<abstract xmlns="http://www.w3.org/1999/xhtml">Spatially explicit and consistent mapping of forest biomass is one of the key tasks towards full and appropriate accounting of carbon budgets and productivity potentials at different scales. Landsat imagery coupled with terrestrial-based data and processed using modern machine learning techniques is a suitable data source for mapping of forest components such as deadwood. Using relationships between deadwood biomass and growing stock volume, here we indirectly map this ecosystem compartment within the study area in northern Ukraine. Several machine learning techniques were applied: Random Forest (RF) for the land cover and tree species classification task, <italic>k</italic>-Nearest Neighbours (<italic>k</italic>-NN) and Gradient Boosting Machines (GBM) for the deadwood imputation purpose. Land cover (81.9%) and tree species classification (78.9%) were performed with a relatively high level of overall accuracy. Outputs of deadwood biomass mapping using <italic>k</italic>-NN and GBM matched quite well (8.4 ± 2.3 t·ha−1 (17% of the mean) vs. 8.1 ± 1.7 t·ha−1 (16% of the mean), respectively mean ± <italic>SD</italic> deadwood biomass stock), indicating a strong potential of ensemble boosters to predict forest biomass in a spatially explicit manner. The main challenges met in the study were related to the limitations of available ground-based data, thus showing the need for national statistical inventory implications in Ukraine.</abstract>

Spatially explicit and consistent mapping of forest biomass is one of the key tasks towards full and appropriate accounting of carbon budgets and productivity potentials at different scales. Landsat imagery coupled with terrestrial-based data and processed using modern machine learning techniques is a suitable data source for mapping of forest components such as deadwood. Using relationships between deadwood biomass and growing stock volume, here we indirectly map this ecosystem compartment within the study area in northern Ukraine. Several machine learning techniques were applied: Random Forest (RF) for the land cover and tree species classification task, k-Nearest Neighbours (k-NN) and Gradient Boosting Machines (GBM) for the deadwood imputation purpose. Land cover (81.9%) and tree species classification (78.9%) were performed with a relatively high level of overall accuracy. Outputs of deadwood biomass mapping using k-NN and GBM matched quite well (8.4 ± 2.3 t·ha−1 (17% of the mean) vs. 8.1 ± 1.7 t·ha−1 (16% of the mean), respectively mean ± SD deadwood biomass stock), indicating a strong potential of ensemble boosters to predict forest biomass in a spatially explicit manner. The main challenges met in the study were related to the limitations of available ground-based data, thus showing the need for national statistical inventory implications in Ukraine.

An indirect approach to predict deadwood biomass in forests of Ukrainian Polissya using Landsat images and terrestrial data

Department of Forest Mensuration and Forest Management

National University of Life and Environmental Sciences of Ukraine

Forestry Studies

This work is licensed under the Creative Commons Attribution 4.0 International License.

Spatially explicit and consistent mapping of forest biomass is one of the key tasks towards full and appropriate accounting of carbon budgets and productivity...

An indirect approach to predict deadwood biomass in forests of Ukrainian Polissya using Landsat images and terrestrial data

Article Category: Research paper

Publié en ligne: 11 mars 2021

Pages: 107 - 124

Reçu: 16 sept. 2020

Accepté: 16 nov. 2020

DOI: https://doi.org/10.2478/fsmu-2020-0018

Mots clés
deadwood mapping, Random Forest, -Nearest Neighbours, gradient boosting, biomass

© 2020 Maksym Matsala et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

An indirect approach to predict deadwood biomass in forests of Ukrainian Polissya using Landsat images and terrestrial data

Article Category: Research paper

Publié en ligne: 11 mars 2021

Pages: 107 - 124

Reçu: 16 sept. 2020

Accepté: 16 nov. 2020

DOI: https://doi.org/10.2478/fsmu-2020-0018

Mots clésdeadwood mapping, Random Forest, -Nearest Neighbours, gradient boosting, biomass

© 2020 Maksym Matsala et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
deadwood mapping, Random Forest, -Nearest Neighbours, gradient boosting, biomass