HydroQUEEN: Hydrological Detection Using CYGNSS and Quantum Deep AI

Le résumé fourni par la source

The global navigation satellite system-reflectometry (GNSS-R) technology facilitates the estimation of physical parameters on the Earth’s surface. Leveraging GNSS-R technology, NASA’s Cyclone Global Navigation Satellite System (CYGNSS) provides delay-Doppler maps (DDMs) with high temporal resolution and extensive spatial coverage, making it a promising data source for hydrological detection. Despite these advantages, a robust methodology for retrieving inland waterbodies remains unsolved. In this paper, we propose HydroQUEEN, a hydrological detection framework based on quantum deep network (QUEEN). Specifically, it employs a dual-branch structure, an affine-computing feature (ACF) branch and a QUEEN branch, to offer fundamentally distinct representations. These features are then fused for the subsequent classification. HydroQUEEN well detects high-precision inland waterbody textures over the Amazon basin area, demonstrating its superiority over the existing global hydrography maps.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.