Phase-Preserving Trimodal Transformer for Tropical Forest Biomass Estimation Using Optical and PolInSAR Data

[Submitted on 4 Jul 2026 (v1), last revised 9 Jul 2026 (this version, v3)]

Authors:Luiz Felipe Parente Santiago (1 and 2), Felipe Ferrari (3), Daniel Rodrigues dos Santos (3), Rosiane de Freitas (1) ((1) Instituto de Computação, Universidade Federal do Amazonas (IComp/UFAM), Manaus-AM, Brazil, (2) Instituto de Pesquisas do Exército na Amazônia (IPEAM), Manaus-AM, Brazil, (3) Instituto Militar de Engenharia (IME), Rio de Janeiro-RJ, Brazil)

View PDF HTML (experimental)

Abstract:The accurate estimation of Above-Ground Biomass (AGB) in mature tropical forests remains a critical challenge in remote sensing, primarily due to the saturation of Synthetic Aperture Radar (SAR) signals in high-density areas and persistent cloud cover affecting optical imagery. To overcome these physical limitations, we propose the Trimodal Coherent Co-attention Transformer (TCCT), a physics-informed deep learning architecture. The TCCT natively fuses optical surface reflectance (Landsat-5) with complex-valued Polarimetric SAR Interferometry (PolInSAR) data from both P and L bands. Unlike traditional fusion methods, our architecture employs complex-valued encoders to preserve spatial phase coherence, coupled with a dynamic co-attention mechanism that acts as an adaptive gating module, reducing the weight of cloud-corrupted optical pixels and shifting reliance to microwave phase data. We also derived a localized spatial allometric calibration model via Levenberg-Marquardt optimization, tailored to the specific wood density of the Paracou region in the Amazon basin. Evaluated using a two-stage protocol, the TCCT first underwent a rigorous 5-fold cross-validation to establish robust global weights (achieving a global RMSE of 4.19 m). Subsequently, following a localized spatial fine-tuning phase over 200 epochs, the model attained an absolute RMSE of 3.78 m and an $R^2$ of 0.33 for Canopy Height Models (CHM), outperforming standard Random Forest, CNN, and Vision Transformer baselines. Our ablation study confirms that preserving phase coherence mitigates deep-canopy signal saturation. When converted to AGB, the fine-tuned TCCT map yielded a Relative RMSE (rRMSE) of 4.51% in dense forest areas above 50 Mg/ha. By meeting the European Space Agency (ESA) BIOMASS mission requirement of less than 20% error, the TCCT provides a robust framework for continuous carbon stock mapping in tropical biomes.

Submission history

From: Luiz Felipe Parente Santiago [view email]
[v1] Sat, 4 Jul 2026 02:32:51 UTC (9,484 KB)
[v2] Tue, 7 Jul 2026 18:48:23 UTC (9,484 KB)
[v3] Thu, 9 Jul 2026 15:14:29 UTC (9,484 KB)