Next generation materials demand silicon era engineering. In order to meet the challenge, we develop methods to run multiple experiments simultaneously in combination with machine learning. We combines Material Science and experience with colloidal synthesis with Data Science to discover breakthrough materials properties for energy and opto-electronic devices. Traditional Edisonian approach to explore new materials' properties can be slow and expensive. However, by integrating robotic synthesis and machine learning we aim to overcome this bottleneck leveraging the machine's capability to comprehend multi-dimensional data beyond human visualization. A key focus is understanding colloidal perovskite and how various features, like growth temperature or precursors reactivity, influence perovskite nanocrystals' dimensions
and shapes. We envision a future self-driving synthetic lab where automated high-throughput processes work alongside machine learning predictive models, ushering the era of Big Data into Material Science.