Magnetic reconnection is a fundamental plasma process which facilitates the conversion of magnetic energy to particle energies. This local process both contributes to and is affected by a larger system, being dependent on plasma conditions and transporting energy around the system, such as Earth's magnetosphere. When studying the reconnection process with in situ spacecraft data, it can be difficult to determine where spacecraft are in relation to the reconnection structure. In this work, we use k-means clustering, an unsupervised machine learning technique, to identify regions in a 2.5-D PIC simulation of symmetric magnetic reconnection with conditions comparable to those observed in Earth’s magnetotail. This allows energy flux densities to be attributed to these regions. The ion enthalpy flux density is the most dominant form of energy flux density in the outflows, agreeing with previous studies. Poynting flux density may be dominant at some points in the outflows and is only half that of the Poynting flux density in the separatrices. The proportion of outflowing particle energy flux decreases as guide field increases. We find that k-means is beneficial for analysing data and comparing between simulations and in situ data. This demonstrates an approach which may be applied to large volumes of data to determine statistically different regions within phenomena in simulations and could be extended to in situ observations, applicable to future multi-point missions.