**ZeoSyn: A Comprehensive Zeolite Synthesis Dataset Enabling Machine-Learning Rationalization of Hydrothermal Parameters** Zeolites, nanoporous aluminosilicates with well-defined structures, are versatile materials used in catalysis, gas separation, and ion exchange. Hydrothermal synthesis is a widely used method for zeolite production, offering control over composition, crystallinity, and pore size. However, the complex interplay of synthesis parameters necessitates a comprehensive understanding of synthesis-structure relationships to optimize the process. Previous datasets on zeolite synthesis are limited in scale and scope, covering only a subset of parameters. The authors present ZeoSyn, a comprehensive dataset of 23,961 zeolite hydrothermal synthesis routes, encompassing 233 zeolite topologies and 921 organic structure-directing agents (OSDAs). Each synthesis route includes detailed parameters such as gel composition, reaction conditions, OSDAs, and the resulting zeolite products. Using ZeoSyn, the authors develop a machine learning classifier that predicts the resultant zeolite with over 70% accuracy. They employ SHapley Additive exPlanations (SHAP) to identify key synthesis parameters for over 200 zeolite frameworks and their composite building units (CBUs). The dataset also includes negative data, such as failed syntheses, which is crucial for understanding the limitations of synthesis parameters. The study reveals that gel composition, reaction conditions, and OSDAs play significant roles in driving zeolite crystallization. For example, low crystallization temperatures favor the formation of small-pore zeolites like LTA, while high temperatures are necessary for larger-pore zeolites. The SHAP analysis provides insights into the impact of synthesis parameters on specific zeolite frameworks and CBUs, highlighting the importance of inorganic and OSDA components in gel-dominated, OSDA-dominated, and balanced syntheses. The authors demonstrate the utility of ZeoSyn and SHAP analysis in rationalizing synthesis parameters for phase-selective and intergrowth synthesis. For instance, they show how to design synthesis conditions to achieve phase-selective synthesis of TON and MFI zeolites, and how to promote the crystallization of two frameworks within the same crystal, such as FAU and EMT intergrowths. In conclusion, ZeoSyn is the largest and most comprehensive dataset on zeolite synthesis to date, enabling advanced machine learning models to predict and rationalize synthesis parameters. This dataset has the potential to guide the discovery of new zeolite frameworks and improve the efficiency of zeolite synthesis processes.**ZeoSyn: A Comprehensive Zeolite Synthesis Dataset Enabling Machine-Learning Rationalization of Hydrothermal Parameters** Zeolites, nanoporous aluminosilicates with well-defined structures, are versatile materials used in catalysis, gas separation, and ion exchange. Hydrothermal synthesis is a widely used method for zeolite production, offering control over composition, crystallinity, and pore size. However, the complex interplay of synthesis parameters necessitates a comprehensive understanding of synthesis-structure relationships to optimize the process. Previous datasets on zeolite synthesis are limited in scale and scope, covering only a subset of parameters. The authors present ZeoSyn, a comprehensive dataset of 23,961 zeolite hydrothermal synthesis routes, encompassing 233 zeolite topologies and 921 organic structure-directing agents (OSDAs). Each synthesis route includes detailed parameters such as gel composition, reaction conditions, OSDAs, and the resulting zeolite products. Using ZeoSyn, the authors develop a machine learning classifier that predicts the resultant zeolite with over 70% accuracy. They employ SHapley Additive exPlanations (SHAP) to identify key synthesis parameters for over 200 zeolite frameworks and their composite building units (CBUs). The dataset also includes negative data, such as failed syntheses, which is crucial for understanding the limitations of synthesis parameters. The study reveals that gel composition, reaction conditions, and OSDAs play significant roles in driving zeolite crystallization. For example, low crystallization temperatures favor the formation of small-pore zeolites like LTA, while high temperatures are necessary for larger-pore zeolites. The SHAP analysis provides insights into the impact of synthesis parameters on specific zeolite frameworks and CBUs, highlighting the importance of inorganic and OSDA components in gel-dominated, OSDA-dominated, and balanced syntheses. The authors demonstrate the utility of ZeoSyn and SHAP analysis in rationalizing synthesis parameters for phase-selective and intergrowth synthesis. For instance, they show how to design synthesis conditions to achieve phase-selective synthesis of TON and MFI zeolites, and how to promote the crystallization of two frameworks within the same crystal, such as FAU and EMT intergrowths. In conclusion, ZeoSyn is the largest and most comprehensive dataset on zeolite synthesis to date, enabling advanced machine learning models to predict and rationalize synthesis parameters. This dataset has the potential to guide the discovery of new zeolite frameworks and improve the efficiency of zeolite synthesis processes.