@article{10.11648/j.acm.20261505.16,
  author = {Fred Junior Onyango and Charity Wamwea and Amos Kipkorir Langat},
  title = {Estimating and Mapping Forest Carbon Sequestration in the Mau Forest Complex Using Sentinel-2 Remote Sensing and Machine Learning},
  journal = {Applied and Computational Mathematics},
  volume = {15},
  number = {5},
  pages = {206-219},
  doi = {10.11648/j.acm.20261505.16},
  url = {https://doi.org/10.11648/j.acm.20261505.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.acm.20261505.16},
  abstract = {Accurate forest-carbon estimates are essential for climate mitigation, restoration planning and monitoring, reporting and verification, yet conventional field inventories are expensive and spatially discontinuous. This study evaluated whether freely available Sentinel-2 imagery combined with statistical and machine-learning models can estimate and map forest carbon across the Mau Forest Complex, Kenya. Existing geo-referenced forest inventory data comprising 3,907 measured trees were linked to seven Sentinel-2 vegetation indices: Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Soil-Adjusted Vegetation Index (SAVI), Normalized Difference Moisture Index (NDMI), Normalized Burn Ratio (NBR), red-edge Chlorophyll Index (CIre) and Red-Edge Normalized Difference Vegetation Index (RENDVI). Above-ground biomass was estimated using a pan-tropical allometric equation; below-ground biomass, carbon stock and CO2 equivalent were subsequently derived using IPCC factors. Ordinary linear regression, a linear mixed-effects model, Random Forest and Extreme Gradient Boosting (XGBoost) were compared using a 70:30 training-test split, with five-fold cross-validation for machine-learning hyperparameter tuning. All vegetation indices were positively associated with above-ground biomass (p2=0.473, RMSE=0.424, MAE=0.327), followed by Random Forest (R2=0.468, RMSE=0.426, MAE=0.329), the mixed-effects model (R2=0.454, RMSE=0.431, MAE=0.333) and linear regression (R2=0.436, RMSE=0.438, MAE=0.340). XGBoost reduced RMSE by 3.3% relative to the linear baseline. Residual spatial autocorrelation was negligible (Moran’s I=0.059). Spatial prediction identified higher carbon densities in western and south-western portions of the Complex and lower values in more disturbed eastern blocks. The study contributes a reproducible, low-cost benchmark of linear, mixed-effects and ensemble models for spatial forest-carbon monitoring in a heterogeneous African montane forest; the modest gain from nonlinear models shows that optical indices alone limit accuracy, so future improvements will likely require structural information from radar or LiDAR.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Estimating and Mapping Forest Carbon Sequestration in the Mau Forest Complex Using Sentinel-2 Remote Sensing and Machine Learning
AU  - Fred Junior Onyango
AU  - Charity Wamwea
AU  - Amos Kipkorir Langat
Y1  - 2026/10/23
PY  - 2026
N1  - https://doi.org/10.11648/j.acm.20261505.16
DO  - 10.11648/j.acm.20261505.16
T2  - Applied and Computational Mathematics
JF  - Applied and Computational Mathematics
JO  - Applied and Computational Mathematics
SP  - 206
EP  - 219
PB  - Science Publishing Group
SN  - 2328-5613
UR  - https://doi.org/10.11648/j.acm.20261505.16
AB  - Accurate forest-carbon estimates are essential for climate mitigation, restoration planning and monitoring, reporting and verification, yet conventional field inventories are expensive and spatially discontinuous. This study evaluated whether freely available Sentinel-2 imagery combined with statistical and machine-learning models can estimate and map forest carbon across the Mau Forest Complex, Kenya. Existing geo-referenced forest inventory data comprising 3,907 measured trees were linked to seven Sentinel-2 vegetation indices: Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Soil-Adjusted Vegetation Index (SAVI), Normalized Difference Moisture Index (NDMI), Normalized Burn Ratio (NBR), red-edge Chlorophyll Index (CIre) and Red-Edge Normalized Difference Vegetation Index (RENDVI). Above-ground biomass was estimated using a pan-tropical allometric equation; below-ground biomass, carbon stock and CO2 equivalent were subsequently derived using IPCC factors. Ordinary linear regression, a linear mixed-effects model, Random Forest and Extreme Gradient Boosting (XGBoost) were compared using a 70:30 training-test split, with five-fold cross-validation for machine-learning hyperparameter tuning. All vegetation indices were positively associated with above-ground biomass (p2=0.473, RMSE=0.424, MAE=0.327), followed by Random Forest (R2=0.468, RMSE=0.426, MAE=0.329), the mixed-effects model (R2=0.454, RMSE=0.431, MAE=0.333) and linear regression (R2=0.436, RMSE=0.438, MAE=0.340). XGBoost reduced RMSE by 3.3% relative to the linear baseline. Residual spatial autocorrelation was negligible (Moran’s I=0.059). Spatial prediction identified higher carbon densities in western and south-western portions of the Complex and lower values in more disturbed eastern blocks. The study contributes a reproducible, low-cost benchmark of linear, mixed-effects and ensemble models for spatial forest-carbon monitoring in a heterogeneous African montane forest; the modest gain from nonlinear models shows that optical indices alone limit accuracy, so future improvements will likely require structural information from radar or LiDAR.
VL  - 15
IS  - 5
ER  - 

Copy | Download