Work

Forest Aboveground Biomass Estimation Using High-Resolution Imagery and Integrated Machine Learning

Year: 2025

Type: article

Abstract: This study quantifies forest aboveground biomass (AGB) using integrated remote sensing features from high-resolution GaoFen-7 (GF-7) satellite imagery. We combined texture features, vegetation indices, and RGB spectral bands to improve estimation accuracy. Three machine learning algorithms—Random Forest (RF), Gradient Boosting Tree (GBT), and XGBoost—were compared with a stacking ensemble model using five-fold cross-validation on forest plots in Beijing’s Daxing District. Feature importance was evaluated through SHAP to identify key predictive variables. Results show that texture features exhibit scale-dependent predictive power, while visible-band vegetation indices strongly correlate with AGB. The Stacking ensemble achieved optimal performance (R2 = 0.62, RMSE = 57.34 Mg/ha, MAE = 39.99 Mg/ha), outperforming XGBoost (R2 = 0.59), RF (R2 = 0.58), and GBT (R2 = 0.57). Compared to the best individual model, Stacking improved R2 by 5.1% and effectively mitigated over- and underestimation biases. These findings demonstrate the effectiveness of ensemble learning for forest AGB estimation and suggest potential for regional-scale carbon monitoring applications.

Source: Forests

DOI: 10.3390/f16121777

Authors: Jiaqi Liu, Maohua Liu, Tao Shen, Fei Yan, Zeyuan Zhou

Institutions: Shenyang Jianzhu University, Chinese Academy of Surveying and Mapping, Beijing Forestry University

Language: English

Topic: Remote Sensing and LiDAR Applications

Subfield: Environmental Engineering

Field: Environmental Science

Domain: Physical Sciences

SDGs: Life on land, Climate action

Open Access status: gold

Estimated APC paid: $3,137