Quantum computers have shown their potential to revolutionize computing due to their exponentially faster speeds over current classical (non-quantum) digital computers. To evaluate if quantum repeaters can be trained to perform their task and remain resistant to noise and decoherence using machine learning. Using a simulation of a quantum machine in MATLAB, a system of 2-qubits is trained to sufficiently low error using machine learning. The system is then scaled up to 4-,6-, and 8-qubits using transfer learning of the previous system’s parameters, with no additional training. Once complete, noise and decoherence are added to the systems and tested to evaluate their resilience. Research is still in progress. Preliminary results show that the initial system of two qubits can be trained to very low errors, on the order of 10-7. Increasing system size to 4+ qubits led to only a very slight increase in error to a magnitude of 10-4, still less than 0.1%. Testing on a trained system demonstrated that the system could handle noise and decoherence up to a magnitude of 10-5 with no issue. Because of its flat geography and position, Kansas could become home to quantum networking and quantum satellite communications, making it a leader in groundbreaking quantum repeaters in quantum communication technology in the US and the world.