POSTER Session 2

HYPERSPECTRAL PARTICULATE BACKSCATTERING COEFFICIENT RETRIEVAL IN INLAND AND COASTAL WATERS VIA PHYSICS-INFORMED MIXTURE DENSITY NETWORKS

The absorbing and backscattering inherent optical properties (IOPs) of water and its associated constituents shape the ocean’s color. We previously developed machine-learning-based models, mixture density networks (MDNs), to retrieve the absorbing (a(λ)) components in optically complex coastal and inland waters from hyperspectral satellite imagery (O’Shea et al. 2023). Well-established algorithms, such as the Quasi-Analytical Algorithm (QAA, Lee et al. 2002), the Generalized IOP (GIOP) model (Werdell et al. 2013), and the semi-analytical Gordon et al. model (Gordon et al. 1988) can retrieve the particulate backscattering coefficient (bbp(λ)) from hyperspectral imagery; however, these models were designed for open ocean conditions, not optically complex inland and coastal waters. In this work, we will create a physics-informed MDN for hyperspectral bbp(λ) retrieval from inland and coastal waters. The MDN will learn the relationship between a(λ), bbp(λ), and Rrs(λ) via the inclusion of the semi-analytical Gordon et al. model during training. For training and validation of the physics-informed MDN we have a large (N~500) dataset of in situ measured multispectral bbp(λ) from multiple optically distinct regions. Additionally, we will compare bbp(λ) derived using our physics-informed MDN and operational models (e.g., QAA, GIOP) to in situ bbp(λ) from Lake Erie. Finally, we will compare bbp(λ) retrieved using the MDN and operational models on imagery of Lake Erie from PACE’s Ocean Colour Instrument to evaluate the impact of atmospheric correction uncertainties. Overall, we expect the physics-informed MDN to improve IOP retrieval from inland and coastal waters.

Ryan O’Shea, Science Systems and Applications Inc. (SSAI) and NASA Goddard Space Flight Center, USA

Nim Pahlevan, Science Systems and Applications Inc. (SSAI) and NASA Goddard Space Flight Center, USA

Brandon Smith, Science Systems and Applications Inc. (SSAI) and NASA Goddard Space Flight Center, USA

Sundarabalan V. Balasubramanian, University of Maryland Baltimore County (UMBC), USA

P. Jeremy Werdell, NASA Goddard Space Flight Center, USA

Emmanuel Boss, School of Marine Sciences, University of Maine, USA

Brice K. Grunert, Cleveland State University, USA

Code of Conduct
Privacy Policy