Sensitivity Analysis of Process Parameters on Deposition Quality and Multi-Objective Prediction in Ion-Assisted Electron Beam Evaporation of Ta2O5 Films

Tantalum pentoxide (Ta₂O₅) films deposited on fused silica substrates are critical components of high-power laser systems. Ion-assisted electron beam evaporation (IAD-EBE) is the mainstream technique for fabricating Ta₂O₅ films. However, it commonly requires extensive experimental efforts for deposition quality optimization, while each coating cycle is extremely time-consuming. To solve this issue, this work establishes a dataset targeting the surface roughness (<i>Rq</i>) and refractive index (<i>n</i>) of Ta₂O₅ films using atomic force microscopy, as well as ellipsometer and deposition experiments. Influence of assisting ion source beam voltage (<i>V</i>)/current (<i>I</i>) and Ar (<i>Q</i>₁)/O₂ (<i>Q</i>₂) flow rate on the <i>n</i> and <i>Rq</i> of Ta₂O₅ films are analyzed. Combining energy-field mechanism analysis with a Bayesian optimization approach (PI-BO), both deposition quality prediction and feature analysis of process parameters are achieved. The determination coefficient/mean absolute error for the prediction models of <i>n</i> and <i>Rq</i> reach 0.927/0.013 nm and 0.821/0.049 nm, respectively. Based on sensitivity analysis, the weight factors of <i>V</i>, <i>I</i>, <i>Q</i>₁, and <i>Q</i>₂ affecting <i>n</i>/<i>Rq</i> of Ta₂O₅ films are determined to be 0.616/0.274, 0.199/0.144, 0.113/0.582, and 0.072/0.000. <i>V</i> and <i>Q</i>₂ are identified as the core factors for regulating deposition quality. The optimal ranges for <i>V</i> and <i>Q</i>₂ are 600~700 V and 70~80 sccm, respectively. This study proposes a PI-BO method for predicting <i>Rq</i> and <i>n</i> of Ta₂O₅ films under small-data conditions, while determining the preferred parameter ranges and their sensitivity weight factors. These findings provide effective theoretical support and technical guidance for IAD-EBE strategy design and optimization of optical films in high-power laser systems.