Authors

Dong Khuc Thanh 1 , Dung Luong Ngoc 1* , Hue Dang Dieu 1 , Van Anh Tran 2

Affiliations

1 Ha Noi University of Civil Engineering; dungln@huce.edu.vn; dongkt@huce.edu.vn; huedd@huce.edu.vn
2 Hanoi University of Mining and Geology; tranvananh@humg.edu.vn
*Corresponding author: dungln@huce.edu.vn; Tel.: +84–915157676

Abstracts

Land cover classification using remote sensing data plays a crucial role in resource management and environmental monitoring. This study compares the performance of Random Forest (RF) and Extreme Gradient Boosting (XGBoost) in land cover classification in Van Yen District, Yen Bai Province, Vietnam. The input data includes Sentinel-1 radar images, Sentinel-2 optical images, and a total of 7,214 sample points collected for model development using the Google Colab platform. The results indicate that both RF and XGBoost achieve high performance, with overall accuracy (OA) ranging from 94.8% to 96.3% and Kappa coefficients between 0.936 and 0.955. Notably, RF demonstrates greater stability and higher accuracy than XGBoost in both scenarios: using Sentinel-2 alone and combining Sentinel-2 with Sentinel-1. This study provides a scientific basis for selecting appropriate algorithms and data to improve land cover classification efficiency in the region.

Keywords

Land cover; Remote sensing images; Random Forest; Extreme gradient boosting.

Cite this paper

Dong, K.T.; Dung, L.N.; Hue, D.D.; Van, T.A. Comparison of random forest and extreme gradient boosting algorithms in land cover classification in Van Yen district, Yen Bai province, Vietnam. J. Hydro-Meteorol. 2025, 23, 50-59.

References

1. Bai, X.; Sharma, R.C.; Tateishi, R.; Kondoh, A.; Wuliangha, B.; Tana, G. A detailed and high-resolution land use and land cover change analysis over the past 16 years in the Horqin sandy land, Inner Mongolia. Math. Probl. Eng. 2017, 1, 1316505.

2. Gibril, M.B.A.; Bakar, S.A.; Yao, K.; Idrees, M.O.; Pradhan, B. Fusion of RADARSAT-2 and multispectral optical remote sensing data for LULC extraction in a tropical agricultural area. Geocarto Int. 2017, 32, 735–748.

3. Shafizadeh-Moghadam, H.; Khazaei, M.; Alavipanah, S.K.; Weng, Q. Google Earth Engine for large-scale land use and land cover mapping: an object-based classification approach using spectral, textural and topographical factors. GIScience Remote Sens. 2021, 58, 914–928.

4. Bui, D.Q.; et al. Landslide susceptibility prediction mapping with advanced ensemble models: Son La province, Vietnam. Nat. Hazards 2023, 116,  2283–2309.

5. Balha, A.; Mallick, J.; Pandey, S.; Gupta, S.; Singh, C.K. A comparative analysis of different pixel and object-based classification algorithms using multi-source high spatial resolution satellite data for LULC mapping. Earth Sci. Informatics 2021, 14, 2231–2247.

6. Saba, S.B.; Ali, M.; Turab, S.A.; Waseem, M.; Faisal, S. Comparison of pixel, sub-pixel and object-based image analysis techniques for co-seismic landslides detection in seismically active area in Lesser Himalaya, Pakistan. Nat. Hazards 2023, 115, 2383–2398.

7. Zaabar, N.; Niculescu, S.; Kamel, M.M. Application of Convolutional Neural Networks With Object-Based Image Analysis for Land Cover and Land Use Mapping in Coastal Areas: A Case Study in Ain Témouchent, Algeria. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 5177–5189.

8. Adam, H.E.; Csaplovics, E.; Elhaja, M.E. A comparison of pixel-based and object-based approaches for land use land cover classification in semi-arid areas, Sudan. IOP Conf. Ser. Earth Environ. Sci. 2016, 37, 12061.

9. Tran, V.A.; Brovelli, M.A.; Ha, T.K.; Khuc, T.D.; Tran, N.D.; Tran, H.H.; Le, T.N. Land Subsidence Susceptibility Mapping in Ca Mau Province, Vietnam, Using Boosting Models. ISPRS Int. J. Geo-Inf. 2024, 13, 161.

10. Tran, V.A.; Khuc, T.D.; Ha, T.K.; Tran, H.H.; Le, T.N.; Pham, T.T.H; Nguyen, D.; Le, H.A.; Nguyen, Q.D. Land subsidence susceptibility mapping using machine learning in the Google Earth Engine platform. Intelligence of Things: Technologies and Applications, 2023, pp. 55–64.

11. Xu,  S.; Zhao, Q.; Yin, K.; Zhang, F.; Liu, D.; Yang, G. Combining random forest and support vector machines for object-based rural-land-cover classification using high spatial resolution imagery. J. Appl. Remote Sens. 2019, 13, 14521.

12. Hoa, P.T.T.; Quang, V.N.; Nghi, L.T.; Phuong, D.T.N.; Hai, N.M. Research on the potential of applying Random Forest algorithm and Sentinel-2 to classify land cover in Quang Binh province on the Google Colab platform. VN J. Hydrometeorol. 2023, 12, 29–41.

13. Huong, N.T.T.; Trung, D.M.; Erkki, T.; Ronald, E.M. Land Use/land cover mapping using multitemporal Sentinel-2 imagery and four classification methods: A case study from Dak Nong, Vietnam. Remote Sens. 2020, 12, 1367.

14. Linh, D.Q.; Hai, L.T.; Khanh, D.Q. Applying machine learning in classifying and assessing LULC change in Hau Giang province. ISRM VietRock International Workshop. 2024.

15. Le, Q.T.; Dang, K.B.; Giang, T.L.; Tong, T.H.A; Nguyen, V.G.; Nguyen, T.D.L. Deep learning model development for detecting coffee tree changes based on Sentinel-2 imagery in Vietnam. IEEE Access. 2022, 10, 109097–109107.

16. Tran, X.B.; Vambol, V.; Luu, T.D. Assessing forest cover changes in Dak Lak province (Central Highlands of Vietnam) from multi-temporal Landsat data and machine learning techniques. Ecol. Quest. 2024, 35, 1–18.

17. Nguyen, T.P.; Nguyen, P.K.; Nguyen, H.N.; Tran, T.D.; Pham, G.T.; Le, T.H.; Le, D.H.; Nguyen, T.H.; Nguyen, V.B. Evaluation of statistical and machine learning models using satellite data to estimate aboveground biomass: A study in Vietnam tropical forests. Forest Sci. Technol. 2024, 20, 370–382.

18. Khuc, T.D.; Truong, X.Q.; Tran, V.A.; Bui, D.Q.; Ha, H.; Tran, T.H.M.; Pham, T.T.T.; Yordanov, V. Comparison of multi-criteria decision making, statistics, and machine learning models for landslide susceptibility mapping in Van Yen District, Yen Bai Province, Vietnam. Int. J. Geoinformatics 2023, 19, 33–45.

19. Tran, V.A.; Khuc, T.D.; Truong, X.Q.; Nguyen, A.B.; Phi, T.T. Application of potential machine learning models in landslide susceptibility assessment: A case study of Van Yen district, Yen Bai province, Vietnam. Quat. Sci. Adv. 2024, 14, 100181.

20. Arpitha, M.; Ahmed, S.A.; Harishnaika, N. Land use and land cover classification using machine learning algorithms in google earth engine. Earth Sci. Inf. 2023, 16, 3057–3073.

21. Schulz, D.; Yin, H.; Tischbein, B.; Verleysdonk, S.; Adamou, R.; Kumar, N. Land use mapping using Sentinel-1 and Sentinel-2 time series in a heterogeneous landscape in Niger, Sahel. ISPRS J. Photogramm. Remote Sens. 2021, 178, 97–111.

22. Solórzano, J.V.; Mas, J.F.; Gao, Y.; Gallardo-Cruz, J.A. Land use land cover classification with U-net: Advantages of combining sentinel-1 and sentinel-2 imagery. Remote Sens. 2021, 13, 3600.

23. Viovy, N.; Arino, O.; Belward, A.S. The best index slope extraction (Bise): A method for reducing noise in NDVI time-series. Int. J. Remote Sens. 1992, 13, 1585–1590.

24. Zha, Y.; Gao, J.; Ni, S. Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. Int. J. Remote Sens. 2003, 24, 583–594.

25. Nguyen, C.T.; Chidthaisong, A.; Diem, P.K.; Huo, L.Z. A modified bare soil index to identify bare land features during agricultural fallow-period in Southeast Asia using Landsat 8. Land 2021, 10, 231.

26. Noi, P.T.; Kappas, M. Comparison of Random Forest, k-Nearest Neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 Imagery. Sensors 2018, 18, 18.

27. Georganos, S.; Grippa, T.; Vanhuysse, S.; Lennert, M.; Shimoni, M.; Wolff, E. Very high resolution object-based land use–land cover urban classification using extreme gradient boosting. IEEE Geosci. Remote Sens. Lett. 2018, 15, 607–611.

28. Vizzari, M. PlanetScope, Sentinel-2, and Sentinel-1 data integration for object-based land cover classification in Google Earth Engine. Remote Sens. 2022, 14, 2628.

29. Osgouei, P.E.; Kaya, S.; Sertel, E.; Alganci, U. Separating built-up areas from bare land in mediterranean cities using Sentinel-2A imagery. Remote Sens. 2019, 11, 345.

30. Zhou, Y.; Yang, G.; Wang, S.; Wang, L.; Wang, F.; Liu, X. A new index for mapping built-up and bare land areas from Landsat-8 OLI data. Remote Sens. Lett. 2014, 5, 862–871.