Countries have begun to adopt green energy initiatives requiring high percentages of power generation to come from clean energy sources. Both onshore and offshore wind energy generates reliable clean energy. Due to this, wind energy has had an exponential growth in global adoption. While wind energy is increasingly adopted by several countries, there is a need to address avian and bat interactions on wind turbines. This masters project presents an automatic event detection system built and placed on a wind turbine to monitor and detect bird and bat interactions around wind turbines. The system was tested at the NREL National Wind Technology Center in Boulder, CO on the GE 1.5MW turbine. It includes multiple units to detect impacts through audio, visual, and vibration data. These units are vibration boxes located at the root of the blade that take in vibration and video data to detect and confirm impacts. Patches, located along the blade, with contact microphones to detect low mass impacts. General monitoring of the wind turbine is done by the nacelle unit utilizing ultrasonic microphones and a 360-degree camera. Low light level monitoring is done with an infrared camera located at the root of the blade. Vibration impact monitoring and video confirmation is done by the patches and vibration boxes for low mass projectiles. The infrared camera uses a convolutional neural network to detect impacts, analyzing footage of simulated bird interactions. The IR camera shows promise and success for low light level monitoring on static blades, but fails on dynamic blades due to image blur and similar background colors. The patches and vibration boxes were successful at detecting vibrations and confirming impacts for projectiles of varying mass. The nacelle had successful audio monitoring, but power and connectivity issues caused the unit to be unreliable and fail to record video data. Overall, the system demonstrates an advanced approach at monitoring and detecting simulated wildlife interactions on the wind turbine blades.