(49-4) 17 * << * >> * Russian * English * Content * All Issues

Improving plot-level growing stock volume estimation using machine learning and remote sensing data fusion
I. Mirpulatov 1, A. Kedrov 2, S. Illarionova 1

1 Skolkovo Institute of Science and Technology,
121205, Bolshoy Boulevard, 30, p.1, Skolkovo, Moscow, Russia;
2 Space technologies and services center, Ltd,
614038, str. Lev Lavrov, 14, Perm, Russia

 PDF, 13 MB

DOI: 10.18287/2412-6179-CO-1535

Pages: 682-691.

Full text of article: English language.

Abstract:
Forest characteristics estimation is a vital task for ecological monitoring and forest management. Forest owners make decisions based on timber type and its quality. It usually requires field based observations and measurements that is time- and labor-intensive especially in remote and vast areas. Remote sensing technologies aim at solving the challenge of large area monitoring by rapid data acquisition. To automate the data analysis process, machine learning (ML) algorithms are widely applied, particularly in forestry tasks. As ground truth values for ML models training, forest inventory data are usually leveraged. Commonly it involves individual forest stand measurements that are less precise than sample plots. In this study, we delve into ML-based solution development to create spatial-distributed maps with volume stock using sample plot measurements as reference data. The proposed pipeline includes medium-resolution freely available Sentinel-2 data. The experiments are conducted in the Perm region, Russia, and show a high capacity of ML application for forest volume stock estimation based on multispectral satellite observations. Gradient boosting achieves the highest quality with MAPE equal to 30.5%. In future, the proposed solution can be used by forest owners and integrated in advanced systems for ecological monitoring.

Keywords:
remote sensing of environment, computer vision, machine learning, forestry, timber volume.

Citation:
Mirpulatov I, Kedrov A, Illarionova S. Improving plot-level growing stock volume estimation using machine learning and remote sensing data fusion. Computer Optics 2025; 49(4): 682-691. DOI: 10.18287/2412-6179-CO-1535.

Acknowledgements:
The work was supported by the Russian Science Foundation (Project No. 23-71-01122).

References:
  1. Viljur M-L, Abella SR, Adámek M, et al. The effect of natural disturbances on forest biodiversity: an ecological synthesis. Biol Rev Camb Philos Soc 2022; 97(5): 1930-1947. DOI: 10.1111/brv.12876.
  2. Tinya F, Kovács B, Bidló A, et al. Environmental drivers of forest biodiversity in temperate mixed forests – A multi-taxon approach. Sci Total Environ 2021; 795: 148720. DOI: 10.1016/j.scitotenv.2021.148720.
  3. Illarionova S, Shadrin D, Tregubova P, Ignatiev V, Efimov A, Oseledets I, Burnaev E. A survey of computer vision techniques for forest characterization and carbon monitoring tasks. Remote Sens 2022; 14(22): 5861. DOI: 10.3390/rs14225861.
  4. Guimarães N, Pádua L, Marques P, Silva N, Peres E, Sousa JJ. Forestry remote sensing from unmanned aerial vehicles: A review focusing on the data, processing and potentialities. Remote Sens 2020; 12(6): 1046. DOI: 10.3390/rs12061046.
  5. Illarionova S, Trekin A, Ignatiev V, Oseledets I. Neural-based hierarchical approach for detailed dominant forest species classification by multispectral satellite imagery. IEEE J Sel Top Appl Earth Obs Remote Sens 2020; 14: 1810-1820. DOI: 10.1109/JSTARS.2020.3048372.
  6. Chen L, Letu H, Fan M, et al. An introduction to the Chinese high-resolution Earth observation system: Gaofen-17 civilian satellites. J Remote Sens 2022; 2022: 9769536. DOI: 10.34133/2022/9769536.
  7. Phiri D, Simwanda M, Salekin S, Nyirenda VR, Murayama Y, Ranagalage M. Sentinel-2 data for land cover/use mapping: A review. Remote Sens 2029; 12(14): 2291. DOI: 10.3390/rs12142291.
  8. Zharko VO, Bartalev SA, Sidorenkov VM. Forest growing stock volume estimation using optical remote sensing over snow-covered ground: a case study for Sentinel-2 data and the Russian Southern Taiga region. Remote Sens Lett 2020; 11(7): 677-686. DOI: 10.1080/2150704X.2020.1755473.
  9. Li J, Hong D, Gao L, Yao J, Zheng K, Zhang B, Chanussot J. Deep learning in multimodal remote sensing data fusion: A comprehensive review. Int J Appl Earth Obs Geoinf 2022; 112: 102926. DOI: 10.1016/j.jag.2022.102926.
  10. Mirpulatov I, Illarionova S, Shadrin D, Burnaev E. Pseudo-labeling approach for land cover classification through remote sensing observations with noisy labels. IEEE Access 2023; 11: 82570-82583. DOI: 10.1109/ACCESS.2023.3300967.
  11. Neuville R, Bates JS, Jonard F. Estimating forest structure from UAV-mounted LiDAR point cloud using machine learning. Remote Sens 2021; 13(3): 352. DOI: 10.3390/rs13030352.
  12. Pham TD, Yokoya N, Xia J, Ha NT, Le NN, Nguyen TTT, Dao TH, Vu TTP, Pham TD, Takeuchi W. Comparison of machine learning methods for estimating mangrove above-ground biomass using multiple source remote sensing data in the red river delta biosphere reserve, Vietnam. Remote Sens 2020; 12(8): 1334. DOI: 10.3390/rs12081334.
  13. Ahmadi K, Kalantar B, Saeidi V, Harandi EKG, Janizadeh S, Ueda N. Comparison of machine learning methods for mapping the stand characteristics of temperate forests using multi-spectral Sentinel-2 data. Remote Sens 2020; 12(18): 3019. DOI: 10.3390/rs12183019.
  14. Ghosh SM, Behera MD, Paramanik S. Canopy height estimation using sentinel series images through machine learning models in a mangrove forest. Remote Sens 2020; 12(9): 1519. DOI: 10.3390/rs12091519.
  15. Kislov DE, Korznikov KA, Altman J, Vozmishcheva AS, Krestov PV. Extending deep learning approaches for forest disturbance segmentation on very high-resolution satellite images. Remote Sens Ecol Conserv 2021; 7(3): 355-368. DOI: 10.1002/rse2.194.
  16. Xie Y, Xu Y, Hu C, Lu L, Hu X, Rong Q. Urban forestry detection by deep learning method with GaoFen-2 remote sensing images. J Appl Remote Sens 2022; 16(2): 022206. DOI: 10.1117/1.JRS.16.022206.
  17. Grabska E, Frantz D, Ostapowicz K. Evaluation of machine learning algorithms for forest stand species mapping using Sentinel-2 imagery and environmental data in the Polish Carpathians. Remote Sens Environ 2020; 251: 112103. DOI: 10.1016/j.rse.2020.112103.
  18. Illarionova S, Trekin A, Ignatiev V, Oseledets I. Tree species mapping on Sentinel-2 satellite imagery with weakly supervised classification and object-wise sampling. Forests 2021; 12(10): 1413. DOI: 10.3390/f12101413.
  19. Wan H, Tang Y, Jing L, Li H, Qiu F, Wu W. Tree species classification of forest stands using multisource remote sensing data. Remote Sens 2021; 13(1): 144. DOI: 10.3390/rs13010144.
  20. Hamidi SK, Zenner EK, Bayat M, Fallah A. Analysis of plot-level volume increment models developed from machine learning methods applied to an uneven-aged mixed forest. Ann For Sci 2021; 78: 4. DOI: 10.1007/s13595-020-01011-6.
  21. Iizuka K, Hayakawa YS, Ogura T, Nakata Y, Kosugi Y, Yonehara T. Integration of multi-sensor data to estimate plot-level stem volume using machine learning algorithms–case study of evergreen conifer planted forests in Japan. Remote Sens 2020; 12(10): 1649. DOI: 10.3390/rs12101649.
  22. Chen M, Qiu X, Zeng W, Peng D. Combining sample plot stratification and machine learning algorithms to improve forest aboveground carbon density estimation in northeast China using airborne LiDAR data. Remote Sens 2022; 14(6): 1477. DOI: 10.3390/rs14061477.
  23. Rees WG, Tomaney J, Tutubalina O, Zharko V, Bartalev S. Estimation of boreal forest growing stock volume in russia from Sentinel-2 msi and land cover classification. Remote Sens 2021; 13(21): 4483. DOI: 10.3390/rs13214483.
  24. Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sens Environ 2017; 202: 18-27. DOI: 10.1016/j.rse.2017.06.031.
  25. Traganos D, Poursanidis D, Aggarwal B, Chrysoulakis N, Reinartz P. Estimating satellite-derived bathymetry (SDB) with the google earth engine and Sentinel-2. Remote Sens 2018; 10(6): 859. DOI: 10.3390/rs10060859.
  26. Matsushita B, Yang W, Chen J, Onda Y, Qiu G. Sensitivity of the enhanced vegetation index (EVI) and normalized difference vegetation index (NDVI) to topographic effects: a case study in high-density cypress forest. Sensors 2007; 7(11): 2636-2651. DOI: 10.3390/s7112636.
  27. Howat IM, Porter C, Smith BE, Noh M-J, Morin P. The reference elevation model of Antarctica. The Cryosphere 2019; 13(2): 665-674. DOI: 10.5194/tc-13-665-2019.
  28. Smolina A, Illarionova S, Shadrin D, Kedrov A, Burnaev E. Forest age estimation in northern Arkhangelsk region based on machine learning pipeline on Sentinel-2 and auxiliary data. Sci Rep 2023; 13: 22167. DOI: 10.1038/s41598-023-49207-w.
  29. Breiman L. Random forests. Mach Learn 2001; 45: 5-32. DOI: 10.1023/A:1010933404324.
  30. Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Statist 2001; 29(5): 1189-1232. DOI: 10.1214/aos/1013203451.
  31. Pedregosa F, Varoquaux G, Gramfort A, Michel V. Scikit-learn: machine learning in Python. J Mach Learn Res 2011; 12: 2825-2830.
  32. Arik SÖ, Pfister T. TabNet: Attentive interpretable tabular learning. Proc AAAI Conf on Artificial Intelligence 2021; 35(8): 6679-6687. DOI: 10.1609/aaai.v35i8.16826.
  33. Paszke A, Gross S, Massa F, et al. PyTorch: An imperative style, high-performance deep learning library. Proceedings of the 33rd Int Conf on Neural Information Processing Systems 2019: 8026-8037.
  34. Illarionova S, Shadrin D, Ignatiev V, Shayakhmetov S, Trekin A, Oseledets I. Estimation of the canopy height model from multispectral satellite imagery with convolutional neural networks. IEEE Access 2022; 10: 34116-34132. DOI: 10.1109/ACCESS.2022.3161568.
  35. Hu Y, Xu X, Wu F, Sun Z, Xia H, Meng Q, Huang W, Zhou H, Gao J, Li W, Peng D, Xiao X. Estimating forest stock volume in Hunan Province, China, by integrating in situ plot data, Sentinel-2 images, and linear and machine learning regression models. Remote Sens 2020; 12(1): 186. DOI: 10.3390/rs12010186.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20