Physics informed Transformer-VAE for biophysical parameter estimation: PROSAIL model inversion in Sentinel-2 imagery

TL;DR

This paper introduces a physics-informed Transformer-VAE model that accurately estimates vegetation biophysical parameters from Sentinel-2 satellite data by integrating the PROSAIL radiative transfer model as a differentiable physical decoder, trained solely on simulated data.

Contribution

It presents a novel Transformer-VAE architecture that incorporates physical models for satellite image inversion, enabling accurate biophysical parameter estimation without real-image training data.

Findings

Achieves comparable accuracy to models trained on real data

Requires no in-situ labels or calibration on real images

Demonstrates effective inversion of vegetation parameters from Sentinel-2 data

Abstract

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.