Block copolymers are known to self-assemble into a multitude of phases with vastly different geometries, depending on the ordering of its molecules. Due to their highly regular patterns, these phases are attractive for applications involving ordered nanoscale porous materials like high-surface area separation membranes, catalysts, solar cells, and energy storage devices. In order to tap into the unique properties of the different phases, we need to be able to design and control their formation. This requires a deeper understanding of the nucleation and growth mechanisms through which they self-assemble.Paramount to understanding and controlling this “order” is to have good “order parameters (OP)”, variables that can be used to track the changes occurring in the system as it transitions from disorder to order. Oftentimes however, the definition of an optimal OP is highly nontrivial especially for complex macromolecular systems like block copolymers, and there exists a need to develop simple and general strategies for identifying known phase transitions. In this work, we have attempted to address this challenge by developing a pattern recognition-based framework to track the kinetics of order-disorder phase transitions in soft materials, including common block copolymer systems like the lamellar, cylinder, gyroid as well as other bicontinuous phases like the single diamond formed from oligomeric molecules. We have found our proposed framework to be successful at capturing this phase transition, while also proving to be a suitable tool to map the corresponding disorder to order free energy profiles, via different sampling methods. While the technique has been developed and studied on common block copolymer systems, the method is general enough to be applied to other systems, and we hope that it can be leveraged to uncover more interesting phase transitions in material studies.