This work illustrates the use of artificial neural network modeling to study and characterize broadband blade-wake interaction noise from hovering sUAS rotors subject to varying airfoil geometries, rotor geometries, and operating conditions. Design of Experiments was used to create input feature spaces over 9 input features: the number of rotor blades, rotor size, rotor speed, the amount of blade twist, blade taper ratio, tip chord length, collective pitch, airfoil camber, and airfoil thickness. A high-fidelity strategy was then implemented at the discrete data points defined by the designed input feature spaces to design airfoils and rotor blades, predict the unsteady rotor aerodynamics and aeroacoustics, and isolate the blade-wake interaction noise from the acoustic broadband noise, which was then used for prediction model training and validation. An artificial neural network tool was developed and implemented into NASA's ANOPP2 code and was used to identify an optimal prediction model for the nonlinear functional relationship between the 9 input features and blade-wake interaction noise. This optimal artificial neural network was then validated over test data, and exhibited prediction accuracy over 91% for data previously unseen by the model. First- and second-order sensitivity analyses were then conducted using the developed artificial neural network tool and it was seen that input features which serve to directly modify the thrust coefficient, such as airfoil camber and collective pitch, had a dominant effect over blade-wake interaction noise, followed by second-order interaction effects related to the mean rotor solidity. The optimal prediction model along with aerodynamic simulations were used to further study the effect of varying input features on blade-wake interaction noise and three types of blade-wake interaction noise were identified. Blade-wake interaction noise caused by impingement of the turbulence entrained in a tip vortex on the leading edge of a subsequent rotor blade showed to be the most prominent type of blade-wake interaction noise, exhibiting an acoustic contribution upward of 7 dB. Blade-wake interaction noise caused by a direct impingement of a tip vortex on the leading edge of a subsequent rotor blade had the second largest acoustic significance, exhibiting roughly 6 dB of broadband noise. The third, and least significant type of blade-wake interaction noise was shown to be caused by impingement of a blade-wake sheet on the mid-span of a subsequent rotor. This last type of blade-wake interaction noise was seen to only occur in the turbulent-wake operating state and possibly mild vertical descent conditions, and had approximately a 2.5 dB acoustic contribution.