Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification

Monitoring deforestation-driven carbon emissions requires both spatially explicit and temporally continuous estimates of aboveground biomass density (AGBD) with calibrated uncertainty. NASA's Global Ecosystem Dynamics Investigation (GEDI) provides reliable LIDAR-derived AGBD, but its orbital sampling causes irregular spatiotemporal coverage, and occasional operational interruptions, including a 13-month hibernation from March 2023 to April 2024, leave extended gaps in the observational record. Prior work has used machine learning approaches to fill GEDI's spatial gaps using satellite-derived features, but temporal interpolation of biomass through unobserved periods, particularly across active disturbance events, remains largely unaddressed. Moreover, standard ensemble methods for biomass mapping have been shown to produce systematically miscalibrated prediction intervals. To address these gaps, we extend the Attentive Neural Process (ANP) framework, previously applied to spatial biomass interpolation, to jointly sparse spatiotemporal settings using geospatial foundation model embeddings. We treat space and time symmetrically, empirically validating a form of space-for-time substitution in which observations from nearby locations at other times inform predictions at held-out periods. Our results demonstrate that the ANP produces well-calibrated uncertainty estimates across disturbance regimes, supporting its use in Measurement, Reporting, and Verification (MRV) applications that require reliable uncertainty quantification for forest carbon accounting.

Spatially continuous quantification of forest above-ground biomass (AGB) is what makes carbon accounting credible and mitigation strategies actionable. While field inventories provide high localized accuracy, they are spatially sparse; conversely, spaceborne LiDAR from the Global Ecosystem Dynamics Investigation (GEDI) offers broad biomass samples but lacks spatial continuity and systematic underestimation of high-biomass forests. This paper presents an operational framework centered on a single globally trained convolutional neural network (CNN) that is seamlessly adapted to each new landscape through a lightweight empirical field-calibration workflow. The global model combines optical (Sentinel-2), C-band SAR (Sentinel-1), L-band SAR (ALOS-2 PALSAR-2), and terrain (DEM) data. It is trained once against GEDI Level-4A biomass reference data spanning multiple regions and both wet and dry seasons so that it learns the persistent woody-structure rather than a single-date appearance. To avoid retraining for every landscape, the framework applies a small number of local field plots to fit a scale-and-bias correction that aligns the global prediction with ground truth in each region. The pipeline harmonizes sensor data onto a shared 10 m grid, derives vegetation indices and polarimetric ratios, computes per-band normalization stats, and trains the CNN with a hybrid log-domain SmoothL1 with RMSE loss for skewed biomass distribution. On held-out validation the global GEDI-based model achieved R^2 approximately 0.78 and RMSE approximately 22 Mg/ha. A subsequent field calibration combining Random Forest fine-tuning under a 10-fold cross-validation eliminates localized regional biases. This improves local validation performance to R^2 approximately 0.82 and reduces RMSE to approximately 15 Mg/ha, outperforming both the uncalibrated global model and the ESA CCI Biomass product against field plots.

Accurate estimation of above-ground biomass (AGB) from satellite imagery is essential for the large-scale monitoring of carbon stocks, yet it remains a challenging regression task at global scale. Geospatial Foundation Models (GFMs) have recently emerged as a promising machine learning paradigm to derive general-purpose representations from Earth observation (EO) data, but their utility for quantitative regression tasks like biomass estimation remains largely unexplored, as most benchmarks focus on classification and segmentation. Here, we benchmark 13 GFMs for above-ground biomass estimation, specifically GEDI L4A biomass values. We compare them against a fully supervised state-of-the-art (SOTA) baseline trained on A Global-scale Biomass Dataset (AGBD), a machine learning-ready benchmark spanning diverse biomes and geographies. Most of the GFMs evaluated substantially underperform with respect to the supervised baseline, whether frozen or fine-tuned; only TESSERA and AlphaEarth Foundations (AEF) features with certain prediction heads yield a better performance. Our SOTA model trained on AEF embeddings and selected raw EO features achieves the best overall result (RMSE of 50.79 Mg/ha vs. 53.73 Mg/ha on AGBD features). This feature combination also generalizes better than AGBD features: it reduces RMSE by up to 25% in selected regions excluded from training, and, trained on single-year data alone, it outperforms the model trained on multi-year AGBD features. With labels from only 11 regions around the world, the AEF-based model also performs on par with the globally calibrated ESA CCI biomass product on independent reference plots. These findings indicate that GFM features can be highly informative for biomass estimation, when the underlying model is trained on rich multi-modal data.