Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes

TL;DR

This paper presents TAM-RL, a novel framework combining representation learning and physical constraints to improve the accuracy and generalization of terrestrial carbon flux upscaling across diverse biomes.

Contribution

Introduction of TAM-RL, a task-aware, physically guided representation learning framework that enhances global carbon flux predictions beyond observed regions.

Findings

Reduces RMSE by 8-9.6% compared to existing datasets.

Increases explained variance (R2) from 19.4% to 43.8%.

Demonstrates improved robustness and transferability across diverse biomes.

Abstract

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.