Quantifying uncertainty in high resolution biophysical variable retrieval with machine learning

Laura Martínez-Ferrer

doi:10.1016/j.rse.2022.113199

Quantifying uncertainty in high resolution biophysical variable retrieval with machine learning

2022-10-01

15

OA

AI

L

Laura Martínez-Ferrer *

Á

Álvaro Moreno‐Martínez

M

Manuel Campos‐Taberner

F

Francisco Javier Garcı́a-Haro

DOI：10.1016/j.rse.2022.113199

原文链接

查看原文

摘要

En 中文

The estimation of biophysical variables is at the core of remote sensing science, allowing a close monitoring of crops and forests. Deriving temporally resolved and spatially explicit maps of parameters of interest has been the subject of intense research. However, deriving products from optical sensors is typically hampered by cloud contamination and the trade-off between spatial and temporal resolutions. In this work we rely on the HIghly Scalable Temporal Adaptive Reflectance Fusion Model (HISTARFM) algorithm to generate long gap-free time series of Landsat surface reflectance data by fusing MODIS and Landsat reflectances. An artificial neural network is trained on PROSAIL inversion to predict monthly biophysical variables at 30 m spatial resolution with asso-ciated, realistic uncertainty bars. We emphasize the need for a more thorough analysis of uncertainty, and propose a general and scalable approach to combine both epistemic and aleatoric uncertainties by exploiting Monte Carlo (MC) dropout techniques from the trained artificial network and the propagation of HISTARFM uncertainties through the model, respectively. A model recalibration was performed in order to provide reliable uncertainties. We provide new high resolution products of several key variables to quantify the terrestrial biosphere: Leaf Area Index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FAPAR), Canopy Water Content (CWC) and Fractional Vegetation Cover (FVC) are at 30 m Landsat spatial resolution and over large continental areas. Two study areas are considered: the large heterogeneous but moderately cloud covered contiguous United States, and the homogeneous but largely cloud covered Amazonia. The produced vegetation products largely agree with the test dataset (R = 0.90, RMSE = 0.80 m2/m2 and ME = 0.12 m2/m2 for LAI, and R = 0.98, RMSE = 0.07 and ME = 0.01 for FAPAR) providing low error and high accuracy. Additionally, the validation considers a thorough comparison with operational and largely validated medium resolution products, such as the Moderate-Resolution Imaging Spectroradiometer (MODIS) and Copernicus Global Land Service. Our products presented a good agreement and consistency with both MODIS (R = 0.84 and R = 0.85 for LAI and FAPAR, respectively) and Copernicus (R = 0.92 and R = 0.91 for LAI and FAPAR, respectively). To foster a wider adoption and reproducibility of the methodology we provide an application in GEE and source code at:https:// github.com/IPL-UV/ee_BioNet/

Keyword:

MODIS

Landsat

Downscaling

Biophysical parameter estimation

Uncertainty

Neural networks

Quantifying uncertainty in high resolution biophysical variable retrieval with machine learning

摘要

AI总结

期刊

机构