Effects of deposition precursors of hydrogenated amorphous carbon films on the plasma etching resistance based on mass spectrometer measurements and machine learning analysis

Kurokawa, Jumpei; Kondo, Hiroki; Tsutsumi, Takayoshi; Ishikawa, Kenji; Sekine, Makoto; Hori, Masaru

doi:10.1016/j.vacuum.2022.111351

Cited by 11 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following this improvement, the second requirement is fast calculation that can keep pace with real process times. Currently, approaches such as machine learning, [212][213][214][215][216][217] the fusion of physical models with machine learning, 218,219), and surrogate models 220,221) are being adopted to solve this issue. Figure 45 218) presents an example of a fusion model, which uses incident gas fluxes derived from machine learning with real-time plasma monitoring, EES, and PQC data as inputs, while process properties such as feature-scale profiles, damage distributions, and film properties are simulated by a physical model.…”

Section: Future Perspectivesmentioning

confidence: 99%

Review and perspective of dry etching and deposition process modeling of Si and Si dielectric films for advanced CMOS device applications

Kuboi

2024

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

Dry etching and deposition of Si and Si dielectric films are critical processes for achieving of high performance in advanced complementary metal-oxide-semiconductor (CMOS) devices. To accurately predict and control fluctuations in these process properties during mass production, it is essential that dry process simulation technology considers various factors. These include fluctuations in plasma-chamber wall interaction, effects of by-products on critical dimensions, Si recess dependence on wafer open area ratios and local pattern structures, the time-dependent distribution of plasma-induced damage associated with feature-scale profiles, and film properties such as density, permeability, and adhesion. Addressing these considerations can overcome issues with conventional simulations that lack the accuracy required for mass production. This paper reviews these advanced simulation technologies and discusses the perspective of fusion physical models with machine learning, incorporating real-time monitoring in manufacturing equipment, known as process informatics. This approach is anticipated to usher in the era of full digital twins.

show abstract

Section: Future Perspectivesmentioning

confidence: 99%

Review and perspective of dry etching and deposition process modeling of Si and Si dielectric films for advanced CMOS device applications

Kuboi

2024

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

show abstract

“…After this improvement, fast calculation comparable to process time is the next issue as the second factor. Currently, machine learning, 100 – 104 fusion physical model with machine learning, 105 , 106 and surrogate models 107 , 108 are adopted to solve this issue. Figure 48 shows an example of a fusion model (or hybrid model) in which incident gas fluxes derived from machine learning using real-time monitoring of plasma and EES were used as an input and feature scale profiles, and damage distributions were simulated by a physical model.…”

Section: Future Perspectivesmentioning

confidence: 99%

Review and future perspective of feature scale profile modeling for high-performance semiconductor devices

Kuboi

2023

J. Micro/Nanopattern. Mats. Metro.

View full text Add to dashboard Cite

.Modeling and simulation of feature scale profiles, including damage distributions and film properties in dry etching (continuous wave, pulse, cycle, and atomic layer etching) and deposition processes (chemical vapor, physical vapor, and atomic layer deposition) using string, shock tracking, level-set, and cell removable (or voxel) methods, are useful for predicting process properties and gain insights into the variation mechanisms for realizing high performance of advanced complementary metal-oxide semiconductor devices and have been comprehensively reviewed in this work. The future perspective has also been discussed from the viewpoint of a fusion physical model with machine learning using real-time monitoring of the manufacturing equipment, so-called process informatics. Furthermore, after the introduction of quantum computing for process simulations on atomic scales, the epoch of full digital twins might be realized.

show abstract

“…The prediction accuracy was improved by the use of Shapley additive explanation value (SHAP) in ML. 306)…”

Section: Advanced Process Control Of Chemical Vapor and Atomic Layer ...mentioning

confidence: 99%

Science-based, data-driven developments in plasma processing for material synthesis and device-integration technologies

Kambara

Kawaguchi

Lee

et al. 2022

Jpn. J. Appl. Phys.

Self Cite

View full text Add to dashboard Cite

Low-temperature plasma processing technologies is essential for material synthesis, device fabrication, and surface treatment. The development of plasma-related products and services requires an understanding of the multiscale complex behaviors of plasma and the hierarchical integration of plasma generation, energy and mass transports through sheath region, surface reactions, and other processes. The importance of science-based and data-driven approaches to controlling systems is argued. The state-of-the-art of deep learning, machine learning, and artificial intelligence in low-temperature plasma science and technology is reviewed. In this review, the requirements and challenges for plasma parameter prediction and processing recipe discovery are asserted by researchers in the fields of material science and plasma processing. It also outlined a science-based, data-driven approach for development of virtual metrology in plasma processes.

show abstract

Effects of deposition precursors of hydrogenated amorphous carbon films on the plasma etching resistance based on mass spectrometer measurements and machine learning analysis

Cited by 11 publications

References 35 publications

Review and perspective of dry etching and deposition process modeling of Si and Si dielectric films for advanced CMOS device applications

Review and perspective of dry etching and deposition process modeling of Si and Si dielectric films for advanced CMOS device applications

Review and future perspective of feature scale profile modeling for high-performance semiconductor devices

Science-based, data-driven developments in plasma processing for material synthesis and device-integration technologies

Contact Info

Product

Resources

About