Modeling reactive ion etching of silicon dioxide films using neural networks

Silicon dioxide films are useful as interlayer dielectrics for integrated circuits and multichip modules. Reactive ion etching (RIE) in RF glow discharges is used extensively to form via holes in SiO₂ between metal layers of a multichip module. However, the precise modeling of RIE is difficult due to the extremely complex nature of particle dynamics within a plasma. Recently, empirical RIE models derived from neural networks have been shown to offer advantages in both accuracy and robustness over more traditional statistical approaches. In this paper, neural networks are used to build models of etch rate, anisotropy, uniformity, and selectivity for SiO₂ films etched in a chloroform and oxygen plasma. Back-propagation neural nets were trained on data resulting from a 2⁴ factorial experiment designed to characterize etch variation with RF power, pressure and gas composition. Etching took place in a Plasma Therm 700 series RIE system. Excellent agreement between model predictions and measured data was obtained