An Emulator Toolbox to Approximate Radiative Transfer Models with Statistical Learning

Rivera, Juan Pablo; Verrelst, Jochem; Gómez-Dans, José; Muñoz-Marí, Jordi; Moreno, José; Camps‐Valls, Gustau

doi:10.3390/rs70709347

Cited by 64 publications

(79 citation statements)

References 63 publications

(76 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The large majority of the work was undertaken within the in-house developed ARTMO framework [68]. ARTMO consists of a suite of leaf and canopy RTMs, retrieval toolboxes, and recently a GSA toolbox [69] and an Emulator toolbox was added [37]. The Emulator toolbox is based on an earlier developed MLRA retrieval toolbox, which is equipped with a diversity of nonparametric regression models, mostly from the family of MLRAs [47].…”

Section: Methodsmentioning

confidence: 99%

“…However, the full, contiguous spectral profile typically consists above 2000 bands when binned to 1 nm resolution. This can take considerable training time, especially when using neural networks [37]. To enable the models to cope with large hyperspectral datasets (e.g., reflectance, transmittance, fluorescence), applying a principal component analysis (PCA) dimensionality reduction step [48] prior to training a model has been implemented.…”

Section: Emulator Theorymentioning

confidence: 99%

“…The regression methods are then trained to predict the PCA reduced spectra, and the inverse of the PCA transformation is subsequently applied to obtain the reconstructed output spectra. This dimensionality reduction strategy not only greatly speeds up the training phase but also makes the problem better conditioned [36][37][38]. An additional advantage of applying the PCA transformation is that it allows converting single-output MLRAs into multiple output methods, i.e., meaning that in principle any multivariate regression algorithm can function as emulator.…”

Section: Emulator Theorymentioning

confidence: 99%

“…Based on the literature review above and an earlier comparison study conducted [37], the following three MLRAs potentially serve as powerful methods to function as emulators, being kernel ridge regression (KRR), neural networks (NN) and Gaussian processes regression (GPR). These methods have been amply described in earlier publications (e.g., [5,38,44,46,49,50]).…”

Section: Emulator Theorymentioning

confidence: 99%

“…Only recently Rivera et al (2015) [37] and Gómez-Dans et al (2016) [38] started exploring the possibility of emulating RTMs and applying them for retrieval applications. The authors constructed RTM-like emulators with capabilities to deliver accurately and quasi-instantly spectral outputs such as reflectance, fluorescence and radiance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Emulation of Leaf, Canopy and Atmosphere Radiative Transfer Models for Fast Global Sensitivity Analysis

et al. 2016

Self Cite

View full text Add to dashboard Cite

Abstract:Physically-based radiative transfer models (RTMs) help understand the interactions of radiation with vegetation and atmosphere. However, advanced RTMs can be computationally burdensome, which makes them impractical in many real applications, especially when many state conditions and model couplings need to be studied. To overcome this problem, it is proposed to substitute RTMs through surrogate meta-models also named emulators. Emulators approximate the functioning of RTMs through statistical learning regression methods, and can open many new applications because of their computational efficiency and outstanding accuracy. Emulators allow fast global sensitivity analysis (GSA) studies on advanced, computationally expensive RTMs. As a proof-of-concept, three machine learning regression algorithms (MLRAs) were tested to function as emulators for the leaf RTM PROSPECT-4, the canopy RTM PROSAIL, and the computationally expensive atmospheric RTM MODTRAN5. Selected MLRAs were: kernel ridge regression (KRR), neural networks (NN) and Gaussian processes regression (GPR). For each RTM, 500 simulations were generated for training and validation. The majority of MLRAs were excellently validated to function as emulators with relative errors well below 0.2%. The emulators were then put into a GSA scheme and compared against GSA results as generated by original PROSPECT-4 and PROSAIL runs. NN and GPR emulators delivered identical GSA results, while processing speed compared to the original RTMs doubled for PROSPECT-4 and tripled for PROSAIL. Having the emulator-GSA concept successfully tested, for six MODTRAN5 atmospheric transfer functions (outputs), i.e., direct and diffuse at-surface solar irradiance (E di f , E dir ), direct and diffuse upward transmittance (T dir , T di f ), spherical albedo (S) and path radiance (L 0 ), the most accurate MLRA's were subsequently applied as emulator into the GSA scheme. The sensitivity analysis along the 400-2500 nm spectral range took no more than a few minutes on a contemporary computer-in comparison, the same analysis in the original MODTRAN5 would have taken over a month. Key atmospheric drivers were identified, which are on the one hand aerosol optical properties, i.e., aerosol optical thickness (AOT), Angstrom coefficient (AMS) and scattering asymmetry variable (G), mostly driving diffuse atmospheric components, E di f and T di f ; and those affected by atmospheric scattering, L 0 and S. On the other hand, as expected, AOT, AMS and columnar water vapor (CWV) in the absorption regions mostly drive E dir and T dir atmospheric functions. The presented emulation schemes showed very promising results in replacing costly RTMs, and we think they can contribute to the adoption of machine learning techniques in remote sensing and environmental applications.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Emulator Theorymentioning

confidence: 99%

Section: Emulator Theorymentioning

confidence: 99%

Section: Emulator Theorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Emulation of Leaf, Canopy and Atmosphere Radiative Transfer Models for Fast Global Sensitivity Analysis

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

Machine Learning for Clouds and Climate

Beucler,

Ebert‐Uphoff,

Rasp

et al. 2023

Geophysical Monograph Series

View full text Add to dashboard Cite

Machine Learning for Clouds and Climate (Invited Chapter for the AGU Geophysical Monograph Series "Clouds and Climate")

Beucler¹,

Ebert‐Uphoff²,

Rasp³

et al. 2021

Preprint

View full text Add to dashboard Cite

Key Points: * Machine learning (ML) helps model the interaction between clouds and climate using large datasets. * We review physics-guided/explainable ML applied to cloud-related processes in the climate system. * We also provide a guide to scientists who would like to get started with ML. Abstract: Machine learning (ML) algorithms are powerful tools to build models of clouds and climate that are more faithful to the rapidly-increasing volumes of Earth system data than commonly-used semiempirical models. Here, we review ML tools, including interpretable and physics-guided ML, and outline how they can be applied to cloud-related processes in the climate system, including radiation, microphysics, convection, and cloud detection , classification, emulation, and uncertainty quantification. We additionally provide a short guide to get started with ML and survey the frontiers of ML for clouds and climate .

show abstract

An Emulator Toolbox to Approximate Radiative Transfer Models with Statistical Learning

Cited by 64 publications

References 63 publications

Emulation of Leaf, Canopy and Atmosphere Radiative Transfer Models for Fast Global Sensitivity Analysis

Emulation of Leaf, Canopy and Atmosphere Radiative Transfer Models for Fast Global Sensitivity Analysis

Machine Learning for Clouds and Climate

Machine Learning for Clouds and Climate (Invited Chapter for the AGU Geophysical Monograph Series "Clouds and Climate")

Contact Info

Product

Resources

About