Porous media represent a wide range of materials that have yet to be fully understood and present a challenge in being harnessed to their full capacity. From rocks to bones, the ubiquity of porous materials across engineering disciplines cannot be overstated. However, due to the non-uniformity of their structure, it has been challenging to accurately assess material performance across a wide variety of scenarios, from strength to internal diffusivity. It has been shown that this complexity may boil down to the great heterogeneity and stochasticity of porous materials' microstructures. Unfortunately, due to the multiscale effects and multiphysics inherent to these systems, an exact relationship between a porous material's microstructure to a material's structural performance remains elusive. Although destructive testing and finite element analysis (FEA) are proven methods for calculating a porous material's properties, the former is costly, wasteful and largely impractical at larger scales, and the latter is computationally intensive and time-consuming. Machine learning has proven itself over the past few decades as a method of expediting the discovery of correlations within data and creating powerful predictive models. However, common obstacles for creating an effective machine learning model include having a lack of data for training the model and having an over complicated set or unnecessary number of input features. In order to overcome the challenges and drawbacks of using these various methods, we have developed a methodology for analyzing porous material structure-property relationships that includes generating realistic synthetic structures, extracting relevant and useful geometric descriptors for defining the structures, and using these descriptors of reduced complexity to train a machine learning model that predicts the mechanical response of the structure from its descriptors. Through this work we aim to accelerate the analysis of porous material structure-property relationships via a machine learning model trained on microstructural features.