AI-Assisted Physical Modeling of Sun Glint to Improve Inter-Sensor Consistency of Remote Sensing Reflectance in Coastal Waters

Abstract. The remote sensing of biophysical parameters in aquatic systems, such as water constituents, depends strongly on the quality of the spectral data. Sun glint, specular reflection from the water surface, is a major artifact that can substantially contaminate the remote sensing reflectance (Rrs). Accurate modeling of sun glint is therefore essential, particularly in multi-sensor analyses, to ensure seamless Rrs and water constituent products. Here, we build upon the recently developed WASI-AI model to mitigate sun-glint effects. WASI-AI is an AI-assisted physical inversion that offers key advantages over traditional physics-only approaches, including improved handling of spectral ambiguities and significantly faster inversions. We evaluate the effectiveness of WASI-AI’s glint correction capability through an inter-sensor consistency analysis between Landsat-9 and Sentinel-2. The analysis uses near-simultaneous acquisitions over optically complex coastal waters of the Adriatic Sea. The two overpasses are only a few minutes apart, which allows us to assume stable bio-optical conditions. In contrast, sun glint can vary rapidly because it is sensitive to viewing and illumination geometry as well as wind-driven surface roughness and currents. These factors may affect the data from the two sensors differently, even within a short time window. Our results show that the WASI-AI glint correction identifies substantial differences in both the magnitude and spatial patterns of sun glint between the near-simultaneous Landsat-9 and Sentinel-2 acquisitions. The Rrs consistency analysis demonstrates that, after glint correction, agreement between corresponding bands of the two sensors improves on average by 6% in R2 and by 5% in normalized root-mean-square difference.

Duke Scholars

Author Sonia Silvestri Earth and Climate Sciences