EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Modeling forest aboveground biomass in cloud-prone tropical mountains using temporally encoded Sentinel-2 time series and synthetic training data

Thi Nhat Minh Doan, Vu Dong Pham, Van Manh Vu, Dinh Hung Nguyen, Felipe Bravo

Modeling Earth Systems and Environment · 2026-08 · 12 (4)

DOI: 10.1007/s40808-026-02859-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Modeling Earth Systems and Environment, online erschienen am 28.07.2026. Verfasst von Thi Nhat Minh Doan und 4 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Erasmus+ International Credit Mobility KA171.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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. A scalable framework uses S2 time-series and synthetic data for AGB in Northern Vietnam. Temporal encoding reconstructs forest phenology from irregular S2 observations. This approach enables biomass mapping in tropics with sparse ground data. Synthetic data enables 1D-CNN to perform well with limited field AGB references. The 10 m AGB map achieves RMSE 1.61 kg m⁻² and R² of 0.87 at regional scale. A scalable framework uses S2 time-series and synthetic data for AGB in Northern Vietnam. Temporal encoding reconstructs forest phenology from irregular S2 observations. This approach enables biomass mapping in tropics with sparse ground data. Synthetic data enables 1D-CNN to perform well with limited field AGB references. The 10 m AGB map achieves RMSE 1.61 kg m⁻² and R² of 0.87 at regional scale.

Förderung

  • Erasmus+ International Credit Mobility KA171

Zitieren

APA

Doan, T. N. M., Pham, V. D., Vu, V. M., Nguyen, D. H., & Bravo, F. (2026). Modeling forest aboveground biomass in cloud-prone tropical mountains using temporally encoded Sentinel-2 time series and synthetic training data. Modeling Earth Systems and Environment, 12(4). https://doi.org/10.1007/s40808-026-02859-9

Vancouver

Doan TNM, Pham VD, Vu VM, Nguyen DH, Bravo F. Modeling forest aboveground biomass in cloud-prone tropical mountains using temporally encoded Sentinel-2 time series and synthetic training data. Modeling Earth Systems and Environment. 2026;12(4). doi:10.1007/s40808-026-02859-9

BibTeX
@article{Doan2026,
  author = {Doan, Thi Nhat Minh and Pham, Vu Dong and Vu, Van Manh and Nguyen, Dinh Hung and Bravo, Felipe},
  title = {Modeling forest aboveground biomass in cloud-prone tropical mountains using temporally encoded Sentinel-2 time series and synthetic training data},
  journal = {Modeling Earth Systems and Environment},
  year = {2026},
  volume = {12},
  number = {4},
  doi = {10.1007/s40808-026-02859-9}
}
Kostenlos starten →