# Better Coherence, Better Height: Fusing Physical Models and Deep Learning for Forest Height Estimation from Interferometric SAR Data

arXiv: https://arxiv.org/abs/2504.10395 · HTML: https://mlsanity.com/paper/2504.10395/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 45 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 6 of 6)

- [High-resolution canopy height map in the Landes forest (France) based on GEDI, Sentinel-1, and Sentinel-2 data with a deep learning approach](https://mlsanity.com/paper/2212.10265/) (2022)
- [Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Deep Ensembles](https://mlsanity.com/paper/2111.13154/) (2021)
- [Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights](https://mlsanity.com/paper/2304.11487/) (2023)
- [Living in the Physics and Machine Learning Interplay for Earth Observation](https://mlsanity.com/paper/2010.09031/) (2020)
- [Deep Learning Model Transfer in Forest Mapping using Multi-source Satellite SAR and Optical Images](https://mlsanity.com/paper/2308.05005/) (2023)
- [CATSNet: a context-aware network for Height Estimation in a Forested Area based on Pol-TomoSAR data](https://mlsanity.com/paper/2403.20273/) (2024)

## Abstract (arXiv)

Estimating forest height from Synthetic Aperture Radar (SAR) images often relies on traditional physical models, which, while interpretable and data-efficient, can struggle with generalization. In contrast, Deep Learning (DL) approaches lack physical insight. To address this, we propose CoHNet - an end-to-end framework that combines the best of both worlds: DL optimized with physics-informed constraints. We leverage a pre-trained neural surrogate model to enforce physical plausibility through a unique training loss. Our experiments show that this approach not only improves forest height estimation accuracy but also produces meaningful features that enhance the reliability of predictions.