Knowledge-guided machine learning for predicting the carbon sequestration potential of natural forests in Heilongjiang Province
Research paper
Key message
Integrating ecological process knowledge into machine learning substantially improves the robustness and extrapolation of forest carbon stock predictions. The knowledge-guided model maintained strong predictive performance over 10–15-year horizons, when conventional machine-learning performance declined markedly, providing a promising framework for long-term forest carbon assessment under climate change.
Keywords
Forest carbon stock; Long-term extrapolation; XGBoost; CO2 fertilization effect; Process-based modeling; Climate change scenarios; Forest biomass density; Ecological process knowledge
Publication
Geng, L., Bian, S., Ma, X. et al. Knowledge-guided machine learning for predicting the carbon sequestration potential of natural forests in Heilongjiang Province. Annals of Forest Science 83, 42 (2026). https://doi.org/10.1186/s13595-026-01359-1
Handling editor
Frédéric Frappart