Inference over radiative transfer models using variational and expectation maximization methods

TL;DR

This paper introduces two advanced computational methods, variational autoencoder and MCEM, to perform inference over complex radiative transfer models, enabling estimation of biophysical parameters from satellite data.

Contribution

The paper presents novel applications of variational autoencoders and MCEM for joint distribution inference over nonlinear, non-differentiable RTMs, with comparative analysis.

Findings

Both methods effectively infer biophysical parameters from synthetic and real data.

The approaches reveal trade-offs in accuracy and computational efficiency.

Results demonstrate improved parameter estimation over traditional methods.

Abstract

Earth observation from satellites offers the possibility to monitor our planet with unprecedented accuracy. Radiative transfer models (RTMs) encode the energy transfer through the atmosphere, and are used to model and understand the Earth system, as well as to estimate the parameters that describe the status of the Earth from satellite observations by inverse modeling. However, performing inference over such simulators is a challenging problem. RTMs are nonlinear, non-differentiable and computationally costly codes, which adds a high level of difficulty in inference. In this paper, we introduce two computational techniques to infer not only point estimates of biophysical parameters but also their joint distribution. One of them is based on a variational autoencoder approach and the second one is based on a Monte Carlo Expectation Maximization (MCEM) scheme. We compare and discuss benefits and drawbacks of each approach. We also provide numerical comparisons in synthetic simulations and the real PROSAIL model, a popular RTM that combines land vegetation leaf and canopy modeling. We analyze the performance of the two approaches for modeling and inferring the distribution of three key biophysical parameters for quantifying the terrestrial biosphere.