Research Article
BibTex RIS Cite

Land Cover and Land Use Classification at National Scale Using Land Parcel Identification System Data (LPIS)

Year 2023, Volume: 4 Issue: 2, 276 - 288, 28.09.2023
https://doi.org/10.48123/rsgis.1268155

Abstract

The Integrated Administration and Control System (IACS) is a system that provides the management and administration of the support of inspections by the European Union. One of the main components of this system, which consists of many different components and systems, is the Land Parcel Identification System (LPIS), which includes reference parcels in different classes based on a geographic database. In 2016, it was digitized within the scope of LPIS, using 30cm resolution orthophoto images, without any gaps across the country. In the study, land cover and land use classification was made at the country scale using physical blocks (13.5 million) and multi-time Sentinel-2 images (370 frames), which are the key components of the LPIS. This study, which included very large raster and vector data, was carried out using LightGBM machine learning algorithm in the open-source EO-Learn library located on the servers of Sinergise company in Amazon Web Service (AWS) and the overall accuracy value of 86.07 % was reached. In addition to determining the land cover and usage classes for 2021 as a result of the classification process, it is aimed to use the physical blocks of the LPIS classes drawn in 2016 and the classification result to be used as a reference base for updating the classes, especially in the areas with change.

References

  • AWS. (2022, Kasım 11). Registry of open data on AWS. Retrieved from https://registry. opendata.aws/sentinel-2/.
  • Apaydın, C., & Abdikan, S. (2021). Fındık bahçelerinin Sentinel-2 verileri kullanılarak piksel tabanlı sınıflandırma yöntemleriyle belirlenmesi. Geomatik, 6(2), 107-114.
  • Candido, C., Blanco, A. C, Medina, J., Gubatanga, E., Santo, A., Ana, R. C., & Reyes, R. B. (2021) . Improving the consistency of multi-temporal land cover mapping of Laguna lake watershed using light gradient boosting machine (LightGBM) approach, change detection analysis, and Markov chain. Remote Sensing Applications: Society and Environment, 23(5), 100565. doi: 10.1016/j.rsase.2021.100565.
  • Eitel, J. H., Vierling, L. A., Litvak, M. A., Long, D. S., Schulthess, U., Ager, A. A., Krofcheck, D. J., & Stoscheck, L. (2011). Broadband, red-edge information from satellites improves early stress detection in a new mexico conifer woodland. Remote Sensing of Environment, 115(12), 3640-3646.
  • ESRI. (2022, Eylül 11). Tasseled cap function. Retrieved from https://pro.arcgis.com/en/pro-app/latest/help/analysis/ raster-functions/tasseled-cap-function.htm.
  • EO-Learn, (2022a, Aralık 17). Introduction EO-Learn. Retrieved from https://eo-learn.readthedocs.io/en/latest/#.
  • EO-Learn, (2022b, Aralık 24). EO-Learn core is the main subpackage which implements the basic building blocks. Retrieved from https://eo-learn.readthedocs.io/en/latest/examples/core/CoreOverview.html#EOPatch.
  • Gergeli, B. (2008). AB’de Entegre İdare ve Kontrol Sistemi Bilgi Teknolojileri (IT) yapısı, ödeme kuruluşu altyapısı ile olan ilişkisi ve etkileri, Türkiye’de uygulanabilirliği (AB Uzmanlık Tezi). Tarım ve Köy işleri Bakanlığı, Dış İlişkiler ve Avrupa Birliği Koordinasyon Dairesi Başkanlığı, Ankara, Türkiye.
  • GITHUB, (2022, Aralık 17). Sentinel Hub’s cloud dedector for Sentinel-2 imagery. Retrieved from https://github.com/ sentinel-hub/sentinel2-cloud-detector.
  • Guolin, K., Men, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye Q., & Liu, T. Y. (2017, December). LightGBM: A highly efficient gradient boosting decision tree. In 31st Conference on Neural Information Processing Systems, 2017. Proceedings. (pp. 1-9). NeurIPS.
  • Harvolk, S., Kornatz, P., Otte, A., & Simmering, D., (2014). Using existing landscape data to assess the ecological potential of miscanthus cultivation in a marginal landscape. GCB Bioenergy, 6(3), 227-241.
  • Jarray, N., Abbes, A. B., Rhif, M., Chouikhi, F., & Farah, I. R. (2021, July). An open source platform to estimate Soil Moisture using Machine Learning Methods based on Eo-learn library. In International Congress of Advanced Technology and Engineering, 2021. Proceedings. (pp. 1-5). IEEE.
  • Kauth, R. J., & Thomas, G. S. (1976, June). The Tasselled Cap - a graphic description of the spectral - temporal development of agricultural crops as seen by LANDSAT. In Symposium on Machine Processing of Remotely Sensed Data, 1976. Proceedings. (pp. 41-59). IEEE.
  • Karlsen, S. R., Stendardi, L., Tømmervik, H., Nilsen, L., Arntzen, I. M., & Cooper, E. J. (2021). Time-Series of Cloud-Free Sentinel-2 NDVI data used in mapping the onset of growth of central Spitsbergen, Svalbard. Remote Sensing, 13(15), 3031. doi: 10.3390/rs13153031.
  • Kohavi, R. (1995, August). A study of cross-validation and bootstrap for accuracy estimation and model selection. In International Joint Conference of Artificial Intelligence, 1995. Proceedings. (pp. 1137-1145). IJCAI.
  • Keser, T. Z. (2007). Entegre idare ve kontrol sistemi, mevcut durum ve AB üye ülkeleri arasından seçilen örnekler üzerinden incelenmesi (AB Uzmanlık Tezi). Tarım ve Köy işleri Bakanlığı, Dış İlişkiler ve Avrupa Birliği Koordinasyon Dairesi Başkanlığı, Ankara, Türkiye.
  • Langat, P. K., Kumar, L., & Koech, R. (2019). Monitoring river channel dynamics using remote sensing and GIS techniques. Geomorphology, 325, 92-102.
  • Lambin, E. F., Geist, H. J., & Rindfuss, R. R. (2006). Local Processes with Global Impacts. In E.F. Lambin & H.J. Geist (Eds.), Land-Use and Land-Cover Change: Local processes and global impacts (pp. 1-8), Heidelberg: Springer Berlin.
  • LPIS Guideline, (2015). LPIS data capture photo interpretation and digitization guidelines. Republic of Turkey Ministry of Agriculture and Forestry, Ankara, Turkey.
  • Li, W., Ding, S., Chen, Y., Wang, H., & Yang, S. (2019). Transfer learning-based default prediction model for consumer credit in China. Journal of Supercomputing, 75(2), 862-884.
  • LightGBM, (2023, Şubat 1). Welcome to LightGBM’s documentation. Retrieved from https://lightgbm.readthedocs.io/ en/latest/index.html#.
  • Liu, L., Ji, M., & Buchroithner, M. F. (2017). Combining partial least squares and the gradient-boosting method for soil property retrieval using visible near-ınfrared shortwave ınfrared spectra. Remote Sensing, 9(12), 1299. doi: 10.3390/rs9121299.
  • Lu, D., & Weng, Q. (2007). A survey of image classification methods and techniques for improving classification Performance. International Journal of Remote Sensing, 28(5), 823-870.
  • Lubej, M., Aleksandrov, M., Batic, M., Kadunc, M., Milcinski, G., Peressutti, D., & Zupanc, A. (2019, May). Spatio-temporal deep learning: an application to land cover classification. In ESA Living Planet Symposium, 2019. Proceedings. (pp. 2-5). ESA.
  • Lüker-Jans, N., Simmering, D., & Otte, A. (2016). Analysing data of the integrated administration and control system (IACS) to detect patterns of agricultural land-use change at municipality level. Landscape Online, 48(1), 1-24. doi: 10.3097/LO.201648.
  • Marston, C. G., O'Neil, A. W., Morton, R. D., Wood, C. M., & Rowland, C. S. (2023). LCM2021 - The UK land cover map 2021 [preprint]. Earth System Science Data Discussions, doi: 10.5194/essd-2023-78.
  • Medium, (2022a, Ekim 14). Introducting EO-Learn. Retrieved from https://medium.com/sentinel-hub/introducing-eo-learn-ab37f2869f5c.
  • Medium, (2022b, Kasım 8). Land cover classification with EO-Learn. Retrieved from https://medium.com/sentinel-hub/land-cover-classification-with-eo-learn-part-3-c62ed9ecd405.
  • Medium, (2023, Ocak 5). Improving cloud dedection with machine learning. Retrieved from https://medium.com/ sentinel-hub/improving-cloud-detection-with-machine-learning-c09dc5d7cf13.
  • Pettorelli, N., Wegmann, M., Skidmore, A., Mucher, S., Dawson, T., Fernandez, M., ... Geller, G. (2016). Framing the concept of satellite remote sensing essential biodiversity variables: challenges and future directions. Remote Sensing Ecology Conservonsevation, 2(3), 122-131.
  • Üstüner, M., & Balık Şanlı, F. (2020). Çok zamanlı polarimetrik SAR verileri ile tarımsal ürünlerin sınıflandırılması. Jeodezi ve Jeoinformasyon Dergisi, 7(1), 1-10.
  • Skakun, S., Wevers, J., Brockmann, C., Doxani, G., Aleksandrov, M., Batič, M., ... Žust, L. (2022), Cloud Mask Intercomparison Exercise (CMIX): An evaluation of cloud masking algorithms for Landsat 8 and Sentinel-2. Remote Sensing of Environment, 274, 112990, doi: 10.1016/j.rse.2022.112990.
  • Şimşek, F. F. (2023). Çiftçi kayıt verileri ve açık kaynak koldu EO-Learn Kütüphanesi kullanılarak tarımsal ürün desen tespiti ve kontrolü (Doktora Tezi). Necmettin Erbakan Üniversitesi, Fen Bilimleri Enstitüsü, Konya, Türkiye.
  • Şimşek, F. F., & Durduran, S. (2022), Land cover classification using Land Parcel Identification System (LPIS) data and open source EO-Learn library. Geocarto International. Advance online publication. doi: 10.1080/10106049.2022.2146760.
  • Şimşek, F. F., & Durduran, S. (2023), Açık kaynak kodlu EO - Learn kütüphanesi ve çok zamanlı sentinel-2 görüntüleri ile tarımsal ürün sınıflandırması. Jeodezi ve Jeoinformasyon Dergisi, 10(1), 45-62.
  • Verde, N., Kokkoris, I. P., Georgiadis, C., Kaimaris, D., Dimopoulos, P., Mitsopoulos I., & Mallinis, G. (2020). National scale land cover classification for ecosystem services mapping and assessment, Using Multitemporal Copernicus EO Data And Google Earth Engine. Remote Sensing, 12(20), 3303. doi: 10.3390/rs12203303.
  • VBO. (2023, Ocak 13). LightGBM. Retrieved from https://medium.com/sentinel-hub/introducing-eo-learn-ab37f2869f5c.
  • Zanaga, D., Van De Kerchove, R., De Keersmaecker, W., Souverijns, N., Brockmann, C., Quast, R., … Arino, O. (2021). ESA WorldCover 10 m 2020 v100 [Data set]. Zenodo. Retrieved from https://doi.org/10.5281/zenodo.5571936.
  • 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), 583-94.
  • Zhu, Z., & Woodcock, C. E. (2012). Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sensing of Environment, 118, 83-94.

Arazi Parsel Tanımlama Sistemi Verileri Kullanılarak Ülkesel Ölçekte Arazi Örtüsü ve Arazi Kullanım Sınıflandırması

Year 2023, Volume: 4 Issue: 2, 276 - 288, 28.09.2023
https://doi.org/10.48123/rsgis.1268155

Abstract

Entegre İdare ve Kontrol Sistemi (EİKS), Avrupa Birliği tarafından tarımsal desteklemelerin sevk ve idaresini sağlayan bir sistemdir. Birçok farklı bileşenden ve sistemden oluşan bu sistemin ana bileşenlerinden biri de coğrafi bir veri tabanına dayalı olan ve farklı sınıflardaki referans parselleri içeren Arazi Parsel Tanımlama Sistemi (ATPS)’dir. 2016 yılında 30 cm çözünürlüklü ortofoto görüntüler kullanılarak ülke geneli boşluk kalmayacak şekilde APTS kapsamında sayısallaştırılmıştır. Çalışmada APTS’nin kilit bileşeni olan fiziksel bloklar (13,5 milyon) ile çok zamanlı Sentinel-2 görüntüleri (370 çerçeve) kullanılarak ülke ölçeğinde arazi örtüsü ve arazi kullanım sınıflandırması yapılmıştır. Çok büyük boyutta raster ve vektör veri içeren bu çalışma, Sinergise firmasının Amazon Web Servis (AWS) içerisindeki sunucularında bulunan açık kaynak kodlu EO-Learn kütüphanesi içerisindeki LightGBM makine öğrenme algoritması kullanılarak yapılmış olup % 86,07 genel doğruluk değerine ulaşılmıştır. Sınıflandırma işlemi sonucu 2021 yılına ait arazi örtüsü ve kullanım sınıflarının belirlenmesinin yanısıra, 2016 yılında çizilen APTS sınıflarına ait fiziksel bloklar ile sınıflandırma sonucu karşılaştırılarak özellikle değişim olan alanlar ile sınıfların güncellenmesinde referans altlık olarak kullanılması da hedeflenmektedir.

References

  • AWS. (2022, Kasım 11). Registry of open data on AWS. Retrieved from https://registry. opendata.aws/sentinel-2/.
  • Apaydın, C., & Abdikan, S. (2021). Fındık bahçelerinin Sentinel-2 verileri kullanılarak piksel tabanlı sınıflandırma yöntemleriyle belirlenmesi. Geomatik, 6(2), 107-114.
  • Candido, C., Blanco, A. C, Medina, J., Gubatanga, E., Santo, A., Ana, R. C., & Reyes, R. B. (2021) . Improving the consistency of multi-temporal land cover mapping of Laguna lake watershed using light gradient boosting machine (LightGBM) approach, change detection analysis, and Markov chain. Remote Sensing Applications: Society and Environment, 23(5), 100565. doi: 10.1016/j.rsase.2021.100565.
  • Eitel, J. H., Vierling, L. A., Litvak, M. A., Long, D. S., Schulthess, U., Ager, A. A., Krofcheck, D. J., & Stoscheck, L. (2011). Broadband, red-edge information from satellites improves early stress detection in a new mexico conifer woodland. Remote Sensing of Environment, 115(12), 3640-3646.
  • ESRI. (2022, Eylül 11). Tasseled cap function. Retrieved from https://pro.arcgis.com/en/pro-app/latest/help/analysis/ raster-functions/tasseled-cap-function.htm.
  • EO-Learn, (2022a, Aralık 17). Introduction EO-Learn. Retrieved from https://eo-learn.readthedocs.io/en/latest/#.
  • EO-Learn, (2022b, Aralık 24). EO-Learn core is the main subpackage which implements the basic building blocks. Retrieved from https://eo-learn.readthedocs.io/en/latest/examples/core/CoreOverview.html#EOPatch.
  • Gergeli, B. (2008). AB’de Entegre İdare ve Kontrol Sistemi Bilgi Teknolojileri (IT) yapısı, ödeme kuruluşu altyapısı ile olan ilişkisi ve etkileri, Türkiye’de uygulanabilirliği (AB Uzmanlık Tezi). Tarım ve Köy işleri Bakanlığı, Dış İlişkiler ve Avrupa Birliği Koordinasyon Dairesi Başkanlığı, Ankara, Türkiye.
  • GITHUB, (2022, Aralık 17). Sentinel Hub’s cloud dedector for Sentinel-2 imagery. Retrieved from https://github.com/ sentinel-hub/sentinel2-cloud-detector.
  • Guolin, K., Men, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye Q., & Liu, T. Y. (2017, December). LightGBM: A highly efficient gradient boosting decision tree. In 31st Conference on Neural Information Processing Systems, 2017. Proceedings. (pp. 1-9). NeurIPS.
  • Harvolk, S., Kornatz, P., Otte, A., & Simmering, D., (2014). Using existing landscape data to assess the ecological potential of miscanthus cultivation in a marginal landscape. GCB Bioenergy, 6(3), 227-241.
  • Jarray, N., Abbes, A. B., Rhif, M., Chouikhi, F., & Farah, I. R. (2021, July). An open source platform to estimate Soil Moisture using Machine Learning Methods based on Eo-learn library. In International Congress of Advanced Technology and Engineering, 2021. Proceedings. (pp. 1-5). IEEE.
  • Kauth, R. J., & Thomas, G. S. (1976, June). The Tasselled Cap - a graphic description of the spectral - temporal development of agricultural crops as seen by LANDSAT. In Symposium on Machine Processing of Remotely Sensed Data, 1976. Proceedings. (pp. 41-59). IEEE.
  • Karlsen, S. R., Stendardi, L., Tømmervik, H., Nilsen, L., Arntzen, I. M., & Cooper, E. J. (2021). Time-Series of Cloud-Free Sentinel-2 NDVI data used in mapping the onset of growth of central Spitsbergen, Svalbard. Remote Sensing, 13(15), 3031. doi: 10.3390/rs13153031.
  • Kohavi, R. (1995, August). A study of cross-validation and bootstrap for accuracy estimation and model selection. In International Joint Conference of Artificial Intelligence, 1995. Proceedings. (pp. 1137-1145). IJCAI.
  • Keser, T. Z. (2007). Entegre idare ve kontrol sistemi, mevcut durum ve AB üye ülkeleri arasından seçilen örnekler üzerinden incelenmesi (AB Uzmanlık Tezi). Tarım ve Köy işleri Bakanlığı, Dış İlişkiler ve Avrupa Birliği Koordinasyon Dairesi Başkanlığı, Ankara, Türkiye.
  • Langat, P. K., Kumar, L., & Koech, R. (2019). Monitoring river channel dynamics using remote sensing and GIS techniques. Geomorphology, 325, 92-102.
  • Lambin, E. F., Geist, H. J., & Rindfuss, R. R. (2006). Local Processes with Global Impacts. In E.F. Lambin & H.J. Geist (Eds.), Land-Use and Land-Cover Change: Local processes and global impacts (pp. 1-8), Heidelberg: Springer Berlin.
  • LPIS Guideline, (2015). LPIS data capture photo interpretation and digitization guidelines. Republic of Turkey Ministry of Agriculture and Forestry, Ankara, Turkey.
  • Li, W., Ding, S., Chen, Y., Wang, H., & Yang, S. (2019). Transfer learning-based default prediction model for consumer credit in China. Journal of Supercomputing, 75(2), 862-884.
  • LightGBM, (2023, Şubat 1). Welcome to LightGBM’s documentation. Retrieved from https://lightgbm.readthedocs.io/ en/latest/index.html#.
  • Liu, L., Ji, M., & Buchroithner, M. F. (2017). Combining partial least squares and the gradient-boosting method for soil property retrieval using visible near-ınfrared shortwave ınfrared spectra. Remote Sensing, 9(12), 1299. doi: 10.3390/rs9121299.
  • Lu, D., & Weng, Q. (2007). A survey of image classification methods and techniques for improving classification Performance. International Journal of Remote Sensing, 28(5), 823-870.
  • Lubej, M., Aleksandrov, M., Batic, M., Kadunc, M., Milcinski, G., Peressutti, D., & Zupanc, A. (2019, May). Spatio-temporal deep learning: an application to land cover classification. In ESA Living Planet Symposium, 2019. Proceedings. (pp. 2-5). ESA.
  • Lüker-Jans, N., Simmering, D., & Otte, A. (2016). Analysing data of the integrated administration and control system (IACS) to detect patterns of agricultural land-use change at municipality level. Landscape Online, 48(1), 1-24. doi: 10.3097/LO.201648.
  • Marston, C. G., O'Neil, A. W., Morton, R. D., Wood, C. M., & Rowland, C. S. (2023). LCM2021 - The UK land cover map 2021 [preprint]. Earth System Science Data Discussions, doi: 10.5194/essd-2023-78.
  • Medium, (2022a, Ekim 14). Introducting EO-Learn. Retrieved from https://medium.com/sentinel-hub/introducing-eo-learn-ab37f2869f5c.
  • Medium, (2022b, Kasım 8). Land cover classification with EO-Learn. Retrieved from https://medium.com/sentinel-hub/land-cover-classification-with-eo-learn-part-3-c62ed9ecd405.
  • Medium, (2023, Ocak 5). Improving cloud dedection with machine learning. Retrieved from https://medium.com/ sentinel-hub/improving-cloud-detection-with-machine-learning-c09dc5d7cf13.
  • Pettorelli, N., Wegmann, M., Skidmore, A., Mucher, S., Dawson, T., Fernandez, M., ... Geller, G. (2016). Framing the concept of satellite remote sensing essential biodiversity variables: challenges and future directions. Remote Sensing Ecology Conservonsevation, 2(3), 122-131.
  • Üstüner, M., & Balık Şanlı, F. (2020). Çok zamanlı polarimetrik SAR verileri ile tarımsal ürünlerin sınıflandırılması. Jeodezi ve Jeoinformasyon Dergisi, 7(1), 1-10.
  • Skakun, S., Wevers, J., Brockmann, C., Doxani, G., Aleksandrov, M., Batič, M., ... Žust, L. (2022), Cloud Mask Intercomparison Exercise (CMIX): An evaluation of cloud masking algorithms for Landsat 8 and Sentinel-2. Remote Sensing of Environment, 274, 112990, doi: 10.1016/j.rse.2022.112990.
  • Şimşek, F. F. (2023). Çiftçi kayıt verileri ve açık kaynak koldu EO-Learn Kütüphanesi kullanılarak tarımsal ürün desen tespiti ve kontrolü (Doktora Tezi). Necmettin Erbakan Üniversitesi, Fen Bilimleri Enstitüsü, Konya, Türkiye.
  • Şimşek, F. F., & Durduran, S. (2022), Land cover classification using Land Parcel Identification System (LPIS) data and open source EO-Learn library. Geocarto International. Advance online publication. doi: 10.1080/10106049.2022.2146760.
  • Şimşek, F. F., & Durduran, S. (2023), Açık kaynak kodlu EO - Learn kütüphanesi ve çok zamanlı sentinel-2 görüntüleri ile tarımsal ürün sınıflandırması. Jeodezi ve Jeoinformasyon Dergisi, 10(1), 45-62.
  • Verde, N., Kokkoris, I. P., Georgiadis, C., Kaimaris, D., Dimopoulos, P., Mitsopoulos I., & Mallinis, G. (2020). National scale land cover classification for ecosystem services mapping and assessment, Using Multitemporal Copernicus EO Data And Google Earth Engine. Remote Sensing, 12(20), 3303. doi: 10.3390/rs12203303.
  • VBO. (2023, Ocak 13). LightGBM. Retrieved from https://medium.com/sentinel-hub/introducing-eo-learn-ab37f2869f5c.
  • Zanaga, D., Van De Kerchove, R., De Keersmaecker, W., Souverijns, N., Brockmann, C., Quast, R., … Arino, O. (2021). ESA WorldCover 10 m 2020 v100 [Data set]. Zenodo. Retrieved from https://doi.org/10.5281/zenodo.5571936.
  • 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), 583-94.
  • Zhu, Z., & Woodcock, C. E. (2012). Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sensing of Environment, 118, 83-94.
There are 40 citations in total.

Details

Primary Language Turkish
Subjects Photogrammetry and Remote Sensing
Journal Section Research Articles
Authors

Fatih Fehmi Şimşek 0000-0003-4016-4408

Early Pub Date September 26, 2023
Publication Date September 28, 2023
Submission Date March 20, 2023
Acceptance Date May 22, 2023
Published in Issue Year 2023 Volume: 4 Issue: 2

Cite

APA Şimşek, F. F. (2023). Arazi Parsel Tanımlama Sistemi Verileri Kullanılarak Ülkesel Ölçekte Arazi Örtüsü ve Arazi Kullanım Sınıflandırması. Türk Uzaktan Algılama Ve CBS Dergisi, 4(2), 276-288. https://doi.org/10.48123/rsgis.1268155