Defining inkjet printing conditions of superconducting cuprate films through machine learning.

The design and optimization of new processing approaches for the development of rare earth cuprate (REBCO) high temperature superconductors is required to increase their cost-effective fabrication and promote market implementation. The exploration of a broad range of parameters enabled by these methods is the ideal scenario for a new set of high-throughput experimentation (HTE) and data-driven tools based on machine learning (ML) algorithms that are envisaged to speed up this optimization in a low-cost and efficient manner compatible with industrialization. In this work, we developed a data-driven methodology that allows us to analyze and optimize the inkjet printing (IJP) deposition process of REBCO precursor solutions. A dataset containing 231 samples was used to build ML models. Linear and tree-based (Random Forest, AdaBoost and Gradient Boosting) regression algorithms were compared, reaching performances above 87%. Model interpretation using Shapley Additive Explanations (SHAP) revealed the most important variables for each study. We could determine that to ensure homogeneous CSD films of 1 micron thickness without cracks after the pyrolysis, we need average drop volumes of 190-210 pl, and no. of drops between 5000 and 6000, delivering a total volume deposited close to 1 μl.