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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mahesh, Ragini Bal, Hänsch, Ronny
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915241835626496
author Mahesh, Ragini Bal
Hänsch, Ronny
author_facet Mahesh, Ragini Bal
Hänsch, Ronny
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Better Coherence, Better Height: Fusing Physical Models and Deep Learning for Forest Height Estimation from Interferometric SAR Data
Mahesh, Ragini Bal
Hänsch, Ronny
Computer Vision and Pattern Recognition
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.
title Better Coherence, Better Height: Fusing Physical Models and Deep Learning for Forest Height Estimation from Interferometric SAR Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.10395