Proceedings of the Environmental Science and Technology International Conference (ESTIC 2021)

<Previous Article In Volume
Next Article In Volume>

Application of Random Forest Approach to Biomass Estimation Using Remotely Sensed Data

Authors
Nyamjargal Erdenebaatar1, *, Batbileg Bayaraa2, Amarsaikhan Damdinsuren1
1Institute of Geography and Geoecology, Mongolian Academy of Sciences, Ulaanbaatar, Mongolia
2Mongolian University of Life Science, Ulaanbaatar, Mongolia
*Corresponding author. Email: nyamjargale@mas.ac.mn
Corresponding Author
Nyamjargal Erdenebaatar
Available Online 1 November 2021.
DOI
10.2991/aer.k.211029.020How to use a DOI?
Keywords
Biomass; RF classification; Landsat; QuickBird
Abstract

The aim of this study is to investigate the application of RS-based vegetation indices to biomass estimation, perform a random forest (RF) classification for estimating biomass and compare the performance of RF method for high resolution and medium resolution images. As data sources, orthorectified QuickBird (QB) and Landsat 8 images acquired over Bornuur soum of Tov province, Mongolia are used. Firstly, the spectral indices were calculated for both images and the correlation between field measured biomass and spectral indices was estimated using partial least square regression. Then, the RF classification was performed to estimate the biomass. For all vegetation indices, VARVI yielded the highest correlation coefficient value for the Landsat data, while SR was considered the highest correlated index for the QB data. For both imageries, G-RVI and VARI were the best vegetation indices to explain the ground biomass. The relationship between the measured biomass and QB derived vegetation indices resulted in an r2 value of 0.337 and RMSE=83.435 g/m2, while the vegetation indices from Landsat performed relatively well in predicting the groundcover with a r2 value of 0.617 and RMSE=50.881 g/m2. This could be explained by the fact that high spatial resolution images have lots of shadows from trees and terrain, resulting in errors for AGB estimation.

Copyright
© 2021 The Authors. Published by Atlantis Press International B.V.
Open Access
This is an open access article under the CC BY-NC license.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the Environmental Science and Technology International Conference (ESTIC 2021)
Series
Advances in Engineering Research
Publication Date
1 November 2021
ISBN
10.2991/aer.k.211029.020
ISSN
2352-5401
DOI
10.2991/aer.k.211029.020How to use a DOI?
Copyright
© 2021 The Authors. Published by Atlantis Press International B.V.
Open Access
This is an open access article under the CC BY-NC license.

Cite this article

risenwbib
TY  - CONF
AU  - Nyamjargal Erdenebaatar
AU  - Batbileg Bayaraa
AU  - Amarsaikhan Damdinsuren
PY  - 2021
DA  - 2021/11/01
TI  - Application of Random Forest Approach to Biomass Estimation Using Remotely Sensed Data
BT  - Proceedings of the Environmental Science and Technology International Conference (ESTIC 2021)
PB  - Atlantis Press
SP  - 109
EP  - 115
SN  - 2352-5401
UR  - https://doi.org/10.2991/aer.k.211029.020
DO  - 10.2991/aer.k.211029.020
ID  - Erdenebaatar2021
ER  -