Claim · model-written summary
Chave’s model performed best among traditional methods.
AcaciaNot reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingDirectionValueQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Chave’s allometric model was the best-performing traditional method”
t0“six Acacia species”
Title
Samuel Irungu Kigotho; Kennedy Senagi; John Olukuru; et al. Machine Learning with Applications 2026. doi:10.1016/j.mlwa.2026.100880
Other claims from this paper (7)
- Method / resource Machine learning models generally outperformed allometric approaches for biomass estimation.
- Method / resource Gradient Boosting performed best for Acacia drepanolobium with R² of 0.989.
- Method / resource XGBoost had the highest accuracy for Acacia nilotica with R² of 0.990.
- Method / resource Random Forest had strong and stable performance.
- Method / resource Support Vector Regression had comparatively lower and less consistent accuracy.
- Method / resource Diameter at breast height was the most influential predictor in all machine learning models.
- Method / resource Tree height provided complementary explanatory power.