CUBIST-BASED ESTIMATION OF ABOVEGROUND BIOMASS IN EVERGREEN BROADLEAF FORESTS USING INTEGRATED SENTINEL-1, SENTINEL-2 AND FIELD DATA IN NAM LAU, SON LA PROVINCE
DOI:
https://doi.org/10.70169/VJFS.1338Keywords:
Aboveground biomass, cubist model, evergreen broadleaf forest, remote sensing, Sentinel-2, vegetation indicesAbstract
Evergreen broadleaf forests (EBFs) play an important role in climate regulation, preventing landslides, maintaining biodiversity, and sequestering carbon. Above-ground biomass (AGB) is a fundamental indicator for assessing forest carbon stocks. However, field-based AGB inventories are often time-consuming and costly, making them difficult to implement over large areas. This study developed a Cubist-based AGB estimation model for EBFs in Nam Lau Commune, Sơn La Province, Vietnam. Three groups of independent variables were considered, vegetation indices and individual spectral bands derived from Sentinel-2 data; Sentinel-1 variables, including backscatter values, polarization indices, and Radar texture features; and variables derived from a digital elevation model (DEM). The observed AGB values ranged from 38.81 to 213.99 Mg/ha. Model reliability was evaluated using the coefficient of determination (R²), root mean square error (RMSE), mean absolute error (MAE), and systematic bias (Bias). Model evaluation identified MH1, developed using the NDREn vegetation index, the VV_VH polarization feature, and topographic variables, as a reliable model. MH1 was subsequently used to generate AGB and AGC maps of EBFs, with estimated AGB ranging from 9.77 to 250.88 Mg/ha and AGC ranging from 4.59 to 116.76 Mg/ha. The model achieved an R² of 0.835 on the independent validation dataset and an R² of 0.713 under 10-fold cross-validation. Its lowest validation RMSE was 14.94 Mg/ha, with an MAE of 12.15 Mg/ha and a validation bias of -1.61%. MH1 is recommended for mapping the spatial distribution of AGB in evergreen broadleaf forests in Nam Lau Commune and in other areas with similar topographic characteristics.
References
1. Boegh, E., Soegaard, H., Broge, N., Hasager, C. B., Jensen, N. O., Schelde, K., Thomsen, A., 2002. Airborne multispectral data for quantifying leaf area index, nitrogen concentration, and photosynthetic efficiency in agriculture. Remote Sensing of Environment, 81(2–3), 179–193. DOI: 10.1016/S0034-4257(01)00342-X
2. Dang, A. T. N., Nandy, S., Srinet, R., Nguyen, V. L., Ghosh, S., Senthil Kumar, A., 2019. Forest aboveground biomass estimation using machine learning regression algorithm in Yok Don National Park, Vietnam. Ecological Informatics, 50, 24–32. DOI: 10.1016/j.ecoinf.2018.12.010
3. Dang, H. N., Ba, D. D., Trung, D. N., Viet, H. N. H., 2022. A novel method for estimating biomass and carbon sequestration in tropical rainforest areas based on remote sensing imagery: A case study in the Kon Ha Nung Plateau, Vietnam. Sustainability, 14(24), 16857. DOI:10.3390/su142416857
4. Delegido, J., Verrelst, J., Alonso, L., Moreno, J., 2011. Evaluation of Sentinel-2 red-edge bands for empirical Estimation of green LAI and chlorophyll content. Sensors, 11(7), 7063–7081. https://doi.org/10.3390/s110707063
5. Delwart, S. (2015, July 24). Sentinel-2 user handbook [User Handbook]. ESA.
6. Fan, X., He, G., Zhang, W., Long, T., Zhang, X., Wang, G., Sun, G., Zhou, H., Shang, Z., Tian, D., Li, X., Song, X., 2022. Sentinel-2 images based modeling of grassland above-ground biomass using random forest algorithm: A case study on the tibetan plateau. Remote Sensing, 14(21), 5321. DOI:10.3390/rs14215321
7. Fang, G., Yu, H., Fang, L., Zheng, X., 2023. Synergistic use of Sentinel-1 and Sentinel-2 based on different preprocessing for predicting forest aboveground biomass. Forests, 14(8), 1615. DOI:10.3390/f14081615
8. Feroz, S. M., Enamul Kabir, Md., Hagihara, A., 2015. Species composition, diversity and stratification in subtropical evergreen broadleaf forests along a latitudinal thermal gradient in the Ryukyu Archipelago, Japan. Global Ecology and Conservation, 4, 63–72. DOI:10.1016/j.gecco.2015.05.002
9. Gao, B., 1996. NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing of Environment, 58(3), 257–266. DOI:10.1016/S0034-4257(96)00067-3
10. Georgopoulos, N., Sotiropoulos, C., Stefanidou, A., Gitas, I. Z., 2022. Total stem biomass estimation using Sentinel-1 and -2 Data in a dense coniferous forest of complex structure and terrain. Forests, 13(12), 2157. DOI:10.3390/f13122157
11. Gitelson, A. A., 2004. Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation. Journal of Plant Physiology, 161(2), 165–173. DOI:10.1078/0176-1617-01176
12. Gitelson, A., Merzlyak, M. N., 1994. Spectral reflectance changes associated with Autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation. Journal of Plant Physiology, 143(3), 286–292. DOI:10.1016/S0176-1617(11)81633-0
13. Global Forest Resources Assessment 2020., 2020. FAO. DOI:10.4060/ca9825en
14. Huete, A., Didan, K., Miura, T., Rodriguez, E. P., Gao, X., Ferreira, L. G., 2002. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment, 83(1–2), 195–213. DOI:10.1016/S0034-4257(02)00096-2
15. Huete, A. R., 1988. A soil-adjusted vegetation index (SAVI). Remote Sensing of Environment, 25(3), 295–309. DOI:10.1016/0034-4257(88)90106-X
16. Hunt Jr, E., Rock, B., 1989. Detection of changes in leaf water content using Near- and Middle-Infrared reflectances☆. Remote Sensing of Environment, 30(1), 43–54. DOI:10.1016/0034-4257(89)90046-1
17. Latterini, F., Camarretta, N., Watt, M. S., 2025. Remote sensing for planning harvesting operations and monitoring their effects on the forest ecosystem: State of the art and future perspectives. Forest Ecology and Management, 597, 123175. DOI:10.1016/j.foreco.2025.123175
18. Levy, P. E., Cannell, M. G. R., Friend, A. D., 2004. Modelling the impact of future changes in climate, CO2 concentration and land use on natural ecosystems and the terrestrial carbon sink. Global Environmental Change, 14(1), 21–30. DOI:10.1016/j.gloenvcha.2003.10.005
19. Lima, C. D. S., Soares, A. J. T., Nogueira, B. D. S., Vian, A. L., Carvalho, I. R., Bredemeier, C., 2026. Methodology for Selecting Stable UAV-Based Vegetation Indices for Prediction of Agronomic Variables in Maize Using a Multispectral Sensor. Plants, 15(12), 1782. DOI:10.3390/plants15121782
20. Ma, T., Zhang, C., Ji, L., Zuo, Z., Beckline, M., Hu, Y., Li, X., Xiao, X., 2024. Development of forest aboveground biomass estimation, its problems and future solutions: A review. Ecological Indicators, 159, 111653. DOI:10.1016/j.ecolind.2024.111653
21. Muhe, S., Argaw, M., 2022. Estimation of above-ground biomass in tropical afro-montane forest using Sentinel-2 derived indices. Environmental Systems Research, 11(1), 5. DOI:10.1186/s40068-022-00250-y
22. Ngo, D. T., Dinh, T. V. A., Ngo, D. T., Nguyen, H. D., Pham, T. V., Dang, N. T., 2026. Estimation of the tree aboveground biomass and carbon stock of the Bai Tu Long National Park forest ecosystem from Sentinel-2 images via regression models. Discover Sustainability, 7(1), 277. DOI:10.1007/s43621-026-02667-2
23. Nguyen, T. D., Kappas, M., 2020. Estimating the aboveground biomass of an evergreen broadleaf forest in Xuan Lien Nature Reserve, Thanh Hoa, Vietnam, Using SPOT-6 data and the random forest algorithm. International Journal of Forestry Research, 2020, 1–13. DOI:10.1155/2020/4216160
24. Nhung Đ. T., Hùng N. Đ., Hải P. N., Phương Đ. Đ. L., My N. T. D., Mạnh P. V., 2023. Ước tính sinh khối trên mặt đất bằng viễn thám tích hợp và thuật toán học máy: Nghiên cứu điểm tại Khu dự trữ sinh quyển miền Tây Nghệ An, Việt Nam. Tạp chí Khoa học và Công nghệ Lâm nghiệp, 12(4), 81–92. DOI:10.55250/jo.vnuf.12.4.2023.081-092
25. Quinlan, R. J., 1992. Learning with continuous classes. AI ’92, 343–348.
26. Tan, Z.-H., Zhang, Y.-P., Schaefer, D., Yu, G.-R., Liang, N., Song, Q.-H., 2011. An old-growth subtropical Asian evergreen forest as a large carbon sink. Atmospheric Environment, 45(8), 1548–1554. DOI:10.1016/j.atmosenv.2010.12.041
27. TCVN 14287:2024. 2024. Phương pháp xác định sinh khối và trữ lượng các-bon rừng (Tiêu chuẩn Việt Nam TCVN 14287:2024). Bộ Khoa học và Công nghệ.
28. Vinh N. Q., Hải N. T. T., Hải P. N., Anh P. T., Đức N. H., 2025. Ước tính sinh khối trên mặt đất trong rừng kín lá rộng thường xanh bằng viễn thám UAV‑RGB: Nghiên cứu điểm tại xã A Lưới 4, thành phố Huế. Tạp chí Khoa học và Công nghệ Lâm nghiệp, 15(3), 117–126. DOI: 10.55250/Jo.vnuf.15.3.2026.117-126
29. Xue, J., Su, B., 2017. Significant remote sensing vegetation indices: A review of developments and applications. Journal of Sensors, 2017, 1–17. DOI:10.1155/2017/1353691
30. Yan, X., Li, J., Smith, A.R., Yang, D., Ma, T., Su, Y., Shao, J., 2023. Evaluation of machine learning methods and multi-source remote sensing data combinations to construct forest above-ground biomass models, International Journal of Digital Earth, 16:2, 4471-4491, DOI: 10.1080/17538947.2023.2270459
31. Zoltán, L., Tanács, E., Standovár, T., 2023. Validation and limitations of large-scale forest condition indicators – An example from Hungary. Ecological Indicators, 154, 110539. DOI:10.1016/j.ecolind.2023.110539
