Research Article
BibTex RIS Cite

Crop Classification Using Light Gradient Boosting Machines

Year 2020, Volume: 1 Issue: 2, 97 - 105, 30.09.2020

Abstract

In recent years, machine learning and data science communities have started to develop novel algorithms, especially in the area of ensemble learning. The new generation ensemble learning algorithms such as extreme gradient boosting (XGBoost) and light gradient boosting machines (LightGBM) have gained great attention in data science because of their greater performance compared to the state-of-art machine learning algorithms. However, they have not yet been fully tested for the classification of remotely-sensed images. This paper compares the performance of the XGBoost and LightGBM in terms of classification accuracy and computation time for crop classification using multi-temporal polarimetric SAR (PolSAR) data. The linear backscatter of full-polarimetric RADARSAT-2 were used as the polarimetric feature in this research. A multi-temporal dataset was used in our study because of the time-dynamic structure of crops. Our experimental results demonstrate that LightGBM yielded greater performance compared to XGBoost in terms of classification accuracy (0.860 vs 0.845) and computation cost. K-fold (k=5) cross validation was used to assess the classification results.

References

  • Abdi, A. M. (2020). Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data. GIScience & Remote Sensing, 57(1), 1-20, doi: 10.1080/15481603.2019.1650447.
  • Abdikan, S., Bilgin, G., Sanli, F. B., Uslu, E., & Ustuner, M. (2015). Enhancing land use classification with fusing dual-polarized TerraSAR-X and multispectral RapidEye data. Journal of Applied Remote Sensing, 9(1), 096054, doi: 10.1117/1.JRS.9.096054.
  • Akar, Ö., & Güngör, O. (2012). Classification of multispectral images using Random Forest algorithm. Journal of Geodesy and Geoinformation, 1(2), 105-112.
  • Atzberger, C. (2013). Advances in remote sensing of agriculture: Context description, existing operational monitoring systems and major information needs. Remote Sensing, 5(2), 949-981.
  • Ayhan, S., & Erdoğmuş, Ş. (2014). Destek vektör makineleriyle sınıflandırma problemlerinin çözümü için çekirdek fonksiyonu seçimi. Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilimler Dergisi, 9(1), 175-201.
  • Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31.
  • Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. Proceedings. (pp. 785–794).
  • Conrad, C., Dech, S., Dubovyk, O., Fritsch, S., Klein, D., Löw, F., ... & Zeidler, J. (2014). Derivation of temporal windows for accurate crop discrimination in heterogeneous croplands of Uzbekistan using multitemporal RapidEye images. Computers and Electronics in Agriculture, 103, 63-74.
  • Dey, S., Mandal, D., Robertson, L. D., Banerjee, B., Kumar, V., McNairn, H., Bhattacharya, A. & Rao, Y. S. (2020). In-season crop classification using elements of the Kennaugh matrix derived from polarimetric RADARSAT-2 SAR data. International Journal of Applied Earth Observation and Geoinformation, 88, 102059, doi: 10.1016/j.jag.2020.102059.
  • 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.
  • Gómez-Chova, L., Tuia, D., Moser, G., & Camps-Valls, G. (2015). Multimodal classification of remote sensing images: A review and future directions. In Proceedings of the IEEE, 103(9), (pp. 1560-1584). IEEE.
  • Hütt, C., Koppe, W., Miao, Y., & Bareth, G. (2016). Best accuracy land use/land cover (LULC) classification to derive crop types using multitemporal, multisensor, and multi-polarization SAR satellite images. Remote Sensing, 8(8), 684, doi: 10.3390/rs8080684.
  • Inglada, J., Arias, M., Tardy, B., Hagolle, O., Valero, S., Morin, D., ... & Koetz, B. (2015). Assessment of an operational system for crop type map production using high temporal and spatial resolution satellite optical imagery. Remote Sensing, 7(9), 12356-12379.
  • Jiang, H., Li, D., Jing, W., Xu, J., Huang, J., Yang, J., & Chen, S. (2019). Early season mapping of sugarcane by applying machine learning algorithms to Sentinel-1A/2 time series data: a case study in Zhanjiang City, China. Remote Sensing, 11(7), 861, doi: 10.3390/rs11070861.
  • 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.
  • Kavzoglu, T., & Colkesen, 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.
  • Khosravi, I., & Alavipanah, S. K. (2019). A random forest-based framework for crop mapping using temporal, spectral, textural and polarimetric observations. International Journal of Remote Sensing, 40(18), 7221-7251.
  • 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. In Advances in neural information processing systems (NIPS 2017), 2017. Proceedings. (pp. 3146-3154).
  • Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In 14th international joint conference on Artificial intelligence (IJCAI’95), 1995. Proceedings. (pp. 1137-1145).
  • 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.
  • LightGBM, (2020, June 15). LightGBM Python API, Retrieved from https://lightgbm.readthedocs.io/en/latest/Python-API.html.
  • Liu, L., Ji, M., & Buchroithner, M. (2017). Combining partial least squares and the gradient-boosting method for soil property retrieval using visible near-infrared shortwave infrared spectra. Remote Sensing, 9(12), 1299, doi: 10.3390/rs9121299.
  • 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.
  • McNairn, H., & Shang, J. (2016). A review of multitemporal synthetic aperture radar (SAR) for crop monitoring. In Y. Ban (Eds.), Multitemporal Remote Sensing: Methods and Applications, (pp. 317-340), Cham, Switzerland: Springer International Publishing AG.
  • McNairn, H., Ellis, J., Van Der Sanden, J. J., Hirose, T., & Brown, R. J. (2002). Providing crop information using RADARSAT-1 and satellite optical imagery. International Journal of Remote Sensing, 23(5), 851-870.
  • 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.
  • Moorthy, S. M. K., Calders, K., Vicari, M. B., & Verbeeck, H. (2019). Improved supervised learning-based approach for leaf and wood classification from LiDAR point clouds of forests. IEEE Transactions on Geoscience and Remote Sensing, 58(5), 3057-3070.
  • Pal, M. (2012). Advanced algorithms for land use and cover classification. In X. Yang & J. Li (Eds.), Advances in Mapping from Remote Sensor Imagery: Techniques and Applications, (pp. 70-82), Boca Raton: CRC Press.
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825-2830.
  • Petropoulos, G. P., Kalaitzidis, C., & Vadrevu, K. P. (2012). Support vector machines and object-based classification for obtaining land-use/cover cartography from Hyperion hyperspectral imagery. Computers & Geosciences, 41, 99-107.
  • Rumora, L., Miler, M., & Medak, D. (2020). Impact of Various Atmospheric Corrections on Sentinel-2 Land Cover Classification Accuracy Using Machine Learning Classifiers. ISPRS International Journal of Geo-Information, 9(4), 277, doi: 10.3390/ijgi9040277.
  • Saini, R., & Ghosh, S. K. (2019). Crop classification in a heterogeneous agricultural environment using ensemble classifiers and single-date Sentinel-2A imagery. Geocarto International, 1-19, doi: 10.1080/10106049.2019.1700556.
  • Shi, X., Cheng, Y., & Xue, D. (2019, October). Classification Algorithm of Urban Point Cloud Data based on LightGBM. In IOP Conference Series: Materials Science and Engineering (Vol. 631, No. 5, p. 052041). IOP Publishing.
  • Skakun, S., Kussul, N., Shelestov, A. Y., Lavreniuk, M., & Kussul, O. (2016). Efficiency assessment of multitemporal C-band Radarsat-2 intensity and Landsat-8 surface reflectance satellite imagery for crop classification in Ukraine. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(8), 3712-3719.
  • 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, 19, e00662, doi: 10.1016/j.gecco.2019.e00662.
  • Ustuner, M., & Balik Sanli, 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, doi: 10.3390/ijgi8020097.
  • Villa, P., Stroppiana, D., Fontanelli, G., Azar, R., & Brivio, P. A. (2015). In-season mapping of crop type with optical and X-band SAR data: A classification tree approach using synoptic seasonal features. Remote Sensing, 7(10), 12859-12886.
  • Waldhoff, G., Curdt, C., Hoffmeister, D., & Bareth, G. (2012). Analysis of multitemporal and multisensor remote sensing data for crop rotation mapping. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 1, 177-182.
  • XGBoost, (2020, June 15). XGBoost Python Package, Retrieved from https://xgboost.readthedocs.io/en/latest/python/ index.html.
  • Zhong, L., Hu, L., & Zhou, H. (2019). Deep learning based multi-temporal crop classification. Remote Sensing of Environment, 221, 430-443.

Hafif Gradyan Artırma Makineleri ile Tarımsal Ürünlerin Sınıflandırılması

Year 2020, Volume: 1 Issue: 2, 97 - 105, 30.09.2020

Abstract

Son yıllarda, makine öğrenmesi ve veri bilimi alanındaki araştırmacılar özgün ve de özellikle topluluk öğrenmesi alanında yeni algoritmalar geliştirmeye başlamışlardır. Bu yeni nesil topluluk öğrenme algoritmalarından olan aşırı gradyan artırma (XGBoost) ve hafif gradyan artırma makineleri (LightGBM) yöntemleri, mevcut ve aynı zamanda sık kullanılan makine öğrenme algoritmalarına kıyasla daha yüksek performans gösterdiklerinden dolayı veri bilimindeki araştırmacıların ilgisini çekmiştir. Ancak uzaktan algılama görüntülerinin sınıflandırılması amacıyla henüz yeterli düzeyde test edilmemiştir. Bu çalışma kapsamında, XGBoost ve LightGBM algoritmalarının çok zamanlı polarimetrik sentetik açıklıklı radar (PolSAR) görüntüleri kullanılarak tarımsal ürünlerin sınıflandırılmasındaki performansları, hem işlem hızı hem de elde edilen sınıflandırma doğrulukları açısından karşılaştırılmıştır. Çalışma kapsamında, tam polarimetrik RADARSAT-2 uydu görüntülerine ait doğrusal geri saçılım değerleri kullanılmıştır. Tarımsal ürünlerin zamana bağlı dinamik olarak değişen yapılarından dolayı çalışmamızda çok zamanlı bir veri seti kullanılmıştır. Deneysel sonuçlarımız, LightGBM yönteminin hem işlem hızı hem de sınıflandırma performansı açısından XGBoost yöntemine göre daha üstün olduğunu göstermiştir, bu iki yöntem için elde edilen doğruluklar sırası ile 0.860 ve 0.845’dir. Sınıflandırma sonuçlarının elde edilmesinde k-katlamalı (k=5) çapraz doğrulama tekniği kullanılmıştır.

References

  • Abdi, A. M. (2020). Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data. GIScience & Remote Sensing, 57(1), 1-20, doi: 10.1080/15481603.2019.1650447.
  • Abdikan, S., Bilgin, G., Sanli, F. B., Uslu, E., & Ustuner, M. (2015). Enhancing land use classification with fusing dual-polarized TerraSAR-X and multispectral RapidEye data. Journal of Applied Remote Sensing, 9(1), 096054, doi: 10.1117/1.JRS.9.096054.
  • Akar, Ö., & Güngör, O. (2012). Classification of multispectral images using Random Forest algorithm. Journal of Geodesy and Geoinformation, 1(2), 105-112.
  • Atzberger, C. (2013). Advances in remote sensing of agriculture: Context description, existing operational monitoring systems and major information needs. Remote Sensing, 5(2), 949-981.
  • Ayhan, S., & Erdoğmuş, Ş. (2014). Destek vektör makineleriyle sınıflandırma problemlerinin çözümü için çekirdek fonksiyonu seçimi. Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilimler Dergisi, 9(1), 175-201.
  • Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31.
  • Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. Proceedings. (pp. 785–794).
  • Conrad, C., Dech, S., Dubovyk, O., Fritsch, S., Klein, D., Löw, F., ... & Zeidler, J. (2014). Derivation of temporal windows for accurate crop discrimination in heterogeneous croplands of Uzbekistan using multitemporal RapidEye images. Computers and Electronics in Agriculture, 103, 63-74.
  • Dey, S., Mandal, D., Robertson, L. D., Banerjee, B., Kumar, V., McNairn, H., Bhattacharya, A. & Rao, Y. S. (2020). In-season crop classification using elements of the Kennaugh matrix derived from polarimetric RADARSAT-2 SAR data. International Journal of Applied Earth Observation and Geoinformation, 88, 102059, doi: 10.1016/j.jag.2020.102059.
  • 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.
  • Gómez-Chova, L., Tuia, D., Moser, G., & Camps-Valls, G. (2015). Multimodal classification of remote sensing images: A review and future directions. In Proceedings of the IEEE, 103(9), (pp. 1560-1584). IEEE.
  • Hütt, C., Koppe, W., Miao, Y., & Bareth, G. (2016). Best accuracy land use/land cover (LULC) classification to derive crop types using multitemporal, multisensor, and multi-polarization SAR satellite images. Remote Sensing, 8(8), 684, doi: 10.3390/rs8080684.
  • Inglada, J., Arias, M., Tardy, B., Hagolle, O., Valero, S., Morin, D., ... & Koetz, B. (2015). Assessment of an operational system for crop type map production using high temporal and spatial resolution satellite optical imagery. Remote Sensing, 7(9), 12356-12379.
  • Jiang, H., Li, D., Jing, W., Xu, J., Huang, J., Yang, J., & Chen, S. (2019). Early season mapping of sugarcane by applying machine learning algorithms to Sentinel-1A/2 time series data: a case study in Zhanjiang City, China. Remote Sensing, 11(7), 861, doi: 10.3390/rs11070861.
  • 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.
  • Kavzoglu, T., & Colkesen, 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.
  • Khosravi, I., & Alavipanah, S. K. (2019). A random forest-based framework for crop mapping using temporal, spectral, textural and polarimetric observations. International Journal of Remote Sensing, 40(18), 7221-7251.
  • 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. In Advances in neural information processing systems (NIPS 2017), 2017. Proceedings. (pp. 3146-3154).
  • Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In 14th international joint conference on Artificial intelligence (IJCAI’95), 1995. Proceedings. (pp. 1137-1145).
  • 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.
  • LightGBM, (2020, June 15). LightGBM Python API, Retrieved from https://lightgbm.readthedocs.io/en/latest/Python-API.html.
  • Liu, L., Ji, M., & Buchroithner, M. (2017). Combining partial least squares and the gradient-boosting method for soil property retrieval using visible near-infrared shortwave infrared spectra. Remote Sensing, 9(12), 1299, doi: 10.3390/rs9121299.
  • 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.
  • McNairn, H., & Shang, J. (2016). A review of multitemporal synthetic aperture radar (SAR) for crop monitoring. In Y. Ban (Eds.), Multitemporal Remote Sensing: Methods and Applications, (pp. 317-340), Cham, Switzerland: Springer International Publishing AG.
  • McNairn, H., Ellis, J., Van Der Sanden, J. J., Hirose, T., & Brown, R. J. (2002). Providing crop information using RADARSAT-1 and satellite optical imagery. International Journal of Remote Sensing, 23(5), 851-870.
  • 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.
  • Moorthy, S. M. K., Calders, K., Vicari, M. B., & Verbeeck, H. (2019). Improved supervised learning-based approach for leaf and wood classification from LiDAR point clouds of forests. IEEE Transactions on Geoscience and Remote Sensing, 58(5), 3057-3070.
  • Pal, M. (2012). Advanced algorithms for land use and cover classification. In X. Yang & J. Li (Eds.), Advances in Mapping from Remote Sensor Imagery: Techniques and Applications, (pp. 70-82), Boca Raton: CRC Press.
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825-2830.
  • Petropoulos, G. P., Kalaitzidis, C., & Vadrevu, K. P. (2012). Support vector machines and object-based classification for obtaining land-use/cover cartography from Hyperion hyperspectral imagery. Computers & Geosciences, 41, 99-107.
  • Rumora, L., Miler, M., & Medak, D. (2020). Impact of Various Atmospheric Corrections on Sentinel-2 Land Cover Classification Accuracy Using Machine Learning Classifiers. ISPRS International Journal of Geo-Information, 9(4), 277, doi: 10.3390/ijgi9040277.
  • Saini, R., & Ghosh, S. K. (2019). Crop classification in a heterogeneous agricultural environment using ensemble classifiers and single-date Sentinel-2A imagery. Geocarto International, 1-19, doi: 10.1080/10106049.2019.1700556.
  • Shi, X., Cheng, Y., & Xue, D. (2019, October). Classification Algorithm of Urban Point Cloud Data based on LightGBM. In IOP Conference Series: Materials Science and Engineering (Vol. 631, No. 5, p. 052041). IOP Publishing.
  • Skakun, S., Kussul, N., Shelestov, A. Y., Lavreniuk, M., & Kussul, O. (2016). Efficiency assessment of multitemporal C-band Radarsat-2 intensity and Landsat-8 surface reflectance satellite imagery for crop classification in Ukraine. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(8), 3712-3719.
  • 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, 19, e00662, doi: 10.1016/j.gecco.2019.e00662.
  • Ustuner, M., & Balik Sanli, 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, doi: 10.3390/ijgi8020097.
  • Villa, P., Stroppiana, D., Fontanelli, G., Azar, R., & Brivio, P. A. (2015). In-season mapping of crop type with optical and X-band SAR data: A classification tree approach using synoptic seasonal features. Remote Sensing, 7(10), 12859-12886.
  • Waldhoff, G., Curdt, C., Hoffmeister, D., & Bareth, G. (2012). Analysis of multitemporal and multisensor remote sensing data for crop rotation mapping. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 1, 177-182.
  • XGBoost, (2020, June 15). XGBoost Python Package, Retrieved from https://xgboost.readthedocs.io/en/latest/python/ index.html.
  • Zhong, L., Hu, L., & Zhou, H. (2019). Deep learning based multi-temporal crop classification. Remote Sensing of Environment, 221, 430-443.
There are 40 citations in total.

Details

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

Mustafa Üstüner 0000-0003-0553-2682

Saygın Abdikan 0000-0002-3310-352X

Gökhan Bilgin 0000-0002-5532-477X

Füsun Balık Şanlı 0000-0003-1243-8299

Publication Date September 30, 2020
Submission Date May 20, 2020
Acceptance Date August 13, 2020
Published in Issue Year 2020 Volume: 1 Issue: 2

Cite

APA Üstüner, M., Abdikan, S., Bilgin, G., Balık Şanlı, F. (2020). Hafif Gradyan Artırma Makineleri ile Tarımsal Ürünlerin Sınıflandırılması. Türk Uzaktan Algılama Ve CBS Dergisi, 1(2), 97-105.