Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Volume 2 Issue 7, July 2022

Extracting hidden state variables from video recordings

State variables are used to mathematically model dynamical systems such as the chaotic swing stick in motion depicted in the cover. Identifying hidden state variables has, however, remained a challenging task. In this issue, Chen et al. introduce a data-driven approach that analyzes high-dimensional observable data — for instance, video frames — to automatically identify not only the minimum number of state variables needed to describe complex system dynamics, but also what these variables might be, without any prior knowledge of the underlying physics.

See Chen et al. and Krämer

Image: Yinuo Qin, Columbia University. Cover Design: Alex Wing

Editorial

  • We highlight how this year’s awardees from some of the most important prizes in mathematics have had an impact in the computational science community.

    Editorial

    Advertisement

Top of page ⤴

Research Highlights

Top of page ⤴

News & Views

  • The problem of automatically determining state variables for physical systems is challenging, but essential in the modeling process of almost all scientific and engineering processes. A deep neural network-based approach is proposed to find state variables for systems whose data are given as video frames.

    • Boris Kramer
    News & Views
  • The design of protein sequences that can precisely fold into pre-specified 3D structures is a challenging task. A recently proposed deep-learning algorithm improves such designs when compared with traditional, physics-based protein design approaches.

    • Jue Wang
    News & Views
Top of page ⤴

Research Briefings

  • Inspired by active learning approaches, we have developed a computational method that selects minimal gene sets capable of reliably identifying cell-types and transcriptional states in large sets of single-cell RNA-sequencing data. As the procedure focuses computational resources on poorly classified cells, active support vector machine (ActiveSVM) scales to data sets with over one million cells.

    Research Briefing
  • A cell clustering model for spatial transcripts that uses cell embedding obtained by graph neural networks can be applied to datasets from multiple platforms for cell type or subpopulation identification and further analysis of the spatial microenvironment.

    Research Briefing
Top of page ⤴

Reviews

  • Quantum embedding theory promises the simulation of realistic materials in quantum computers. In this Perspective, challenges and opportunities of applying different embedding frameworks to calculate solid materials properties are discussed, with a focus on electronic structures of spin defects.

    • Christian Vorwerk
    • Nan Sheng
    • Giulia Galli
    Perspective
Top of page ⤴

Research

Top of page ⤴

Search

Quick links