Adoption of new, low-carbon processes like adsorption-based separation and refrigeration is essential to drive Europe’s net zero transition and achieve the targets of the European Green Deal. Advanced porous nanomaterials like metal-organic frameworks (MOFs) are key enabling technologies to achieve this goal, however their adoption is stymied by a chicken-and-egg problem: identifying the most cost-effective MOF for each application, and investing sufficient research time to reduce synthesis costs for the best candidates. In this fellowship I will address this dual challenge by developing a holistic platform to systematise MOF synthesis methodology research, hence both accelerating and generalising the hunt for an optimal synthesis method. Using a combination of text mining and molecular simulations, I will construct a semantic knowledge graph representation for the synthesis of the common MOF UiO-66, creating a database of synthesis methods connected to to material quality profiles. Once created, I will develop a UiO-66 synthesis “oracle” – a machine learning model which can generate novel synthesis procedures from target material quality profiles. I will then refine the synthesis oracle functions experimentally using Bayesian active learning to identify the global optimum synthesis parameters with respect to several quality metrics. Finally, I will transfer the UiO-66 synthesis oracle to a family of related MOF materials, using further lab synthesis and active learning to fine-tune the quality of these secondary MOFs. This new paradigm in nanomaterial synthesis optimisation will be transformative in the field of synthesis optimisation and intensification, representing a novel approach that is generalisable to any synthesis target. In turn, completion of this fellowship will perfectly position me to transition into an independent academic career at the interface of digital chemistry and process intensification.