Data-driven and interpretable machine learning accelerates discovery of Li 4 SrCaSi 2 O 8 -based microwave ceramics for high-performance dielectric antennas

High-performance dielectric antenna has pursued high quality factor (Q×f) for microwave ceramics. Nevertheless, the cross-laboratory inconsistency in reported Q×f would confuse the invention of materials system, owing to divergent preparation and measurement protocols. Herein, based on a self-consistent dataset, an interpretable machine learning framework is proposed to unveil the structure-property relationship and consequently guide the compositional design of candidate microwave ceramic Li4SrCaSi2O8. Through feature engineering, nine critical features are identified in which the Si/Li atomic mass ratio (Si/Li-AW), Si/Sr ionic radius ratio (Si/Sr-IR), and total electronegativity of cations (TEC) are found to be predominant. Interpretability technologies further reveal that a higher Si/Li-AW coupled with lower Si/Sr-IR and TEC is conductive to the increase in Q×f value for the chosen Decision Tree model. Guided by these insights, Sn4+-doped microwave ceramic Li4SrCaSi1.98Sn0.02O8 is created with a Q×f value up to 83526 GHz, the origin of which is elucidated by P–V–L theory combined with first-principles calculations and infrared spectroscopy. Such an optimized material is ultimately verified by a microstrip patch antenna with a high radiation efficiency of 81.12% and a gain of 5.94 dB in the C-band.