(195e) Microscopic Modeling and Optimal Operation of Thermal Atomic Layer Deposition

Atomic layer deposition (ALD) process has been widely adopted by industry to produce thin-film materials that meet the requirements of major design breakthroughs in semiconductor industry [1]. Despite its popularity, the ALD process remains costly and it is desirable to develop an inexpensive high-fidelity model to characterize the process [2]. Recently, Shirazi and Elliot developed a Density Functional Theory (DFT)-based simulation of the HfO2 deposition on laboratory scale [3]. Motivated by this work, a similar approach is expanded to develop a comprehensive framework for industrial-scale first-principles-based microscopic modeling, data-driven input/output modeling and optimal operation of thermal ALD of SiO2 thin-films using bis(tertiary-butylamino)silane (BTBAS) and ozone as precursors [4].

In this work, we first perform first-principles-based DFT calculations of the key thermodynamic and kinetic parameters, which are then used in the microscopic modeling of the ALD process. Subsequently, a detailed microscopic model is constructed, accounting for the microscopic lattice structure and atomic interactions, as well as multiple microscopic film growth processes including physisorption, abstraction and competing chemical reaction pathways. Kinetic Monte-Carlo (kMC) algorithms are utilized to obtain computationally efficient microscopic model solutions while preserving model fidelity. The obtained kMC simulation results are used to train Artificial Neural Network (ANN)-based data-driven models that capture the relationship between operating process parameters and time to ALD cycle completion. Specifically, a dense two-hidden-layer feed-forward ANN is constructed to find a feasible range of ALD operating conditions accounting for industrial considerations, and a Bayesian Regularized ANN is constructed to implement the cycle-to-cycle optimization of ALD cycle time. Extensive simulation results demonstrate the effectiveness of the proposed approaches. The kMC models successfully achieves a growth per cycle (GPC) of 1.8 Å per cycle, which is in the range of reported experimental values. The ANN models accurately predict deposition time to steady-state from the given operating condition input, and the cycle time optimization using BRANN model reduces the conventional BTBAS cycle time by 60%.