Mapping Oxidation and Wafer Cleaning to Device Characteristics Using Physics-Assisted Machine Learning

Abstract

It is always highly desired to have a well-defined relationship between the chemistry in semiconductor processing and the device characteristics. With the shrinkage of technology nodes in the semiconductors roadmap, it becomes more complicated to understand the relation between the device electrical characteristics and the process parameters such as oxidation and wafer cleaning procedures. In this work, we use a novel machine learning approach, i.e., physics-assisted multitask and transfer learning, to construct a relationship between the process conditions and the device capacitance voltage curves. While conventional semiconductor processes and device modeling are based on a physical model, recently, the machine learning-based approach or hybrid approaches have drawn significant attention. In general, a huge amount of data is required to train a machine learning model. Since producing data in the semiconductor industry is not an easy task, physics-assisted artificial intelligence has become an obvious choice to resolve these issues. The predicted C – V uses the hybridization of physics, and machine learning provides improvement while the coefficient of determination ( R 2 ) is 0.9442 for semisupervised multitask learning (SS-MTL) and 0.9253 for transfer learning (TL), referenced to 0.6108 in the pure machine learning model using multilayer perceptrons. The machine learning architecture used in this work is capable of handling data sparsity and promotes the usage of advanced algorithms to model the relationship between complex chemical reactions in semiconductor manufacturing and actual device characteristics. The code is available at .

Optical Proximity Correction Using Machine Learning Assisted Human Decision

“…It is important to justify the name of the proposed algorithm, i.e., ML-assisted human decision. There have been a significant amount of works using physics-or domain-knowledge-assisted ML [40], [41], [42], [43], [44], [45], [46], [47]. The incorporation of domain knowledge into ML algorithms can be done in a variety of practices, and the common trait is that both domain knowledge-based information and ML-based information are put into a model of a certain kind to form a hybrid model.…”

Applications and potentials of machine learning in optoelectronic materials research: An overview and perspectives

“…By predicting device properties, unnecessary device fabrication or expensive experimentation can be avoided, thus providing a more cost-effective route to device optimization. Using physics-assisted ML, Pratik et al [30] established the relationship between process conditions and device capacitance-voltage (C-V ) curves. The models were trained using theoretical C-V data at frequencies of 1 kHz, 3 kHz, 5 kHz, 10 kHz, 50 kHz, and 100 kHz and measured C-V data at 1 kHz and 100 kHz.…”

“…[26][27][28][29] Deep learning (DL) has been widely used in optoelectronic materials and often necessitates substantial volumes of data. Convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), and graph neural network (GNN) are mainly applied to properties prediction, [30][31][32] structure prediction, [33][34][35] image analysis, [36] and optimization. [37] Nevertheless, numerous material or device datasets in practice fall short of achieving such scale.…”

“…Transfer learning (TL) emerges as a valuable technique, enabling DL models to be effectively trained even when confronted with limited data. [30,31] With the development of ML in materials, advanced ML algorithms have gradually been applied to optoelectronics, providing more intelligent, efficient, and adaptive methods for the research and application of optoelectronic materials. Active learning is used in applications such as property prediction, [38] discovering new materials, [39] and capturing atomic force fields.…”

Meta-Learned and TCAD-Assisted Sampling in Semiconductor Laser Annealing

“…Theory-assisted ML has been drawing great attention over the past few years. − The main idea is to count on prior knowledge and theory to reduce the loading of ML model training in terms of the required sample number and prediction accuracy. Various techniques have been proposed to realize domain knowledge assistance, including semisupervised learning, Bayesian statistics, supervised learning incorporating domain knowledge in some context, and theory-informed reinforcement learning (RL) .…”