logo

Modeling Volume, Basal Area and Tree Density in the Kalala Forest in Northern Iran Using Sentinel-2 Satellite Data and Random Forest Algorithm [Arabic]

2023-11-27 | Volume 1 Issue 3 - Volume 1 | Research Articles | Hassan Ali

Abstract

Gathering accurate data on forest resources is one of the most important steps in sustainable planning for these forests. Remote sensing techniques have been widely used in forest management by predicting various forest parameters such as volume, tree density and basal area. This research was conducted in Kalala Forest in northern Iran, and field data were collected by cluster sampling method. 105 samples were inventoried with an area of 400 square meters per sample. At the level of each sample, diameter at breast height and tree height were measured. The volume, tree density, and basal area per hectare of the studied samples were calculated. The values of vegetation indices at the studied sample sites were extracted through the Sentinel-2 satellite image. The relationship between the studied parameters and vegetation indices was modeled through the use of the Random Forest algorithm. This research aims to investigate the ability of the Sentinel-2 satellite to estimate volume, basal area and tree density in the study area using the Random Forest algorithm. Volume modeling results showed that the coefficient of determination (R2) was equal to 0.88, and the percentage root mean square error (%RMSE) was equal to 21.01%. While the results of basal area modeling showed that the coefficient of determination was 0.88, and the percentage of root mean square error was 20.14%. The results of tree density modeling showed that the coefficient of determination was 0.89, and the percentage of root mean square error was 19.22%. The results also showed that the use of the Sentinel-2 satellite and the Random Forest algorithm in modeling gave positive and acceptable results.

Keywords : Volume, Basal Area, Tree Density, Random Forest Algorithm, Sentinel-2 Satellite.
References :
  1. Ali H, Mohammadi J, and Shataee Jouibary S. Allometric Models and Biomass Conversion and Expansion Factors to Predict Total Tree-level Aboveground Biomass for Three Conifers Species in Iran. Forest Science, 2023, p.fxad013.
  2. Mohammadi J, Shataee S, and Babanezhad M. Estimation of forest stand volume, tree density and biodiversity using Landsat ETM+ Data, comparison of linear and regression tree analyses. Procedia Environmental Sciences, 2011, 7, pp.299-304.
  3. Wulder M.A, White J.C, Nelson R.F, Næsset E, Ørka H.O, Coops N.C, Hilker T, Bater C.W, and Gobakken T. Lidar sampling for large-area forest characterization: A review. Remote sensing of environment, 2012, 121, pp.196-209.
  4. Zhu X, and Liu D. Improving Forest aboveground biomass estimation using seasonal Landsat NDVI time-series. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 102, 222-231.
  5. Immitzer M, Vuolo F, and Atzberger C. First experience with Sentinel-2 data for crop and tree species classifications in central Europe. Remote Sensing, 2016, 8(3) ,166.
  6. Filho M.G, Kuplich T.M, De Quadros F. Estimating natural grassland biomass by vegetation indices using Sentinel 2 remote sensing data. International Journal of Remote Sensing, 2019, 8, 2861–2876.
  7. Mohammadi J, Shataee S, Namiranian M, and Næsset E. Modeling biophysical properties of broad-leaved stands in the hyrcanian forests of Iran using fused airborne laser scanner data and ultraCam-D images. International journal of applied earth observation and geoinformation, 2017, 61, pp.32-45.
  8. Grimm R, Behrens T, Märker M, and Elsenbeer H. Soil organic carbon concentrations and stocks on Barro Colorado Island—Digital soil mapping using Random Forests analysis. Geoderma, 2008, 146(1-2), pp.102-113.
  9. Shataee S, Kalbi S, Fallah A, and Pelz D. Forest attribute imputation using machine-learning methods and ASTER data: comparison of k-NN, SVR and random forest regression algorithms. International journal of remote sensing, 2012, 33(19), pp.6254-6280.
  10. Esteban J, McRoberts R.E, Fernández-Landa A, Tomé J.L, and Nӕsset E. Estimating forest volume and biomass and their changes using random forests and remotely sensed data. Remote Sensing, 2019,11(16), p.1944.
  11. Bolat F, Bulut S, Günlü A, Ercanlı İ and Şenyurt M. Regression kriging to improve basal area and growing stock volume estimation based on remotely sensed data, terrain indices and forest inventory of black pine forests. New Zealand Journal of Forestry Science, 2020, 50.
  12. Astola H, Seitsonen L, Halme E, Molinier M, and Lönnqvist A. Deep neural networks with transfer learning for forest variable estimation using sentinel-2 imagery in boreal forest. Remote Sensing, 2021, 13(12), p.2392.
  13. Lahssini K, Teste F, Dayal K.R, Durrieu S, Ienco D, and Monnet J.M. Combining LiDAR metrics and sentinel-2 imagery to estimate basal area and wood volume in complex forest environment via neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15, pp.4337-4348.
  14. Hallaj M.H.S, Rostaghi A.A. Study on growth performance of Turkish pine (Case study: Arabdagh afforestation plan, Golestan province). Iranian J. for. P. Res. 2011, 3, 201-212.
  15. Ali H, Mohamadi J, and Shataee S. Determination of form factor for three species (Pinus brutia, Pinus pinea and Cupressus sempervirens) in the Arabdagh reforests, Golestan province. Journal of Wood and Forest Science and Technology, 2020, 27(1), pp.31-44.
  16. Belgiu M, and Drăguţ, L. Random forest in remote sensing: A review of applications and future directions. ISPRS journal of photogrammetry and remote sensing, 2016,114, pp.24-31.
  17. Dang A.T.N, Nandy S, Srinet R, Luong N.V, Ghosh S and Kumar A.S. Forest aboveground biomass estimation using machine learning regression algorithm in Yok Don National Park, Vietnam. Ecological Informatics, 2019,50, pp.24-32.
  18. Majasalmi T, and Rautiainen M. The potential of Sentinel-2 data for estimating biophysical variables in a boreal forest: A simulation study. Remote Sensing Letters, 7(5), pp.427-436.
  19. Hu Y, Xu X, Wu F, Sun Z, Xia H, Meng Q, Huang W, Zhou H, Gao J, Li W, and Peng D. 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 Sensing, 2020, 12(1), p.186.
  20. Chrysafis I, Mallinis G, Tsakiri M and Patias P. Evaluation of single-date and multi-seasonal spatial and spectral information of Sentinel-2 imagery to assess growing stock volume of a Mediterranean forest. International Journal of Applied Earth Observation and Geoinformation, 2019, 77, pp.1-14.
  21. Bulut S, Günlü A and Çakır G. Modelling some stand parameters using Landsat 8 OLI and Sentinel-2 satellite images by machine learning techniques: a case study in Türkiye. Geocarto International, 2023,38(1), p.2158238.
  22. Bhattarai R, Rahimzadeh-Bajgiran P, Weiskittel A, Homayouni S, Gara T.W, and Hanavan R.P. Estimating species-specific leaf area index and basal area using optical and SAR remote sensing data in Acadian mixed spruce-fir forests, USA. International Journal of Applied Earth Observation and Geoinformation, 2022,108, p.102727.
  23. Wang S, Zhang X, Hassan M.A, Chen Q, Li C, Tang Z, and Wang Y. QuickBird image-based estimation of tree stand density using local maxima filtering method: A case study in a Beijing forest. Plos one, 2018, 13(12), p.e0208256.
  24. Mascaro, J., Detto, M., Asner, G.P. and Muller-Landau, H.C., 2011. Evaluating uncertainty in mapping forest carbon with airborne LiDAR. Remote Sensing of Environment, 2016, 115(12), pp.3770-3774.
  25. Næsset E, Bollandsås O.M, Gobakken T, Solberg S, and McRoberts R.E. The effects of field plot size on model-assisted estimation of aboveground biomass change using multitemporal interferometric SAR and airborne laser scanning data. Remote Sensing of Environment, 2015, 168, pp.252-264.
  26. Ghosh S.M, Behera M.D. Aboveground Biomass Estimation Using Multi-Sensor Data Synergy and Machine Learning Algorithms in a Dense Tropical Forest. Appl. Geogr. 2018, 96, 29–40.

(ISSN - Online)

2959-8591

Article Information :

  1. Submitted :17/09/2023
  2. Accepted :02/11/2023

Download

  1. Downlaod Article as Pdf

DOI

  1. 10.5281/zenodo.10210570

Correspondence

  1. hso414516@gmail.com

Cited As

  1. 1. Ali H. Modeling volume, basal area and tree density in the study area using Sentinel-2 satellite data and Random Forest algorithm. Syrian Journal for Science and Innovation. 2023Nov27;1(3).

Current Issue