From Spectra to Biophysical Insights: End-to-End Learning with a Biased Radiative Transfer Model

TL;DR

This paper introduces an end-to-end learning framework that integrates radiative transfer models into an auto-encoder to correct biases and improve the retrieval of biophysical variables from spectral data, enhancing interpretability in climate change studies.

Contribution

The novel integration of RTMs into an auto-encoder architecture effectively corrects biases and outperforms traditional neural network regression methods for biophysical variable retrieval.

Findings

Outperforms traditional methods in variable retrieval accuracy

Effectively corrects biases in radiative transfer models

Applicable to inverting biased physical models

Abstract

Advances in machine learning have boosted the use of Earth observation data for climate change research. Yet, the interpretability of machine-learned representations remains a challenge, particularly in understanding forests' biophysical reactions to climate change. Traditional methods in remote sensing that invert radiative transfer models (RTMs) to retrieve biophysical variables from spectral data often fail to account for biases inherent in the RTM, especially for complex forests. We propose to integrate RTMs into an auto-encoder architecture, creating an end-to-end learning approach. Our method not only corrects biases in RTMs but also outperforms traditional techniques for variable retrieval like neural network regression. Furthermore, our framework has potential generally for inverting biased physical models. The code is available on https://github.com/yihshe/ai-refined-rtm.git.