Authors

Ha Phong Doan 1* , Thanh Bang Nguyen 1 , Dang Hung Tran 1 , Dao Xuan Hoang 1 , Tran Anh Doan 1

Affiliations

1 Vietnam Institute of Meteorology Hydrology and Climate Change (IMHEN); doanhaphong@gmail.com; bangnt29@gmail.com; danghung2261991@gmail.com; hoangdx81@gmail.com; dtrananh2612@gmail.com 

*Corresponding author: doanhaphong@gmail.com; Tel.: +84–913212325

Abstracts

Decision tree classification algorithms have significant potential in classifying remote sensing data. This article’s approach method using decision tree technology to classify remote sensing images with the representative object as oil spill. First, this paper discusses the algorithmic structure and algorithmic theory of the decision tree. Second, the build of decision tree classification algorithm with 10 branches for oil spill classification using Sentinel 2 image data based on the JavaScript application’s online interface (API) called Code Editor. Decision tree technology has several advantages for remote sensing applications due to their relatively simple, clear and intuitive classification structure.

Keywords

Decision Tree; Classification; Models; Machine Learning; Remote sensing image; Oil Spill.

Cite this paper

Phong, H.D.; Bang, N.T.; Hung, D.T.; Xuan, H.D.; Anh, D.T. Application of machine learning method–decision tree to classification of oil use sentinel 2. VN J. Hydrometeorol. 2021, 8, 16-27.

References

1. Bayramov, E.; Kada, M.; Buchroithner, M. Monitoring oil spill hotspots, contamination probability modelling and assessment of coastal impacts in the Caspian Sea using SENTINEL–1, LANDSAT–8, RADARSAT, ENVISAT and ERS satellite sensors. J. Oper. Oceanogr. 2018, 11, 27–43.

2. Sun, S.; Lu, Y.; Liu, Y.; Wang, M.; Chuanmin Hu, C. Tracking an Oil Tanker Collision and Spilled Oils in the East China Sea Using Multisensor Day  and Night Satellite Imagery. Geophys. Res. Lett. 2018, 45(7), 3212–3220. https://doi.org/10.1002/2018GL077433.

3. Garcia–Pineda, O.; Holmes, J.; Rissing, M.; Jones, R.; Wobus, C.; Jan Svejkovsky, J.; Mark Hess, M. Detection of Oil near Shorelines during the Deepwater Horizon Oil Spill Using Synthetic Aperture Radar (SAR). Remote Sens. 2017, 9, 567. https://doi.org/10.3390/rs9060567.

4. Ivanov, A.Y.; Filimonova, N.A.; Kucheiko, A.Y.; Evtushenko, N.V.; Terleeva, N.V. Oil spills in the Barents Sea based on satellite monitoring using SAR: spatial distribution and main sources. Int. J. Remote Sens.  2017, 39, 4484–4498. https://doi.org/10.1080/01431161.2017.1371869.

5. Nhân, N.H. và cs. Thử nghiệm mô hình OILSAS – công cụ trợ giúp ứng phó sự cố tràn dầu trên vịnh Vân Phong, tỉnh Khánh Hòa. Tuyển tập Nghiên cứu Biển 2014, 20, 19–29.

6. Dương, N.Đ. Ô nhiễm dầu trên vùng biển Việt Nam  và  biển Đông. Đề tài KC.09.22/06–10, 2010.

7. Dương, N.Đ.; Thu, H.L.; Anh, L.V.; Anh, N.K. Ô nhiễm dầu trên vùng biển  việt nam và kế cận. Tạp chí các Khoa học về Trái đất 2013, 35(4), 424–432.

8. Khánh, N.Q. và cs. Ứng dụng công nghệ viễn thám kết hợp với GIS phục vụ giám sát sự cố ô nhiễm dầu ở Việt Nam. Tạp chí Môi trường 2014, 7, 13–15.

9. Song, Y.Y.; Lu, Y. Decision tree methods: applications for classification and prediction. Shanghai Arch Psychiatry 2015, 27, 130–135.

10. Jenhani, I.; Amor, N.B.; Elouedi, Z. Decision trees as possibilistic classifiers.Int. J. Approximate Reasoning 2018, 48, 784–807.

11. Fouad, M.M. A Decision Tree Classification Model for University Admission System. Int. J. Adv. Computer Sci. Appl. 2012, 3, 184–186.

12. Zeng, X.; Yuan, S.; Li, Y.; Zou, Q. Decision Tree Classification Model for Popularity Forecast of Chinese Colleges.  J. Appl. Math. 2014, 675806. https://doi.org/10.1155/2014/675806.

13. Dai, Q.Y.; Zhang, C.P.; Wu, H. Research of Decision Tree Classification Algorithm in Data Mining. Int. J. Database Theory Appl. 2016, 9, 1–8.

14. Patel, H.H.; Prajapati, P. Study and Analysis of Decision Tree Based Classification Algorithms. Int. J. Computer Sci. Eng. 2018, 6(10), 74–78.

15. Zhong, Y. The analysis of cases based on decision tree. Proceeding of the 7th IEEE International Conference on Software Engineering and Service Science (ICSESS), 2016.

16. Lian, H.; Yang, Y. Study on the Test Data Fault Mining Technology Based on Decision Tree. Procedia Comput. Sci. 2019, 154, 232–237.

17. Ivanov, A. Decision Trees for Evaluation of Mathematical Competencies in the Higher Education: A Case Study. Mathematics 2020, 8(5), 748. https://doi.org/10.3390/math8050748.

18. Zimmerman, R.K.; Balasubramani, G.K.; Nowalk, M.P.; Eng, H.; Urbanski, L.; Jackson, M.L.; Jackson, L.A.; McLean, H.Q.; Belongia, E.A.; Monto, A.S.; Malosh, R.E.; Gaglani, M.; Clipper, L.; Flannery, B.; Wisniewski, S.R. Classification and Regression Tree (CART) analysis to predict influenza in primary care patients. BMC Infect. Dis. 2016, 16(1), 503. https://doi.org/10.1186/s12879-016-1839-x.

19. Lemon, S.C.; Roy, J.; Clark, M.A.; Friedmann, P.D.; Rakowski, W. Classification and regression tree analysis in public health: Methodological review and comparison with logistic regression. Ann. Behav. Med. 2003, 26, 172–181.

20. Machuca, C.; Vettore, M.V.; Krasuska, M. et al. Using classification and regression tree modelling to investigate response shift patterns in dentine hypersensitivity. BMC Med. Res. Method. 2017, 17, 120. https://doi.org/10.1186/s12874-017-0396-3.

21. Denisko, D.; Hofman, M.M. Classification and interaction in random forests. PNAS 2018, 115, 1690–1692.

21. Basu, S.; Kumbier, K.; Brown, J.B.; Yu, B. Iterative random forests to discover predictive and stable high–order interactions. PNAS 2018, 115, 1943–1948.

22. Riddick, G. Predicting in vitro drug sensitivity using Random Forests. Bioinf. 2011, 27, 220–224.