Freshwater mussels are often distributed throughout deep, turbid, and non-wadeable streams of the Southeastern Coastal Plain. These conditions pose significant challenges to the identification and characterization of mussel habitats, and the development of standardized mussel sampling approaches across landscapes. Nearly twenty years ago, a type of sonar called side scan sonar (SSS) first appeared on the recreational market, opening the door to underwater investigation via remote sensing to anglers and biologists alike. Side scan sonar produces a picture-like image of the underwater environment across wide swaths (up to ~90 meters). Data can be collected relatively quickly (8 km/hr), processed into sonar image mosaics, and then interpreted to produce classified habitat maps. Until recently map production was a labor intensive step, requiring significant expertise, but newly emerging (and free) software tools based on machine learning make it possible to both process raw data into mosaics and automatically produce classified substrate maps in a fraction of the time. The utility of these maps for designing sampling approaches, and developing models of the distribution and abundance of mussels via habitat associations is under exploration, and access to these no-cost tools offers the promise of greater rates of adoption and implementation in the future. Now is the time to harness the power of imaging technology and automation to advance mussel conservation at the landscape scale.