Çok zamanlı polarimetrik SAR verileri ile tarımsal ürünlerin sınıflandırılması

Year 2020, Volume: 7 Issue: 1, 1 - 10, 01.05.2020

Mustafa Üstüner Fusun Balık Şanlı

https://doi.org/10.9733/JGG.2020R0001.T

Abstract

Bu çalışma, çok zamanlı Polarimetrik SAR (Polarimetrik Sentetik Açıklıklı Radar, PolSAR) görüntülerinin tarımsal ürünlerin sınıflandırılmasındaki kullanımını araştırmaktadır. Çok zamanlı PolSAR görüntüleri, özellikle zamansal izlemenin önemli olduğu tarım projelerinde önemli avantajlar sağlamaktadır. Bu çalışma kapsamında, beş farklı ürünün (mısır, patates, buğday, ayçiçeği ve yem bitkisi) sınıflandırılması amacıyla üç farklı makine öğrenme algoritması (hafif gradyan hızlandırma makineleri (Light Gradient Boosting Machines, LightGBM), rastgele orman (RO) ve destek vektör makineleri (DVM)) kullanılmıştır. PolSAR verisi olarak, çok zamanlı Radarsat-2 SAR görüntülerine ait doğrusal geri saçılım değerlerini içeren orijinal bantlar kullanılmıştır. Sınıflandırmalara ilişkin genel doğruluk değerleri LightGBM, RO ve DVM algoritmaları için sırasıyla 0.857 (±0.026), 0.855 (±0.033) ve 0.834 (±0.039) olarak elde edilmiştir. McNemar testi sonuçlarına göre, en yüksek iki sınıflandırma doğruluğu arasındaki farkın istatistiksel olarak anlamlı olmadığı görülmüştür. Sınıflandırma sonuçlarının değerlendirilmesi aşamasında k-katlamalı çapraz doğrulama yöntemi kullanılmıştır. Ayrıca bu sonuçlar, çok zamanlı PolSAR verilerinin tarımsal ürünlerin sınıflandırılmasında etkin bir şekilde kullanılabileceğini göstermiştir.

Keywords

Polarimetrik SAR, Sınıflandırma, Uzaktan Algılama, Tarım

Supporting Institution

Yıldız Teknik Üniversitesi (YTÜ) Bilimsel Araştırma Projeleri Koordinatörlüğü

Project Number

FBA-2017-3062

Thanks

Bu çalışma, Yıldız Teknik Üniversitesi (YTÜ) Bilimsel Araştırma Projeleri Koordinatörlüğü tarafından FBA-2017-3062 kodlu proje kapsamında desteklenmiştir. Destekleri için Yıldız Teknik Üniversitesi (YTÜ) Bilimsel Araştırma Projeleri Koordinatörlüğü’ne teşekkür ederiz.

Crop classification using multi-temporal polarimetric SAR data

Abstract

This study evaluates the use of multi-temporal Polarimetric SAR (Polarimetric Synthetic Aperture Radar, PolSAR) images for crop classification. Multi-temporal polarimetric SAR images could be very advantageous for crop classification especially in time-critical agricultural projects. Within this research, three types of machine learning algorithms (light gradient boosting machines (LightGBM), random forest (RF) and support vector machines (SVM)) were utilized for the classification of five crops (maize, potato, wheat, sunflower, and alfalfa). From the multi-temporal PolSAR data, the original features (i.e. linear backscatter coefficients) of Radarsat-2 were extracted and incorporated into the classification step. The overall classification accuracies were obtained as 0.857 (±0.026), 0.855 (±0.033) and 0.834 (±0.039) for LightGBM, RF and SVM, respectively. The difference between the accuracies obtained by LightGBM and random forest (RF) was found to be statistically non-significant based upon the McNemar’s test. K-fold cross validation was used to assess the classification results. Furthermore, these results showed the added benefits of multi-temporal PolSAR data for crop classification.

Keywords

Polarimetric SAR, Classification, Remote sensing, Agriculture

Project Number

FBA-2017-3062

References

• Boualleg, Y., Farah, M., & Farah, I. R. (2019). Remote Sensing Scene Classification Using Convolutional Features and Deep Forest Classifier. IEEE Geoscience and Remote Sensing Letters.
• Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., Grobler, J., Layton, R., Vanderplas, J., Joly, A., Holt, B., & Varoquaux, G. (2013). API design for machine learning software: experiences from the scikit-learn project. arXiv preprint arXiv:1309.0238.
• Georganos, S., Grippa, T., Vanhuysse, S., Lennert, M., Shimoni, M., Kalogirou, S., & Wolff, E. (2018). Less is more: Optimizing classification performance through feature selection in a very-high-resolution remote sensing object-based urban application. GIScience & remote sensing, 55(2), 221-242.
• Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern Recognition Letters, 27(4), 294-300.
• Gui, R., Xu, X., Wang, L., Yang, R., & Pu, F. (2018). A Generalized Zero-Shot Learning Framework for PolSAR Land Cover Classification. Remote Sensing, 10(8), 1307.
• Huang, X., Wang, J., Shang, J., Liao, C., & Liu, J. (2017). Application of polarization signature to land cover scattering mechanism analysis and classification using multi-temporal C-band polarimetric RADARSAT-2 imagery. Remote Sensing of Environment, 193, 11-28.
• Jiao, X., Kovacs, J. M., Shang, J., McNairn, H., Walters, D., Ma, B., & Geng, X. (2014). Object-oriented crop mapping and monitoring using multi-temporal polarimetric RADARSAT-2 data. ISPRS Journal of Photogrammetry and Remote Sensing, 96, 38-46.
• Kavzoğlu, T., & Çölkesen, I. (2009). A kernel functions analysis for support vector machines for land cover classification. International Journal of Applied Earth Observation and Geoinformation, 11(5), 352-359.
• Kavzoğlu, T., & Çölkesen, I. (2013). An assessment of the effectiveness of a rotation forest ensemble for land-use and land-cover mapping. International Journal of Remote Sensing, 34(12), 4224-4241.
• Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems (s. 3146-3154).
• Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. Ijcai 14(2), 1137-1145.
• Larrañaga, A., & Álvarez-Mozos, J. (2016). On the added value of Quad-Pol Data in a multi-temporal crop classification framework based on RADARSAT-2 imagery. Remote Sensing, 8(4), 335.
• Lee, J. S., & Pottier, E. (2009). Polarimetric radar imaging: from basics to applications. CRC press.
• Liu, C., Shang, J., Vachon, P. W., & McNairn, H. (2013). Multiyear crop monitoring using polarimetric RADARSAT-2 data. IEEE Transactions on Geoscience and Remote sensing, 51(4), 2227-2240.
• Li, W., Ding, S., Chen, Y., Wang, H., & Yang, S. (2019). Transfer learning-based default prediction model for consumer credit in China. The Journal of Supercomputing, 75(2), 862-884.
• Ma, Q., Wang, J., Shang, J., & Wang, P. (2013). Assessment of multi-temporal RADARSAT-2 polarimetric SAR data for crop classification in an urban/rural fringe area. 2013 Second International Conference on Agro-Geoinformatics (Agro-Geoinformatics) (s. 314-319). IEEE.
• Maghsoudi, Y., Collins, M. J., & Leckie, D. G. (2013). Radarsat-2 polarimetric SAR data for boreal forest classification using SVM and a wrapper feature selector. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(3), 1531-1538.
• McNairn, H., & Brisco, B. (2004). The application of C-band polarimetric SAR for agriculture: A review. Canadian Journal of Remote Sensing, 30(3), 525-542.
• McNairn, H., & Shang, J. (2016). A review of multitemporal synthetic aperture radar (SAR) for crop monitoring. In Multitemporal Remote Sensing (pp. 317-340). Springer, Cham.
• Melgani, F., & Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on geoscience and remote sensing, 42(8), 1778-1790.
• Niu, X., & Ban, Y. (2013). Multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using an object-based support vector machine and a rule-based approach. International journal of remote sensing, 34(1), 1-26.
• Ok, A. O., Akar, O., & Güngör, O. (2012). Evaluation of random forest method for agricultural crop classification. European Journal of Remote Sensing, 45(1), 421-432.
• Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, È. (2011). Scikit-learn: Machine learning in Python. Journal of machine learning research, 12(Oct), 2825-2830.
• Ressel, R., Singha, S., Lehner, S., Rösel, A., & Spreen, G. (2016). Investigation into different polarimetric features for sea ice classification using X-band synthetic aperture radar. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(7), 3131-3143.
• Rodriguez-Galiano, V. F., Ghimire, B., Rogan, J., Chica-Olmo, M., & Rigol-Sanchez, J. P. (2012). An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67, 93-104.
• Saner, C. B., Kesici, M., Mahdı, M., Yaslan, Y., & Genç, V. İ. (2019). Güç Sistemlerinde Geçici Hal Kararsızlığının Arıza Öncesi Fazör Ölçümleri Kullanarak Karar Ağacı Tabanlı Kestirimi. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 23(1), 6-14.
• Schmullius, C., Thiel, C., Pathe, C., & Santoro, M. (2015). Radar time series for land cover and forest mapping. Remote Sensing Time Series (s. 323-356). Springer, Cham.
• Tamiminia, H., Homayouni, S., McNairn, H., & Safari, A. (2017). A particle swarm optimized kernel-based clustering method for crop mapping from multi-temporal polarimetric L-band SAR observations. International journal of applied earth observation and geoinformation, 58, 201-212.
• Toosi, N. B., Soffianian, A. R., Fakheran, S., Pourmanafi, S., Ginzler, C., & Waser, L. T. (2019). Comparing different classification algorithms for monitoring mangrove cover changes in southern Iran. Global Ecology and Conservation, e00662.
• Üstüner, M., & Balık Şanlı, F. (2019). Polarimetric Target Decompositions and Light Gradient Boosting Machine for Crop Classification: A Comparative Evaluation. ISPRS International Journal of Geo-Information, 8(2), 97.
• Valcarce-Diñeiro, R., Arias-Pérez, B., Lopez-Sanchez, J. M., & Sánchez, N. (2019). Multi-Temporal Dual-and Quad-Polarimetric Synthetic Aperture Radar Data for Crop-Type Mapping. Remote Sensing, 11(13), 1518.
• Xia, J., Yokoya, N., & Iwasaki, A. (2016). Hyperspectral image classification with canonical correlation forests. IEEE Transactions on Geoscience and Remote Sensing, 55(1), 421-431.
• URL-1: Microsoft Dağıtık Makine Öğrenmesi Yazılımı (Distributed Machine Learning Toolkit), http://www.dmtk.io/, (Erişim Tarihi: 21 Eylül 2019).
• URL-2: LightGBM, Light Gradient Boosting Machine, https://github.com/Microsoft/lightGBM, (Erişim Tarihi: 21 Eylül 2019).
• URL-3: Machine Learning Challenge Winning Solutions, https://github.com/microsoft/LightGBM/blob/master/examples/README.md# machine-learning-challenge-winning-solutions (Erişim Tarihi: 21 Eylül 2019).
• URL-4: Parameters Tuning, https://lightgbm.readthedocs.io/en/latest/Parameters-Tuning.html (Erişim Tarihi: 21 Eylül 2019).