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

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.

Plant phenotyping relevance

Sentinel-2のTOA放射輝度からLAIを推定する機械学習アルゴリズムを開発・比較しており、植物形質の取得手法が研究の中心である。

Code and data availability

The paper's hybrid LAI retrieval (GPR/VHGPR) was developed within the authors' ALG-ARTMO software framework, and code snippets/demos for GPR and VHGPR are publicly available from the authors' UV-ES soft regression page. Both are explicitly stated as freely downloadable in the supplied text. No paper-specific phenotype/