Jove
Visualize
Contact Us

Related Experiment Video

Updated: May 3, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.6K

Leveraging deep learning-based foundation models for optical turbulence (Cn2) estimation under data scarcity.

Sukanta Basu

    Applied Optics
    |March 17, 2026
    PubMed
    Summary

    Tabular foundation models (TFMs) can predict optical turbulence (Cn2) using limited data. These models, pre-trained on diverse datasets, offer a fast, tuning-free solution for optical turbulence prediction.

    Related Concept Videos

    Turbulent Flow01:24

    Turbulent Flow

    856
    Turbulent flow is characterized by unpredictable fluctuations in velocity and pressure, which result in a chaotic fluid movement distinct from the orderly patterns of laminar flow. While laminar flow is governed by smooth, parallel layers with minimal mixing, turbulent flow exhibits highly irregular, three-dimensional patterns. This behavior arises due to instabilities in the fluid's velocity profile, and amplifies as the flow velocity increases. Minor disturbances, known as turbulent...
    856

    You might also read

    Related Articles

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

    Sort by
    Same author

    Analysis of atmospheric turbulence dynamics during the total solar eclipse with AI-based sensing.

    Journal of the Optical Society of America. A, Optics, image science, and vision·2025
    Same author

    Intercomparison of flux-, gradient-, and variance-based optical turbulence (<i>C</i> <i>n</i>2) parameterizations.

    Applied optics·2024
    Same author

    Π-ML: a dimensional analysis-based machine learning parameterization of optical turbulence in the atmospheric surface layer.

    Optics letters·2023
    Same author

    Hybrid Profile-Gradient Approaches for the Estimation of Surface Fluxes.

    Boundary-layer meteorology·2019
    Same author

    Estimating higher-order structure functions from geophysical turbulence time series: Confronting the curse of the limited sample size.

    Physical review. E·2017
    Same author

    Utilizing the Kantorovich metric for the validation of optical turbulence predictions.

    Optics letters·2016
    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

    Area of Science:

    • Atmospheric physics and remote sensing
    • Machine learning applications in geosciences
    • Optical engineering and adaptive optics

    Background:

    • Estimating optical turbulence (Cn2) is crucial for applications like astronomy and free-space communication.
    • Data-driven Cn2 estimation is hindered by sparse and costly high-quality training data.
    • Existing methods often require extensive data or complex physics-based models.

    Purpose of the Study:

    • To investigate the efficacy of tabular foundation models (TFMs) for data-driven optical turbulence (Cn2) estimation.
    • To assess TFMs' performance in a few-shot learning scenario with minimal task-specific adaptation.
    • To determine if TFMs pre-trained on general tabular data can generalize to the specialized domain of optical turbulence.

    Main Methods:

    Related Experiment Videos

    Last Updated: May 3, 2026

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.6K
    • Utilized meteorological and turbulence observations from the Mauna Loa Observatory.
    • Evaluated two state-of-the-art TFMs: TabPFNv2 and TabDPT.
    • Employed a few-shot learning approach without fine-tuning or hyperparameter optimization.

    Main Results:

    • Both TFMs accurately captured the diurnal cycle and dynamic range of Cn2.
    • TabPFNv2 demonstrated superior data efficiency and ensemble stability.
    • Model performance matched or exceeded previous data-driven and physics-based approaches.
    • Feature importance analysis revealed physically meaningful learned relationships in TabPFNv2, aligning with surface layer theory.

    Conclusions:

    • TFMs show significant promise for optical turbulence prediction, especially in data-limited scenarios.
    • TFMs offer a "plug-and-play" solution, reducing the need for extensive data and hyperparameter tuning.
    • These findings pave the way for faster, more accessible operational optical turbulence forecasting.