Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Crystal Growth: Principles of Crystallization01:25

Crystal Growth: Principles of Crystallization

2.2K
Crystallization is a phase transformation process in which crystals are precipitated from a supersaturated solution or formed from other sources. During crystallization, atoms or molecules arrange themselves into a well-defined, rigid crystal lattice to minimize energy.
Initiating crystallization involves manipulating the concentration of the solute and the temperature of the solution. Since crystal growth occurs when the ratio of concentration and solubility of the solute in the solvent...
2.2K
Recrystallization: Solid–Solution Equilibria01:10

Recrystallization: Solid–Solution Equilibria

1.1K
Recrystallization is a purification technique used to separate impurities from solid compounds. In this technique, no chemical reactions occur. Instead, it exploits physical properties only, specifically, the solubility differences between the desired compound and impurities, either at a single temperature or at different temperatures, and under other selected conditions. The solid-solution equilibrium (solubility equilibrium) of each component in the solution represents a binary phase...
1.1K
Solution Equilibrium and Saturation01:59

Solution Equilibrium and Saturation

18.7K
Imagine adding a small amount of sugar to a glass of water, stirring until all the sugar has dissolved, and then adding a bit more. You can repeat this process until the sugar concentration of the solution reaches its natural limit, a limit determined primarily by the relative strengths of the solute-solute, solute-solvent, and solvent-solvent attractive forces. You can be certain that you have reached this limit because, no matter how long you stir the solution, undissolved sugar remains. The...
18.7K
Precipitate Formation and Particle Size Control01:16

Precipitate Formation and Particle Size Control

830
In precipitation gravimetry, the precipitating agent should react specifically or selectively with the analyte. While a specific reagent reacts with the analyte alone, a selective reagent can react with a limited number of chemical species.
The obtained precipitate should be either a pure substance of known composition or easily converted to one by a simple process, such as ignition or drying. In addition, the precipitate should be insoluble and easily filterable. In general, filterability...
830

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Transfer of Optimized Crystal-Growth Environments between Different Furnace Configurations via a Latent Space.

ACS omega·2026
Same author

Multifaceted role of <i>POU5F1P1</i> in regulating its parental stem cell gene, <i>POU5F1</i>.

iScience·2026
Same author

Mitochondrial Transfer in the Tumor Microenvironment.

Cancer science·2026
Same author

The Utility of a Preoperative 3D Imaging Analysis System for Trigonal Meningioma.

Acta medica Okayama·2025
Same author

Focused light birefringence for three-dimensional observation of dislocations in silicon carbide wafers.

The Review of scientific instruments·2025
Same author

A Resected Case of Metachronous Gallbladder Metastasis of Gastric Cancer Mimicking Gallbladder Cancer.

Surgical case reports·2025

Related Experiment Video

Updated: Jul 31, 2025

Growing Protein Crystals with Distinct Dimensions Using Automated Crystallization Coupled with In Situ Dynamic Light Scattering
09:15

Growing Protein Crystals with Distinct Dimensions Using Automated Crystallization Coupled with In Situ Dynamic Light Scattering

Published on: August 14, 2018

10.6K

Data-driven automated control algorithm for floating-zone crystal growth derived by reinforcement learning.

Yusuke Tosa1, Ryo Omae1, Ryohei Matsumoto1

  • 1Anamorphosis Networks, 50 Higashionmaeda-Cho, Nishishichijo, Shimogyo-Ku, Kyoto, 600-8898, Japan.

Scientific Reports
|May 10, 2023
PubMed
Summary
This summary is machine-generated.

We demonstrate automated control of floating zone (FZ) crystal growth using reinforcement learning and Gaussian mixture modeling. This data-driven approach accurately follows ideal growth trajectories, surpassing human operator performance.

More Related Videos

Optimization of Crystal Growth for Neutron Macromolecular Crystallography
12:29

Optimization of Crystal Growth for Neutron Macromolecular Crystallography

Published on: March 13, 2021

5.5K
A Microfluidic Approach for the Study of Ice and Clathrate Hydrate Crystallization
08:01

A Microfluidic Approach for the Study of Ice and Clathrate Hydrate Crystallization

Published on: August 18, 2022

3.1K

Related Experiment Videos

Last Updated: Jul 31, 2025

Growing Protein Crystals with Distinct Dimensions Using Automated Crystallization Coupled with In Situ Dynamic Light Scattering
09:15

Growing Protein Crystals with Distinct Dimensions Using Automated Crystallization Coupled with In Situ Dynamic Light Scattering

Published on: August 14, 2018

10.6K
Optimization of Crystal Growth for Neutron Macromolecular Crystallography
12:29

Optimization of Crystal Growth for Neutron Macromolecular Crystallography

Published on: March 13, 2021

5.5K
A Microfluidic Approach for the Study of Ice and Clathrate Hydrate Crystallization
08:01

A Microfluidic Approach for the Study of Ice and Clathrate Hydrate Crystallization

Published on: August 18, 2022

3.1K

Area of Science:

  • Materials Science
  • Automation Engineering
  • Artificial Intelligence

Background:

  • Floating Zone (FZ) crystal growth is crucial for semiconductor wafer manufacturing, but its complex dynamics necessitate manual control.
  • Complete automation of FZ crystal growth for high productivity remains a significant challenge in materials processing.

Purpose of the Study:

  • To develop a data-driven method for the complete automation of floating zone (FZ) crystal growth.
  • To achieve accurate control following ideal growth trajectories in FZ crystal growth.

Main Methods:

  • Utilized reinforcement learning combined with Gaussian mixture modeling (GMM) to predict FZ crystal growth dynamics.
  • Constructed a completely data-driven control model using a small number of operational trajectories.
  • Employed an emulator program for FZ crystal growth to test and validate the control model.

Main Results:

  • The data-driven control model demonstrated superior accuracy in following ideal growth trajectories compared to human-operated demonstrations.
  • Policy optimization near demonstration trajectories enabled precise control and adherence to the ideal growth path.
  • The proposed method successfully automated FZ crystal growth control.

Conclusions:

  • Reinforcement learning with GMM provides an effective, data-driven solution for automating complex FZ crystal growth processes.
  • This approach significantly enhances control accuracy and productivity in semiconductor materials manufacturing.
  • The findings pave the way for more autonomous and efficient materials processing.