Multi-source remote sensing refers to the acquisition and integrated use of remotely sensed information originating from different sensors, platforms, observation modalities, or data sources to provide complementary information about the same geographic phenomenon ^[1][2]. The sources may differ in sensing modality, spatial or spectral characteristics, acquisition platform, or observation time, resulting in datasets that contain heterogeneous but potentially complementary information ^[2][3]. The central characteristic of multi-source remote sensing is therefore the combination of information that cannot be fully represented by a single observation source. Integration may involve optical, multispectral or hyperspectral imagery, synthetic aperture radar, LiDAR, thermal observations, and other remotely sensed or ancillary data ^[1][3]. Such integration is commonly implemented through data fusion, which can operate at the data or pixel level, feature level, or decision level, depending on the stage at which information from different sources is combined ^[1][4]. Effective multi-source integration requires consideration of differences in spatial resolution, spectral characteristics, acquisition geometry, temporal coverage, and data registration ^[2][3]. Multi-source remote sensing thus provides a framework for combining heterogeneous observations into a more comprehensive representation of geographic or environmental phenomena.