There are few allometric equations available for dipterocarp forests, despite the fact that this forest type covers extensive areas in tropical Southeast Asia. This study aims to develop a set of equations to estimate tree aboveground biomass (AGB) in dipterocarp forests in Vietnam and to validate and compare their predictive performance with allometric equations used for dipterocarps in Indonesia and pantropical areas. Diameter at breast height (DBH), total tree height (H), and wood density (WD) were used as input variables of the nonlinear weighted least square models. Akaike information criterion (AIC) and residual plots were used to select the best models; while percent bias, root mean square percentage error, and mean absolute percent error were used to compare their performance to published models. For mixed-species, the best equation was $\text{AGB}=0.06203\times {\text{DBH}}^{2.26430}\times {\mathrm{H}}^{0.51415}\times {\text{WD}}^{0.79456}$ . When applied to a random independent validation dataset, the predicted values from the generic equations and the dipterocarp equations in Indonesia overestimated the AGB for different sites, indicating the need for region-specific equations. At the genus level, the selected equations were $\text{AGB}=0.03713\times {\text{DBH}}^{2.73813}$ and $\text{AGB}=0.07483\times {\text{DBH}}^{2.54496}$ for two genera, Dipterocarpus and Shorea, respectively, in Vietnam. Compared to the mixed-species equations, the genus-specific equations improved the accuracy of the AGB estimates. Additionally, the genus-specific equations showed no significant differences in predictive performance in different regions (e.g., Indonesia, Vietnam) of Southeast Asia.

Accurate modeling of forest aboveground biomass (AGB) in cloud-prone tropical mountains remains constrained by irregular optical remote-sensing observations and limited field-reference data. This study proposes a 10 m AGB modeling framework that combines Sentinel-2 time-series data with regression training based on synthetic samples. Sentinel-2 observations from 2019 to 2021 were folded into target-year annual sequences and encoded as weekly spectral tensors to preserve irregular cloud-free observation patterns. Field-derived AGB samples from northern Vietnam were spatially aggregated to 10 m resolution and used to generate approximately 128,000 synthetic training samples through weighted spectral–biomass mixing. A one-dimensional convolutional neural network (1D-CNN) regression model was then trained using the synthetic samples and evaluated against independent field-derived test samples. The synthetic-data model (Model-S) achieved MAE = 1.19 kg m⁻², RMSE = 1.61 kg m⁻², and R² = 0.87 across all validation locations, improving MAE by 32%, RMSE by 31%, and R² by 18% relative to the model trained only with real samples (Model-R). The resulting 10 m AGB map revealed moderate regional biomass levels and localized high-biomass patches in the western mountainous areas. This framework provides a scalable approach for biomass mapping in regions where field plots are sparse and Sentinel-2 optical time series are irregular.