The traditional mathematical approach to deriving Position Navigation and Timing (PNT) data from Global Navigation Satellite Systems (GNSS) does make some assumptions about the data being received. Machine Learning (ML) techniques could be used to instead of these traditional techniques to integrate GNSS signals and Signals of Opportunity (SOOP) signals in a way that doesn’t make these assumptions and can therefore provide better position solutions utilising GNSS and SOOP from terrestrial or space-based sources. This project, Machine Learning Applied to Signals of Opportunity (MaLASO), will study and demonstrate the benefits of using SOOP (both terrestrial and space-based) for navigation and then demonstrate the benefits of utilising SOOP integrated with GNSS using ML techniques and hardware designed to provide a mass-market solution in a demanding and challenging outdoor environment.