<p>Chromophoric dissolved organic matter (CDOM) is a key constituent of inland waters, and significantly influences aquatic light climates, water quality, and biogeochemical processes. At present, the optical complexity and spatial variability of CDOM have hindered the development of a universally applicable remote sensing quantification model. Recent advances are overcoming these challenges by integrating state-of-the-art remote sensing technologies, high-resolution satellite data, and advanced computational modeling to characterize CDOM dynamics across spatial and temporal scales. Platforms such as Google Earth Engine (GEE) have emerged as powerful tools for long-term CDOM monitoring, as Landsat and Sentinel sensors are being widely utilized. Obtaining high-quality imagery for optically complex and turbid waters requires robust atmospheric correction algorithms and suitable sensor configurations. In retrieval methodology, a variety of innovative band ratio indices and machine learning techniques have been developed, achieving regional estimation accuracy above 75%. The combination of enhanced satellite resolution (radiometric, temporal, and spatial) with machine learning or artificial intelligence (AI) approaches rooted in optical theory opens a promising avenue to improve model generalizability and decode CDOM’s intricate composition. We highlight that cross-regional comparative studies are crucial for large-scale CDOM monitoring. Moreover, CDOM retrieval is increasingly applied to address broader environmental issues, including aquatic carbon cycling and the behavior of co-transported contaminants. Future efforts should prioritize a deeper mechanistic understanding of CDOM dynamics and advance AI models integrated with bio-optical theory and multi-source image fusion.</p>