Physics informed Transformer-VAE for biophysical parameter estimation: PROSAIL model inversion in Sentinel-2 imagery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909907788234752 |
|---|---|
| author | Mensah, Prince Aderinto, Pelumi Victor Yusuf, Ibrahim Salihu Pretorius, Arnu |
| author_facet | Mensah, Prince Aderinto, Pelumi Victor Yusuf, Ibrahim Salihu Pretorius, Arnu |
| contents | Accurate retrieval of vegetation biophysical variables from satellite imagery is crucial for ecosystem monitoring and agricultural management. In this work, we propose a physics-informed Transformer-VAE architecture to invert the PROSAIL radiative transfer model for simultaneous estimation of key canopy parameters from Sentinel-2 data. Unlike previous hybrid approaches that require real satellite images for self-supevised training. Our model is trained exclusively on simulated data, yet achieves performance on par with state-of-the-art methods that utilize real imagery. The Transformer-VAE incorporates the PROSAIL model as a differentiable physical decoder, ensuring that inferred latent variables correspond to physically plausible leaf and canopy properties. We demonstrate retrieval of leaf area index (LAI) and canopy chlorophyll content (CCC) on real-world field datasets (FRM4Veg and BelSAR) with accuracy comparable to models trained with real Sentinel-2 data. Our method requires no in-situ labels or calibration on real images, offering a cost-effective and self-supervised solution for global vegetation monitoring. The proposed approach illustrates how integrating physical models with advanced deep networks can improve the inversion of RTMs, opening new prospects for large-scale, physically-constrained remote sensing of vegetation traits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10387 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Physics informed Transformer-VAE for biophysical parameter estimation: PROSAIL model inversion in Sentinel-2 imagery Mensah, Prince Aderinto, Pelumi Victor Yusuf, Ibrahim Salihu Pretorius, Arnu Computer Vision and Pattern Recognition Machine Learning 14J60 (Primary) 14F05, 14J26 (Secondary) Accurate retrieval of vegetation biophysical variables from satellite imagery is crucial for ecosystem monitoring and agricultural management. In this work, we propose a physics-informed Transformer-VAE architecture to invert the PROSAIL radiative transfer model for simultaneous estimation of key canopy parameters from Sentinel-2 data. Unlike previous hybrid approaches that require real satellite images for self-supevised training. Our model is trained exclusively on simulated data, yet achieves performance on par with state-of-the-art methods that utilize real imagery. The Transformer-VAE incorporates the PROSAIL model as a differentiable physical decoder, ensuring that inferred latent variables correspond to physically plausible leaf and canopy properties. We demonstrate retrieval of leaf area index (LAI) and canopy chlorophyll content (CCC) on real-world field datasets (FRM4Veg and BelSAR) with accuracy comparable to models trained with real Sentinel-2 data. Our method requires no in-situ labels or calibration on real images, offering a cost-effective and self-supervised solution for global vegetation monitoring. The proposed approach illustrates how integrating physical models with advanced deep networks can improve the inversion of RTMs, opening new prospects for large-scale, physically-constrained remote sensing of vegetation traits. |
| title | Physics informed Transformer-VAE for biophysical parameter estimation: PROSAIL model inversion in Sentinel-2 imagery |
| topic | Computer Vision and Pattern Recognition Machine Learning 14J60 (Primary) 14F05, 14J26 (Secondary) |
| url | https://arxiv.org/abs/2511.10387 |