Bayesian statistics is an important formulism and means by which to understand complex relationships which are inherent in many forensic and intelligence investigations. The tool, however, is still met with ambivalence, mistrust, and confusion highlighting a need to demonstrate how it can be practically used. The combination of comprehending riverine/estuarine fluid structure and understanding statistical uncertainty afforded by a simple statistical model can assist evidential search teams make the best use of time and other resources vital to forensic problems. Naïve Bayesian belief network modeling is applied to direct numerically simulated imagery of oscillatory sediment-laden flow to illustrate the feasibility of creating a simple model to aid evidential search and retrieval field personnel recover sub-surface evidence. A statistical system model is created from numerically simulated data which captures the statistical interrelationship of surface layer sediment concentration, pressure, and vertical velocity turbulent eddy information with the sub-surface Reynolds stress responsible for moving subsurface evidence. From a diagnostic reasoning viewpoint, initial results suggest that robustly inferring the specific direction of tidal stress responsible for moving subsurface evidence from surface sediment concentration signatures may be a difficult task. However, from a prognostic reasoning viewpoint, preliminary model results suggest that large sediment concentration signatures visible to the naked eye may indeed be strongly linked to large tidal efflux rather than influx. This statistical result narrows evidential search periods which can be important in solving forensic problems in a timely fashion. The model formulism used allows for the ability to statistically characterize flow structure at depth from observations taken across a surface boundary layer, making the results relevant to image analysis from aerial vehicles such helicopters, drones, and high-resolution