Essential for services such as communication, navigation, and weather prediction, satellite constellations must minimize loss of coverage while being subject to constraints on space traffic and the number of satellites available. Genetic algorithms (GAs) offer a versatile method of optimization with demonstrated success in applied problems. In the case of a computationally expensive problem, the necessity of repeated fitness evaluations prevents convergence of a GA in a feasible timeframe. A potential solution to this dilemma is to implement a computationally-efficient surrogate model to estimate the computationally-expensive objective function value. Recent advances in machine learning methods, in particular neural networks, make them a compelling candidate as a surrogate function. A GA incorporating an ensemble of neural networks as a surrogate function is applied to the problem of constellation design. We demonstrate that through the incorporation of an ensemble of neural networks, we can improve function evaluation and optimization runtime for the GA.