Statistical regression methods are widely used in remote sensing applications but tend to lack physical interpretability. In this article, we introduce a methodological framework to improve model emulation and its understanding with machine learning feature selection. Our wrapper-forward feature selection method seamlessly integrates physics knowledge into model emulation, improving the tradeoff between accuracy and interpretability. We illustrate our methodology by applying it to atmospheric radiative transfer models (RTMs) in the context of global sensitivity analysis (GSA) and emulation. Our approach consistently aligns with variance-based GSA, pinpointing the critical features of aerosol properties, solar zenith angle, and water vapor. While our physically based emulators yield only a modest accuracy improvement of 0.2% over conventional Gaussian process (GP) emulators, its introduction signifies a step forward to physics-aware machine learning-based emulation. The emulator performance remains steadfast, unaffected by substantial changes, further underscoring the reliability of our approach.

Multioutput Feature Selection for Emulation and Sensitivity Analysis

Martino, Luca;
2024-01-01

Abstract

Statistical regression methods are widely used in remote sensing applications but tend to lack physical interpretability. In this article, we introduce a methodological framework to improve model emulation and its understanding with machine learning feature selection. Our wrapper-forward feature selection method seamlessly integrates physics knowledge into model emulation, improving the tradeoff between accuracy and interpretability. We illustrate our methodology by applying it to atmospheric radiative transfer models (RTMs) in the context of global sensitivity analysis (GSA) and emulation. Our approach consistently aligns with variance-based GSA, pinpointing the critical features of aerosol properties, solar zenith angle, and water vapor. While our physically based emulators yield only a modest accuracy improvement of 0.2% over conventional Gaussian process (GP) emulators, its introduction signifies a step forward to physics-aware machine learning-based emulation. The emulator performance remains steadfast, unaffected by substantial changes, further underscoring the reliability of our approach.
2024
Emulation
feature selection
Gaussian processes (GPs)
hyperspectral
physics-aware machine learning
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/613889
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact