Estimation of the diffusion coefficient of GaSb in InSb melt using Bayesian optimization and the ISS experimental results

Ghritli, Rachid; Okano, Yasunori; Inatomi, Yuko; Sekimoto, Atsushi; Dost, S.

doi:10.1016/j.jcrysgro.2021.126280

Cited by 4 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following assumptions were made in the present numerical simulation model: (that corresponds to a typical average gravity level observed on the ISS) was used in the simulation.Three calculation regions are considered: Crystal, BN crucible and Quartz ampoule whose physical properties can be found in our previous article. 26) In Table I, we listed only the operational conditions and properties of the crystals relevant to the current study. Under the assumptions mentioned above, the governing equations of the liquid phase, namely continuity, momentum balance, energy, and mass transport equations are given as:…”

Section: Governing Equations and Associated Boundary Conditionsmentioning

confidence: 99%

“…In our previous work, 26) Bayesian optimization was utilized to construct an equation relating the diffusion coefficient of GaSb in InSb melt to its concentration. This allowed us to more accurately estimate the crystal growth rates and explain the microgravity experimental results.…”

Section: Bayesian Optimization: Fixed Control Recipementioning

confidence: 99%

“…In recent years, AI and machine learning tools are increasingly being used in fluid control and crystal growth problems. [17][18][19][20][21][22][23][24][25] We utilized for instance Bayesian optimization in our previous work 26) for the estimation of the diffusion coefficient of GaSb in InSb melt. This approach showed promising results and proved to be useful for the rapid estimation of unknown variables.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Control of growth interface shape during InGaSb growth by vertical gradient freezing under microgravity, and optimization using machine learning

Ghritli¹,

Okano²,

Inatomi³

et al. 2022

Jpn. J. Appl. Phys.

Self Cite

View full text Add to dashboard Cite

Growth of high quality InGaSb crystals by Vertical Gradient Freezing (VGF) under microgravity was numerically simulated. Machine learning tools were used to optimize the growth conditions. The study focuses on controlling the growth interface shape which directly affects the quality and homogeneity of the grown crystals. Initially, Bayesian optimization was utilized to search for the most favorable growth conditions that promote a desirable flatter growth interface shape. Afterwards, a reinforcement learning model was developed. The system was subjected to a lower temperature gradient near the feed crystal and to crucible rotation with a rate ranging according to the obtained optimal strategy. Results showed that the interface deformation is considerably reduced, and a flatter growth interface could be maintained. The growth rate and solute concentration uniformity were also improved. This adaptive control recipe proves to hold a great potential in the continuous and rapid optimization of other crystal growth processes.

show abstract

Section: Governing Equations and Associated Boundary Conditionsmentioning

confidence: 99%

Section: Bayesian Optimization: Fixed Control Recipementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Control of growth interface shape during InGaSb growth by vertical gradient freezing under microgravity, and optimization using machine learning

Ghritli¹,

Okano²,

Inatomi³

et al. 2022

Jpn. J. Appl. Phys.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, such reaction systems have been studied by ab initio calculations, e.g., density functional theory (DFT) and transition state theory (TST) [13][14][15][16][17][18][19][20][21] . Increased semiconductor device performance has recently necessitated the use of simulators for quantitative process optimization that goes beyond obtaining a qualitative understanding [22][23][24][25] . However, the predictive performance of ab initio reaction rates is often inadequate for such quantitative requirements.…”

mentioning

confidence: 99%

Beyond ab initio reaction simulator: An application to GaN metalorganic vapor phase epitaxy

Kusaba

Nitta

Shiraishi

et al. 2022

Applied Physics Letters

View full text Add to dashboard Cite

To develop a quantitative reaction simulator, data assimilation was performed using high-resolution time-of-flight mass spectrometry (TOF-MS) data applied to a GaN metalorganic vapor phase epitaxy system. Incorporating ab initio knowledge into the optimization enables it to reproduce not only the concentration of CH4 (an impurity precursor) as an objective variable but also known reaction pathways. The simulation results show significant production of GaH3, a precursor of GaN, which has been difficult to detect in TOF-MS experiments. Our proposed approach is expected to be applicable to other applied physics fields that require quantitative prediction that goes beyond ab initio reaction rates.

show abstract

Numerical investigation of the effects of axial temperature gradient and cooling rate on InGaSb crystal growth under micro-gravity

Jin

Bing

2023

Journal of Crystal Growth

View full text Add to dashboard Cite

Estimation of the diffusion coefficient of GaSb in InSb melt using Bayesian optimization and the ISS experimental results

Cited by 4 publications

References 6 publications

Control of growth interface shape during InGaSb growth by vertical gradient freezing under microgravity, and optimization using machine learning

Control of growth interface shape during InGaSb growth by vertical gradient freezing under microgravity, and optimization using machine learning

Beyond ab initio reaction simulator: An application to GaN metalorganic vapor phase epitaxy

Numerical investigation of the effects of axial temperature gradient and cooling rate on InGaSb crystal growth under micro-gravity

Contact Info

Product

Resources

About