areas within the survey area. This demonstrates the impact of industrial operations on urbanization, considering the amount of increase in anthropic surfaces. The study thoroughly evaluates the capabilities of the GEE platform, machine learning-based classification algorithm, and the entire process from image classification to the assessment of obtained findings. These findings are crucial for future studies and the broader implementation of open data sources and cloud-based platforms in RS and Geographic Information Systems research.

Anahtar Kelimeler

• Google Earth Engine
• Remote Sensing
• Random Forest
• Land Use and Land Cover Change
• Güzelhisar Basin

Kaynakça

1. Abdollahizad, S., Balafar, M. A., Feizizadeh, B., Babazadeh Sangar, A., & Samadzamini, K. (2021). Using hybrid artificial ıntelligence approach based on a Neuro-Fuzzy System and evolutionary algorithms for modeling landslide susceptibility in East Azerbaijan province, Iran. Earth Science Informatics. doi: https://doi.org/10.1007/s12145-021-00644-z
2. Aliağa Organize Sanayi Bölgesi Yönetim Kurulu (2022), Kurumsal bilgi, Ekim 30, 2022 tarihinde ALOSBİ: https://www.alosbi.org.tr/kurumsal adresinden alınmıştır.
3. Almutairi, B., El, A., Belaid, M. A., & Musa, N. (2013). Comparative study of SAVI and NDVI vegetation ındices in sulaibiya area (Kuwait) using worldview satellite ımagery. Int. J. Geosci. Geomatics, 1, 50-53.
4. Amani, M., Ghorbanian, A., Ahmadi, S. A., Kakooei, M., Moghimi, A. and Mirmazloumi, S. M. (2020). Google Earth Engine cloud computing platform for remote sensing big data applications: A comprehensive review,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 13, pp. 5326–5350, doi: https://doi.org/10.1109/JSTARS.2020.3021052
5. Arabameri, A., Roy, J., Saha, S., Blaschke, T., Ghorbanzadeh, O., & Bui, D.T. (2019). Application of probabilistic and machine learning models for groundwater potentiality mapping in damghan sedimentary plain, Iran. Remote Sensing 11 (24): 3015. doi: https://doi.org/10.3390/rs11243015
6. Atumane, A., Cabral, P. (2021). Integration of ecosystem services into land use planning in Mozambique. Ecosystems and People 17:1, pages 165-177. doi: https://doi.org/10.1080/26395916.2021.1903081
7. Balchin, P. N., Isaac, D. & Chen, J. (2000). Urban Economics: a global perspective, Palgrave, New York.
8. Bayırhan, İ., & Nas, S. (2018). Güzelhisar Deresi’nin Aliağa Organize Sanayi Bölgesi İçin Suyolu Olarak Tasarımı. Teknik Dergi, 29(1), 8199-8224, doi: https://doi.org/10.18400/tekderg.346896

9. Bağmancı, M. F. (2010). Aliağa İlçe Merkezinin Beşerî Ve Ekonomik Coğrafyası. Kahramanmaraş Sütçü İmam Üniversitesi sosyal Bilimler Enstitüsü coğrafya Ana Bilim Dalı. Basılmamış Yüksek Lisans Tezi.
10. Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 114, Pages 24-31, https://doi.org/10.1016/j.isprsjprs.2016.01.011
11. Belward, A.S. & Skøien, J.O. (2015). Who launched what, when and why; trends in global land cover observation capacity from civilian earth observation satellites ISPRS J. Photogramm. Remote Sens., 103, pp. 115-128, doi: https://doi.org/10.1016/j.isprsjprs.2014.03.009
12. Bozdağ, A., Dokuz, Y., & Gökçek, Ö.B. (2020). Spatial prediction of pm10 concentration using machine learning algorithms in Ankara, Turkey. Environmental Pollution (Barking, Essex: 1987) 263: 114635. doi: https://doi.org/10.1016/j.envpol.2020.114635
13. Breiman L. (2001). Random forests. Machine Learn. 45(1):5–32.
14. Cihlar, J. (2000). Land cover mapping of large areas from satellites: status and research priorities. Int. J. Remote Sens. 21, 1093–1114, doi: https://doi.org/10.1080/014311600210092
15. Colwell, J. E. (1974). Vegetation canopy reflectance. Remote Sensing of Environment, 3, 175−183.
16. Congalton, R.G. and Green, K., (2009). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, 2nd ed. (Boca Raton, FL: CRC Press), doi: https://doi.org/10.1201/9780429052729
17. Cracknell, M. J., & Reading. A.M. (2014). Geological mapping using remote sensing data: a comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial ınformation. Computers & Geosciences 63: 22–33. doi: https://doi.org/10.1016/j.cageo.2013.10.008
18. Danacıoğlu, Ş. (2019). Arazi kullanımı/Arazi örtüsü ve uzaktan algılama. D.D. Yavaşlı ve M.K. Ölgen (Ed.), Coğrafyada Uzaktan Algılama içinde (s. 161-198). İstanbul: Kriter Yayınevi.
19. Diek, S., Fornallaz, F., Schaepman, M.E., de Jong, R. (2017). Barest Pixel Composite for agricultural areas using LANDSAT time series. Remote Sensing, 9, 1245, doi: https://doi.org/10.3390/rs9121245 Eroğlu, İ., & Bozyiğit, R. (2011). Güzelhisar Çayı Havzasında yapısal unsurların jeomorfolojik birimlere etkileri. Selçuk Üniversitesi Ahmet Keleşoğlu Eğitim Fakültesi Dergisi, 32, 169-190.
20. Eroğlu, İ. ve Bozyiğit, R. (2013), Aliağa İlçesinde Arazi Kullanımına Etki Eden Doğal ve Beşerî Faktörler. Marmara Coğrafya Dergisi, 27, 353-400, İstanbul
21. Eroğlu, İ. (2015). Aliağa İlçesindeki (İzmir) Çevre Sorunlarının Coğrafi Açıdan Değerlendirilmesi. Coğrafyacılar Derneği Uluslararası Kongresi, 21-23 Mayıs Başkent Öğretmenevi, Ankara, Türkiye.
22. Gashaw, T., Tulu, T., Argaw, M., Worqlul, A.W. (2018). Modeling the hydrological impacts of land use/land cover changes in the Andassa watershed, blue Nile basin, Ethiopia. Sci. Total Environ., 619–620, pp. 1394-1408, doi: https://doi.org/10.1016/j.scitotenv.2017.11.191
23. Ge, G., Shi, Z., Zhu, Y., Yang, X., Hao, Y., (2020). Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms. Global Ecology and Conservation, 22, e00971, doi: https://doi.org/10.1016/j.gecco.2020.e00971
24. Geenhuizen,V. M. & Nijkamp, P. (1995). 'Urbanization. industrial dynamics, and spatial development: a company life history approach', in Urban agglomeration and economic growth, ed. Giersch, H., Springer, New York, pp. 39-40, doi: 10.1007/978-3-642-79397-4_2.
25. Giri, C.P. (2012). Remote Sensing of Land Use and Land Cover: Principles and Applications; CRC Press, Taylor and Francis Group: Boca Raton, FL, USA.
26. Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R (2017) Google Earth Engine: planetary-scale geospatial analysis for everyone. Remote Sens Environ 202:18–27, doi: https://doi.org/10.1016/j.rse.2017.06.031 Hayter, R. (1997). The dynamics of industrial location: the factory, the firm and the production system, John Wiley & Sons, Sussex.
27. Hejar, S., Jarihani, B., Piralilou, S.T., Chittleborough, D., Avand, M. & Ghorbanzadeh, O. (2019). A Semi-Automated object-based gully networks detection using different machine learning models: A Case study of bowen catchment, Queensland, Australia. Sensors 19 (22): 4893. doi: https://doi.org/10.3390/s19224893
28. Hossein Shafizadeh-Moghadam, Morteza Khazaei, Seyed Kazem Alavipanah & Qihao Weng (2021) Google Earth Engine for large-scale land use and land cover mapping: an object-based classification approach using spectral, textural and topographical factors, GIScience & Remote Sensing, 58:6, 914-928, doi: 10.1080/15481603.2021.1947623
29. Hu Y., Dong Y., Batunacun, Y. (2018). An automatic approach for land-change detection and land updates based on integrated NDVI timing analysis and the CVAPS method with GEE support. ISPRS J Photogramm Remote Sens. 146:347–359, doi: https://doi.org/10.1016/j.isprsjprs.2018.10.008
30. Huete, A. R. (1988). A soil-adjusted vegetation index (SAVI). Remote sensing of environment, 25(3), 295-309, doi: https://doi.org/10.1016/0034-4257(88)90106-X
31. Javed, A., Cheng, Q., Peng, H., Altan, O., Li, Y., Ara, I., Huq, E., Ali, Y., Saleem, N. (2021). Review of spectral ındices for urban remote sensing. Photogramm. Eng. Remote Sens., 87, 513–524, doi: https://doi.org/10.14358/PERS.87.7.513
32. Jia, K., Liang, S., Wei, X., Yao, Y., Su, Y., Jiang, B., & Wang, X. (2014). Land cover classification of LANDSAT data with phenological features extracted from Time Series MODIS NDVI Data. Remote Sensing, 6(11), 11518–11532. https://doi.org/10.3390/rs61111518
33. Jog, S., & Dixit, M., (2016). Supervised classification of satellite images. 2016 Conference on Advances in Signal Processing (CASP), IEEE, 93–98, doi: https://doi.org/10.1109/CASP.2016.7746144
34. Kamal, M., Jamaluddin, I., Parela A., & Farda N.M. (2019). Comparison of Google Earth Engine (GEE)-based Machine Learning Classifiers for Mangrove Mapping. The 40th Asian Conference on Remote Sensing (ACRS 2019) October 14-18, 2019 / Daejeon Convention Center (DCC), Daejeon, Korea
35. Karlson, M., Ostwald, M., Reese, H., Sanou, J., Tankoano, B., Mattsson, E. (2015). Mapping tree canopy cover and aboveground biomass in Sudano-Sahelian woodlands using LANDSAT 8 and random forest. Remote Sensing, 7, p. 10017, doi: https://doi.org/10.3390/rs70810017
36. Khan, N., Sachindra, D. A., Shahid, S., Ahmed, K., Shiru, S. M. & Nawaz, N. (2020). Prediction of droughts over Pakistan using machine learning algorithms. Advances in Water Resources 139: 103562. doi: https://doi.org/10.1016/j.advwatres.2020.103562
37. Kotsiantis S. B. (2007). Supervised machine learning: a review of classification techniques. Informatica,31:249–268.
38. Lambin, E.F. (1999). Monitoring forest degradation in tropical regions by remote sensing: some methodological issues. Global Ecology and Biogeography, 8: 191-198. https://doi.org/10.1046/j.1365-2699.1999.00123.x
39. Lary, D.J., Alavi, A. H., Gandomi, A.H., Walker, A.L. (2016). Machine learning in geosciences and remote sensing, Geoscience Frontiers, 7 (1), 3-10. doi: https://doi.org/10.1016/j.gsf.2015.07.003
40. Li H, Wang C, Zhong C, Su A, Xiong C, Wang J & Liu J. (2017). Mapping urban bare land automatically from LANDSAT ımagery with a simple ındex. Remote Sensing. 9(3):249. doi: https://doi.org/10.3390/rs9030249
41. Li, M, Zang, S, Zhang, B, Li, S, Wu, C. (2014) A review of remote sensing image classification techniques: the role of spatio-contextual information. European Journal of Remote Sensing 47(1):389–411. https://doi.org/10.5721/EuJRS20144723
42. Lillesand, T.M., Kiefer, R.W. , ve Chipman, J.W. (2018). Uzaktan Algılama ve Görüntü Yorumalama (K.Ş. Kavak, Çev.), Palme Yayınevi (Orijinal çalışma basım tarihi 2015).
43. Liu. X., Zhu, X., Zhang, O., Yang, T., Pan, Y., & Sun, P. (2020). A Remote sensing and artificial neural network-based ıntegrated agricultural drought ındex: Index development and applications. Catena 186: 104394. doi: https://doi.org/10.1016/j.catena.2019.104394
44. Loveland, T., Sohl, T., Stehman, S., Gallant, A., Sayler, K., Napton, D. (2002). A strategy for estimating the rates of recent United States land cover changes. Photogramm. Eng. Remote Sens. 68, 1091–1099.
45. Maxwell, A. E., Warner, T. A., & Fang, F. (2018). Implementation of machine-learning classification in remote sensing: An applied review. International Journal of Remote Sensing, 39(9), 2784-2817. Doi: https://doi.org/10.1080/01431161.2018.1433343
46. McFeeters, S. K. (1996). The use of normalized difference water index (NDWI) in the delineation of open water features, International Journal of Remote Sensing, 17: 1425–1432. Doi: https://doi.org/10.1080/01431169608948714
47. MohanRajan, S.N., Loganathan, A. & Manoharan, P. (2020). Survey on Land Use/Land Cover (LU/LC) change analysis in remote sensing and GIS environment: Techniques and Challenges. Environ Sci Pollut Res 27, 29900–29926. https://doi.org/10.1007/s11356-020-09091-7
48. Monserud, R. A., Leemans, R., (1992). Comparing global vegetation maps with the Kappa statistic. Ecological modelling, 62(4), 275–293, doi: https://doi.org/10.1016/0304-3800(92)90003-W Öner, N. (2006). Aliağa-Kemalpaşa (İzmir) Yöresinde Yapılan Kızılçam ve Fıstıkçamı Ağaçlandırmalarının Başarısı. Abant İzzet Baysal Üniversitesi Ormancılık Dergisi2 (1), 68–78
49. Pan, X., Wang, Z., Gao, Y., Dang, X., Han, Y. (2022). Detailed and automated classification of land use/land cover using machine learning algorithms in Google Earth Engine, Geocarto International, 37:18, 5415-5432, doi: https://doi.org/10.1080/10106049.2021.1917005
50. Prakash, N., Manconi, A. & Loew, S. (2020). Mapping Landslides on EO Data: Performance of Deep Learning Models vs. traditional Machine Learning Models. Remote Sensing 12 (3): 346. doi: https://doi.org/10.3390/rs12030346
51. Rai, S., Sharma, E., & Sundriyal, R. (1994). Conservation in the Sikkim Himalaya: Traditional knowledge and land-use of the mamlay Watershed. Environmental Conservation, 21(1), 30-34. doi: https://doi.org/10.1017/S0376892900024048
52. Ravanelli, R., A. Nascetti, R. V. Cirigliano, C. Di Rico, P. Monti, and Crespi, M. (2018). Monitoring Urban Heat Island through Google Earth Engine: Potentialities and Difficulties in Different Cities of the United States. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-3: 1467–1472. doi: https://doi.org/10.5194/isprs-archives-XLII-3-1467-2018
53. Rikimaru, A., Roy, P.S. & Miyatake, S. (2002). Tropical forest cover density mapping. Trop. Ecol., 43, 39–47. Rojan, J., Chen, D. (2004). Remote sensing technology for mapping and monitoring land-cover and land-use change. Prog. Plan., 61, 301–325.
54. Rwanga, S. S., &Ndambuki, J. M. (2017). Accuracy assessment of land use/land cover classification using remote sensing and GIS. International Journal of Geosciences 08 (04): 611–622. doi: https://doi.org/10.4236/ijg.2017.84033
55. Salazar, A., Baldi, G., Hirota, M., Syktus, J., McAlpine, C., (2015). Land use and land cover change impacts on the regional climate of non-Amazonian South America: a review. Glob. Planet. Change 128, 103–119, doi: https://doi.org/10.1016/j.gloplacha.2015.02.009
56. Simmons, I. G. (2008). Global environmental history: 10,000 BC to AD 2000. Edinburgh University Press.
57. Stefanski, J., Mack, B., Waske, B. (2013). Optimization of object-based image analysis with random forests for land cover mapping. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 6, pp. 2492-2504, doi: https://doi.org/10.1109/JSTARS.2013.2253089
58. Taghizadeh-Mehrjardi, R., Toomanian, N., Shamshirband, S., Mosavi, A., Behrens, T., Schmidt, K., and Scholten, T.: Predicting and mapping of soil salinity using machine learning algorithms in central arid regions of Iran, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-18516, https://doi.org/10.5194/egusphere-egu2020-18516 , 2020
59. Tanrıvermiş H, Mülayim ZG (1999). Sanayinin Neden Olduğu Çevre Kirliliğinin Tarıma Verdiği Zararların Değerinin Biçilmesi: Samsun Gübre (TÜGSAS) ve Karadeniz Bakır (KBI) Sanayileri Örneği. Tr. J. of Agriculture and Forestry 23: 337- 345.
60. Turner, B, L., Lambin, E, F., Reenberg, A. (2007). The emergence of land change science for global environmental change and sustainability. Proc Natl Acad Sci USA 104, 20666–20671, doi: https://doi.org/10.1073/pnas.0704119104
61. Viana, C. M., Oliveira, S., Oliveira, S. C. & Rocha, J. (2019). 29—Land use/land cover change detection and urban sprawl analysis, in Spatial Modeling in GIS and R for Earth and Environmental Sciences, H. R. Pourghasemi and C. Gokceoglu, Eds. Amsterdam, The Netherlands: Elsevier, pp. 621–651, doi: https://doi.org/10.1016/B978-0-12-815226-3.00029-6
62. Xie S, Liu L, Zhang X, Yang J, Chen X, Gao Y. (2019). Automatic land-cover mapping using LANDSAT time-series data based on Google Earth Engine. Remote Sens. 11(24):3023, doi: https://doi.org/10.3390/rs11243023
63. Yang C, He X, Yan F, Yu L, Bu K, Yang J, Chang L, Zhang S. (2017). Mapping the ınfluence of land use/land cover changes on the urban heat ısland effect—a case study of Changchun, China. Sustainability 9(2):312. https://doi.org/10.3390/su9020312
64. 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, doi: https://doi.org/10.1080/01431160304987
65. Zhao, H. & Chen, X. (2005). Use of normalized difference bareness index in quickly mapping bare areas from TM/ETM+. In Proceedings of the 2005 IEEE International Geoscience and Remote Sensing Symposium, Seoul, Korea, 29 July 2005; pp. 1666–1668.