Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes
This work addresses the problem of estimating the global carbon budget for climate science by enhancing the robustness and transferability of carbon flux estimates, though it appears incremental as it builds on existing data-driven methods with physical constraints.
The paper tackled the challenge of accurately upscaling terrestrial carbon fluxes from sparse ground measurements by introducing TAM-RL, a framework that improved predictive performance, reducing RMSE by 8-9.6% and increasing explained variance from 19.4% to 43.8% across diverse sites.
Accurately upscaling terrestrial carbon fluxes is central to estimating the global carbon budget, yet remains challenging due to the sparse and regionally biased distribution of ground measurements. Existing data-driven upscaling products often fail to generalize beyond observed domains, leading to systematic regional biases and high predictive uncertainty. We introduce Task-Aware Modulation with Representation Learning (TAM-RL), a framework that couples spatio-temporal representation learning with knowledge-guided encoder-decoder architecture and loss function derived from the carbon balance equation. Across 150+ flux tower sites representing diverse biomes and climate regimes, TAM-RL improves predictive performance relative to existing state-of-the-art datasets, reducing RMSE by 8-9.6% and increasing explained variance (R2) from 19.4% to 43.8%, depending on the target flux. These results demonstrate that integrating physically grounded constraints with adaptive representation learning can substantially enhance the robustness and transferability of global carbon flux estimates.