Cross-Domain Adaptation Dataset for Hyperspectral Wetland Images

Wetland ecosystems are affected by climate change, tidal fluctuations, and human activities, causing significant spectral variations across different times and locations. These variations challenge hyperspectral classification models, limiting their generalization in cross-domain scenarios. However, most existing hyperspectral datasets focus on a single time point or region, lacking standardized resources for cross-temporal and cross-scene studies, which restricts the application of unsupervised domain adaptation (UDA) methods in wetland remote sensing. To address this issue, we constructed two hyperspectral wetland image domain adaptation datasets: the Cross-Temporal Dataset and the Cross-Scene Dataset, both acquired by the ZY1-02D satellite. These datasets are designed to alleviate the data scarcity problem in cross-domain adaptation research for hyperspectral wetland imagery, providing high-quality experimental data to support the development and evaluation of domain adaptation methods.