Gaussian Processes Retrieval of LAI from Sentinel-2 Top-of-Atmosphere Radiance Data

TL;DR

This paper demonstrates that leaf area index (LAI) can be accurately retrieved directly from Sentinel-2 top-of-atmosphere radiance data using a hybrid machine learning approach, bypassing the need for atmospheric correction.

Contribution

It introduces a novel method for LAI retrieval from TOA radiance data using Gaussian processes, validated against bottom-of-atmosphere retrievals, without atmospheric correction.

Findings

VHGPR models produce consistent LAI maps at TOA and BOA levels.

LAI can be retrieved directly from TOA radiance data under clear sky conditions.

Hybrid algorithms enable LAI estimation without atmospheric correction.

Abstract

Retrieval of vegetation properties from satellite and airborne optical data usually takes place after atmospheric correction, yet it is also possible to develop retrieval algorithms directly from top-of-atmosphere (TOA) radiance data. One of the key vegetation variables that can be retrieved from at-sensor TOA radiance data is the leaf area index (LAI) if algorithms account for variability in the atmosphere. We demonstrate the feasibility of LAI retrieval from Sentinel-2 (S2) TOA radiance data (L1C product) in a hybrid machine learning framework. To achieve this, the coupled leaf-canopy-atmosphere radiative transfer models PROSAIL-6S were used to simulate a look-up table (LUT) of TOA radiance data and associated input variables. This LUT was then used to train the Bayesian machine learning algorithms Gaussian processes regression (GPR) and variational heteroscedastic GPR (VHGPR). PROSAIL simulations were also used to train GPR and VHGPR models for LAI retrieval from S2 images at bottom-of-atmosphere (BOA) level (L2A product) for comparison purposes. The VHGPR models led to consistent LAI maps at BOA and TOA scale. We demonstrated that hybrid LAI retrieval algorithms can be developed from TOA radiance data given a cloud-free sky, thus without the need for atmospheric correction.