Sentinel-2A MSI Verisinin Makine Öğrenmesi Tabanlı Destek Vektör Makinesi, Rastgele Orman ve En Büyük Olasılık Algoritmalarını Kullanarak Piksel Tabanlı Kontrollü Sınıflandırılmadaki Etkilerinin Araştırılması

Year 2024, Volume: 5 Issue: 2, 138 - 157, 26.09.2024

Nursaç Serda Kaya , Orhan Dengiz

https://doi.org/10.48123/rsgis.1410250

Abstract

Bu araştırma makalesinde, Sinop havzasına yönelik 03.05.2023 tarihli Sentinel-2A MSI verisinin destek vektör makinesi (DVM), rastgele orman (RO) ve en büyük olasılık (EBO) algoritmalarını kullanarak piksel tabanlı kontrollü sınıflandırılması ve daha sonra her bir sınıflandırma algoritmasına ait genel doğruluk değerlerinin belirlenmesi ile her bir arazi kullanımı/arazi örtüsü sınıfı için üretici doğruluğu, kullanıcı doğruluğu, doğruluk, kesinlik, hassasiyet, F1-skoru ve ROC-AUC (İşlem Karakteristik Eğrisi-Eğri Altında Kalan Alan) metriklerine ait değerlerin kıyaslanması amaçlanmıştır. Elde edilen sonuçlar DVM ve RO algoritmalarının EBO yöntemine göre daha yüksek ve benzer genel doğruluk değerleri verdiğini göstermiştir (0.88). Her bir sınıflandırma algoritması için su kütleleri ve mera sınıflarının en yüksek doğruluk, kesinlik, hassasiyet ve F1-skoru değerlerine sahip olduğu gözlemlenmiştir. Ancak düşük AUC değerleri, eğitim setinin oluşturulduğu aşamada bazı arazi kullanımı/arazi örtüsü sınıfları için çok sayıda piksel toplanırken bazı sınıfların ise daha az piksel kullanılarak temsil edilmesi ya da yüksek doğruluk değerlerine rağmen düşük hassasiyet ve kesinlik değerlerinin varlığı gibi durumlar veri setlerindeki dengesizliği ortaya koymuştur.

Keywords

Uzaktan algılama, Destek vektör makinesi, Rastgele orman, En büyük olasılık, Kontrollü sınıflandırma

Investigation of the Effects of Machine Learning-Based Support Vector Machine, Random Forest and Maximum Likelihood Algorithms on Pixel-Based Supervised Classification of Sentinel-2A MSI Data

Abstract

In this research paper, we aimed to compare different machine learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), and Maximum Likelihood for pixel-based supervised classification of Sentinel-2A MSI data from the Sinop basin on May 3, 2023. We evaluated the overall accuracy values and compared various metrics (producer accuracy, user accuracy, accuracy, precision, sensitivity, F1-score, and ROC-AUC (Receiver Operating Characteristic-Area Under Curve) for each land use/land cover class. The results showed that the SVM and RF algorithms gave higher and similar overall accuracy values than the Maximum Likelihood method (0.88). For each classification algorithm, water and pasture classes had the highest accuracy, precision, sensitivity and F1-score values. However, low AUC values, the fact that many pixels were collected for some land use/land cover classes while others were represented by fewer pixels at the stage of training set creation, or the presence of low precision and accuracy values despite high accuracy values revealed the imbalance in the datasets.

Keywords

Remote sensing, Support vector machine, Random forest, Maximum likelihood, Supervised classification

References

• Adam, E., Mutanga, O., Odindi, J., & Abdel-Rahman, E. M. (2014). Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers. International Journal of Remote Sensing, 35(10), 3440-3458.
• Akar, Ö., & Güngör, O. (2012). Classification of multispectral images using Random Forest algorithm. Journal of Geodesy and Geoinformation, 1(2), 105-112.
• Alakus, T. B., & Turkoglu, I. (2020). Comparison of deep learning approaches to predict COVID-19 infection. Chaos, Solitons & Fractals, 140, Article 110120. https://doi.org/10.1016/j.chaos.2020.110120
• Bawa, A., Samanta, S., Himanshu, S. K., Singh, J., Kim, J., Zhang, T., ... & Ale, S. (2023). A support vector machine and image processing based approach for counting open cotton bolls and estimating lint yield from UAV imagery. Smart Agricultural Technology, 3, Article 100140. https://doi.org/10.1016/j.atech.2022.100140
• Billah, M., Islam, A. S., 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, Article 100947. https://doi.org/10.1016/j.rsase.2023.100947
• Braun, A., & Hochschild, V. (2017). A SAR-based index for landscape changes in African savannas. Remote Sensing, 9(4), Article 359. https://doi.org/10.3390/rs9040359
• Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
• Bromová, P., Škoda, P., & Vážný, J. (2014). Classification of spectra of emission line stars using machine learning techniques. International Journal of Automation and Computing, 11(3), 265-273.
• Campbell, J. B., & Wynne, R. H. (2002). Introduction to remote sensing. Guilford Press.
• Campbell, J. B., & Wynne, R. H. (2011). Introduction to remote sensing. Guilford Press.
• Carranza-García, M., García-Gutiérrez, J., & Riquelme, J. C. (2019). A framework for evaluating land use and land cover classification using convolutional neural networks. Remote Sensing, 11(3), Article 274. https://doi.org/10.3390/rs11030274
• Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357.
• Chawla, N. V., Japkowicz, N., & Kotcz, A. (2004). Special issue on learning from imbalanced data sets. ACM SIGKDD explorations newsletter, 6(1), 1-6. https://doi.org/10.1145/1007730.1007733
• Che, T., Xiao, L., & Liou, Y. A. (2014). Changes in glaciers and glacial lakes and the identification of dangerous glacial lakes in the Pumqu River Basin, Xizang (Tibet). Advances in meteorology, 2014, Article ID 903709. http://dx.doi.org/10.1155/2014/903709
• Chen, Z., Wang, L., Wei, A., Gao, J., Lu, Y., & Zhou, J. (2019). Land-use change from arable lands to orchards reduced soil erosion and increased nutrient loss in a small catchment. Science of the Total Environment, 648, 1097-1104.
• Civco, D. L. (1993). Artificial neural networks for land-cover classification and mapping. International journal of geographical information science, 7(2), 173-186.
• Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote sensing of environment, 37(1), 35-46.
• Cunningham, P., Cord, M., & Delany, S. J. (2008). Supervised learning, machine learning techniques for multimedia. Springer-Verlag Berlin, Heidelberg.
• Çölkesen, İ. (2009). Uzaktan algılamada ileri sınıflandırma tekniklerinin karşılaştırılması ve analizi [Yüksek lisans tezi, Gebze Yüksek Teknoloji Enstitüsü]. YÖK Ulusal Tez Merkezi. https://tez.yok.gov.tr/UlusalTezMerkezi
• Dao, P. D., & Liou, Y. A. (2015). Object-based flood mapping and affected rice field estimation with Landsat 8 OLI and MODIS data. Remote Sensing, 7(5), 5077-5097.
• Demir, N., Sonmez, N.K., Akar, T., Ünal, S., (2018). Automated Measurement of Plant Height of Wheat Genotypes Using a DSM Derived from UAV Imagery. Proceedings of the 2nd International Electronic Conference on Remote Sensing 2(7), Article 350. https://doi.org/10.3390/ecrs-2-05163.
• Dietterich, T. G. (2020). An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization. Machine Learning, 40, 139–157.
• Disperati, L., & Virdis, S. G. P. (2015). Assessment of land-use and land-cover changes from 1965 to 2014 in Tam Giang-Cau Hai Lagoon, central Vietnam. Applied Geography, 58, 48-64.
• Dong, R., Zhang, Y., & Zhao, J. (2018). How green are the streets within the sixth ring road of Beijing? An analysis based on tencent street view pictures and the green view index. International journal of environmental research and public health, 15(7), Article 1367. https://doi.org/10.3390/ijerph15071367
• ED Chaves, M., CA Picoli, M., & D. Sanches, I. (2020). Recent applications of Landsat 8/OLI and Sentinel-2/MSI for land use and land cover mapping: A systematic review. Remote Sensing, 12(18), Article 3062. https://doi.org/10.3390/rs12183062
• Eskandari, S., Sarab, S. A. M., Pourhashemi, M., & Ahmadloo, F. (2022). Selection of the best pixel-based algorithm for land cover mapping in Zagros forests of Iran using Sentinel-2A data: A case study in Khuzestan province. In H. R. Pourghasemi (Ed.), Computers in Earth and Environmental Sciences (pp. 181-190). Elsevier.
• Foody, G. M., & Mathur, A. (2004). Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification. Remote Sensing of Environment, 93(1-2), 107-117.
• Gao, Z., Cecati, C., & Ding, S. X. (2015). A survey of fault diagnosis and fault-tolerant techniques—Part I: Fault diagnosis with model-based and signal-based approaches. IEEE transactions on industrial electronics, 62(6), 3757-3767.
• Ghansah, B., Nyamekye, C., Owusu, S., & Agyapong, E. (2021). Mapping flood prone and Hazards Areas in rural landscape using landsat images and random forest classification: Case study of Nasia watershed in Ghana. Cogent Engineering, 8(1), Article 1923384. https://doi.org/10.1080/23311916.2021.1923384
• Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern recognition letters, 27(4), 294-300.
• Goutte, C., & Gaussier, E. (2005). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In D. E. Losada & J. M. Fernández-Luna (Eds.), Advances in Information Retrieval (pp. 345-359). Springer Berlin Heidelberg.
• Gumma, M. K., Thenkabail, P. S., Teluguntla, P. G., Oliphant, A., Xiong, J., Giri, C., ... & Whitbread, A. M. (2020). Agricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud. GIScience & Remote Sensing, 57(3), 302-322.
• Guo, L., Chehata, N., Mallet, C., & Boukir, S. (2011). Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests. ISPRS Journal of Photogrammetry and Remote Sensing, 66(1), 56-66.
• Günlü, A. (2012). Landsat TM uydu görüntüsü yardımıyla bazı meşcere parametreleri (gelişim çağı ve kapalılık) ve arazi kullanım sınıflarının belirlenmesi. Kastamonu University Journal of Forestry Faculty, 12(1), 71-79.
• Halder, S., Das, S., & Basu, S. (2023). Use of support vector machine and cellular automata methods to evaluate impact of irrigation project on LULC. Environmental Monitoring and Assessment, 195(1), Article 3. https://doi.org/10.1007/s10661-022-10588-6
• Hanley, J. A., & McNeil, B. J. (1982). The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143(1), 29-36.
• Hashem, N., & Balakrishnan, P. (2015). Change analysis of land use/land cover and modelling urban growth in Greater Doha, Qatar. Annals of GIS, 21(3), 233-247.
• Huang, C., Davis, L. S., & Townshend, J. R. G. (2002). An assessment of support vector machines for land cover classification. International Journal of remote sensing, 23(4), 725-749.
• Jensen, J. R. (2005). Digital image processing: a remote sensing perspective (3rd ed.). Prentice Hall.
• 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, İ. (2010). Destek vektör makineleri ile uydu görüntülerinin sınıflandırılmasında kernel fonksiyonlarının etkilerinin incelenmesi. Harita Dergisi, 144(7), 73-82.
• Khan, S. H., Hayat, M., Bennamoun, M., Sohel, F. A., & Togneri, R. (2017). Cost-sensitive learning of deep feature representations from imbalanced data. IEEE transactions on neural networks and learning systems, 29(8), 3573-3587.
• Kubat, M., Holte, R. C., & Matwin, S. (1998). Machine learning for the detection of oil spills in satellite radar images. Machine learning, 30, 195-215.
• Kundu, R. (2022, September 13). Confusion Matrix: How To Use It & Interpret Results. V7 Labs. https://www.v7labs.com/blog/confusion-matrix-guide
• Lillesand T., Kiefer R., & Chipman, J. (2004). Remote Sensing and Image Interpretation. John Wiley and Sons.
• Liou, Y. A., Nguyen, A. K., & Li, M. H. (2017). Assessing spatiotemporal eco-environmental vulnerability by Landsat data. Ecological Indicators, 80, 52-65.
• Mather, P., & Tso, B. (2016). Classification methods for remotely sensed data. CRC press.
• 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.
• Merchant, J. W., & Narumalani, S. (2009). Integrating remote sensing and geographic information systems. In T.A. Warner, M. D. Nellis & G. M. Foody (Eds.), The SAGE handbook of remote sensing (pp. 257-268). SAGE Publications.
• Miao, J., & Zhu, W. (2022). Precision–recall curve (PRC) classification trees. Evolutionary intelligence, 15(3), 1545-1569. https://doi.org/10.1007/s12065-021-00565-2
• Moran, E. F., Skole, D. L., & Turner, B. L. (2004). The development of the international land-use and land-cover change (LUCC) research program and its links to NASA’s Land-Cover and Land-Use Change (LCLUC) Initiative. In G. Gutman, A. C. Janetos, C. O. Justice, E. F. Moran, J. F. Mustard, R. R. Rindfuss D. Skole, B. L. Turner & M. A. Cochrane (Eds.), Land Change Science: Observing, Monitoring and Understanding Trajectories of Change on the Earth’s Surface (Vol. 6, pp. 1-15). Springer. https://doi.org/10.1007/978-1-4020-2562-4_1
• Murty, P. S., & Tiwari, H. (2015). Accuracy assessment of land use classification—a case study of Ken Basin. Journal of Civil Engineering and Architecture Research, 2(12), 1199-1206.
• Muslim, M. A. (2020). Support vector machine (svm) optimization using grid search and unigram to improve e-commerce review accuracy. Journal of Soft Computing Exploration, 1(1), 8-15.
• Myung, I. J. (2003). Tutorial on maximum likelihood estimation. Journal of mathematical Psychology, 47(1), 90-100.
• Nakach, F. Z., Zerouaoui, H., & Idri, A. (2022). Random forest based deep hybrid architecture for histopathological breast cancer images classification. In O. Gervasi, B. Burgante, E. M. T. Hendrix, D. Taniar & B. O. Apduhan (Eds.), Computational Science and Its Applications (Vol. 13376, pp. 3-18). Springer.
• Nguyen, A. K., Liou, Y. A., Li, M. H., & Tran, T. A. (2016). Zoning eco-environmental vulnerability for environmental management and protection. Ecological Indicators, 69, 100-117.
• Nguyen, K. A., & Liou, Y. A. (2019). Global mapping of eco-environmental vulnerability from human and nature disturbances. Science of The Total Environment, 664, 995-1004.
• Nguyen, K. A., Liou, Y. A., Tran, H. P., Hoang, P. P., & Nguyen, T. H. (2020). Soil salinity assessment by using near-infrared channel and Vegetation Soil Salinity Index derived from Landsat 8 OLI data: a case study in the Tra Vinh Province, Mekong Delta, Vietnam. Progress in Earth and Planetary Science, 7, 1-16.
• Nitze, I., Schulthess, U., & Asche, H. (2012, May 7-9). Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification [Conference paper]. 4th International conference on Geographic Object-Based Image Analysis (GEOBIA), Rio de Janeiro, Brazil.
• Okwuashi, O., & Ndehedehe, C. E. (2020). Deep support vector machine for hyperspectral image classification. Pattern Recognition, 103, Article 107298. https://doi.org/10.1016/j.patcog.2020.107298
• Orhan, O., Kirtiloğlu, O. S., & Yakar, M. (2020). Konya kapalı havzası obruk envanter bilgi sisteminin oluşturulması. Geomatik, 5(2), 81-90.
• Osenberg, M., Hilger, A., Neumann, M., Wagner, A., Bohn, N., Binder, J. R., ... & Manke, I. (2023). Classification of FIB/SEM-tomography images for highly porous multiphase materials using random forest classifiers. Journal of Power Sources, 570, Article 233030. https://doi.org/10.1016/j.jpowsour.2023.233030
• Öztürk, M. (2022, April 13). Python ile Sınıflandırma Analizleri – Rastgele Orman (Random Forest) Algoritması. https://miracozturk.com/python-ile-siniflandirma-analizleri-rastgele-orman-random-forest-algoritmasi
• Pal, M. (2005). Random forest classifier for remote sensing classification. International journal of remote sensing, 26(1), 217-222.
• Pal, M., & Mather, P. M. (2005). Support vector machines for classification in remote sensing. International journal of remote sensing, 26(5), 1007-1011.
• Pal, S., & Talukdar, S. (2018). Drivers of vulnerability to wetlands in Punarbhaba river basin of India-Bangladesh. Ecological Indicators, 93, 612-626.
• Phiri, D., Simwanda, M., Salekin, S., Nyirenda, V. R., Murayama, Y., & Ranagalage, M. (2020). Sentinel-2 data for land cover/use mapping: A review. Remote Sensing, 12(14), Article 2291. https://doi.org/10.3390/rs12142291
• Pouyan, S., Pourghasemi, H. R., Bordbar, M., Rahmanian, S., & Clague, J. J. (2021). A multi-hazard map-based flooding, gully erosion, forest fires, and earthquakes in Iran. Scientific Reports, 11(1), Article 14889. https://doi.org/10.1038/s41598-021-94266-6
• Rana, V. K., & Suryanarayana, T. M. V. (2020). Performance evaluation of MLE, RF and SVM classification algorithms for watershed scale land use/land cover mapping using sentinel 2 bands. Remote Sensing Applications: Society and Environment, 19, Article 100351. https://doi.org/10.1016/j.rsase.2020.100351
• Rao, R. B., Krishnan, S., & Niculescu, R. S. (2006). Data mining for improved cardiac care. Acm Sigkdd Explorations Newsletter, 8(1), 3-10.
• Rauf, U., Qureshi, W. S., Jabbar, H., Zeb, A., Mirza, A., Alanazi, E., ... & Rashid, N. (2022). A new method for pixel classification for rice variety identification using spectral and time series data from Sentinel-2 satellite imagery. Computers and Electronics in Agriculture, 193, Article 106731. https://doi.org/10.1016/j.compag.2022.106731
• Rimal, B., Rijal, S., & Kunwar, R. (2020). Comparing support vector machines and maximum likelihood classifiers for mapping of urbanization. Journal of the Indian Society of Remote Sensing, 48(1), 71-79.
• 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.
• Saito, T., & Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PloS one, 10(3), Article e0118432. https://doi.org/10.1371/journal.pone.0118432
• Samaniego, L., Bárdossy, A., & Schulz, K. (2008). Supervised classification of remotely sensed imagery using a modified $ k $-NN technique. IEEE Transactions on Geoscience and Remote Sensing, 46(7), 2112-2125.
• Schneider, C. A., Rasband, W. S., & Eliceiri, K. W. (2012). NIH Image to ImageJ: 25 years of image analysis. Nature methods, 9(7), 671-675.
• Selim, S., & Demir, N. (2018). Analysis of landscape patterns and connectivity between tree clusters derived from LIDAR data. Fresenius Environmental Bulletin, 27(5A), 3512-3520.
• SEOS, (2018). Introduction to Remote Sensing. https://seos-project.eu/remotesensing/remotesensing-c00-p02.html
• Sheykhmousa, M., Mahdianpari, M., Ghanbari, H., Mohammadimanesh, F., Ghamisi, P., & Homayouni, S. (2020). Support vector machine versus random forest for remote sensing image classification: A meta-analysis and systematic review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 6308-6325.
• Soyaslan, İ., & Hepdeniz, K. (2016). Coğrafi bilgi sistemleri ve uzaktan algılama kullanılarak Burdur ili arazi kullanımının zamansal değişiminin belirlenmesi. Mehmet Akif Ersoy Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 7(2), 94-101.
• Su, J., Yi, D., Liu, C., Guo, L., & Chen, W. H. (2017). Dimension reduction aided hyperspectral image classification with a small-sized training dataset: experimental comparisons. Sensors, 17(12), Article 2726. https://doi.org/10.3390/s17122726
• Talukdar, S., & Pal, S. (2019). Effects of damming on the hydrological regime of Punarbhaba river basin wetlands. Ecological Engineering, 135, 61-74.
• Talukdar, S., Singha, P., Mahato, S., Praveen, B., & Rahman, A. (2020). Dynamics of ecosystem services (ESs) in response to land use land cover (LU/LC) changes in the lower Gangetic plain of India. Ecological Indicators, 112, Article 106121. https://doi.org/10.1016/j.ecolind.2020.106121
• Tao, D., Tang, X., Li, X., & Wu, X. (2006). Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval. IEEE transactions on pattern analysis and machine intelligence, 28(7), 1088-1099.
• Tehrany, M. S., Pradhan, B., Mansor, S., & Ahmad, N. (2015). Flood susceptibility assessment using GIS-based support vector machine model with different kernel types. Catena, 125, 91-101.
• Tian, S., Zhang, X., Tian, J., & Sun, Q. (2016). Random forest classification of wetland landcovers from multi-sensor data in the arid region of Xinjiang, China. Remote Sensing, 8(11), Article 954. https://doi.org/10.3390/rs8110954
• Tiwari, R., Sharma, R., & Dubey, R. (2022, September). Microstrip Patch Antenna Parameter Optimization Prediction Model using Machine Learning Techniques. International Journal on Recent and Innovation Trends in Computing and Communication, 10(9), 53-59.
• Topaloğlu, R. H., Sertel, E., & Musaoğlu, N. (2016, July 12-19). Assessment of classification accuracies of Sentinel-2 and Landsat-8 data for land cover/use mapping [Conference paper]. The International archives of the photogrammetry, remote sensing and spatial information sciences, Prague, Czech Republic.
• Üstüner, M., Balık Şanlı, F., & Abdikan, S. (2014, 14-17 Ekim). Kırmızı-Kenar Ve Yakın Kızılötesi Bantlarının Ürün Deseni Sınıflandırma Doğruluğuna Olan Etkisinin Araştırılması [Tam metin bildiri]. V. Uzaktan Algılama ve Coğrafi Bilgi Sistemleri Sempozyumu, Türkiye.
• Üstüner, M., Gökdağ, Ü., Bilgin, G., & Şanlı, F. B. (2018, May 2-5). Comparing the classification performances of supervised classifiers with balanced and imbalanced SAR data sets [Conference paper]. 26th Signal Processing and Communications Applications Conference, İzmir, Türkiye.
• Wang, L., Zhang, L., Qi, X., & Yi, Z. (2021). Deep attention-based imbalanced image classification. IEEE transactions on neural networks and learning systems, 33(8), 3320-3330.
• Yan, G., Mas, J. F., Maathuis, B. H. P., Xiangmin, Z., & Van Dijk, P. M. (2006). Comparison of pixel‐based and object‐oriented image classification approaches—a case study in a coal fire area, Wuda, Inner Mongolia, China. International Journal of Remote Sensing, 27(18), 4039-4055.
• Zhang, T. X., Su, J. Y., Liu, C. J., & Chen, W. H. (2019). Potential bands of sentinel-2A satellite for classification problems in precision agriculture. International Journal of Automation and Computing, 16, 16-26.
• Zhang, T., Su, J., Liu, C., Chen, W. H., Liu, H., & Liu, G. (2017, September 7-8). Band selection in sentinel-2 satellite for agriculture applications [Conference paper]. 23rd International Conference on Automation and Computing, Huddersfield, UK.
• Zhang, Y., Ge, T., Tian, W., & Liou, Y. A. (2019). Debris flow susceptibility mapping using machine-learning techniques in Shigatse area, China. Remote Sensing, 11(23), Article 2801. https://doi.org/10.3390/rs11232801