Skip to main content

High-Performance Computing.
Training.
High-Speed Networking.

What is SCINet?

The SCINet initiative is an effort by the USDA Agricultural Research Service (ARS) to grow USDA’s research capacity by providing scientists with access to high-performance computing clusters, high-speed networking for data transfer, and training in scientific computing.

Get Started with SCINet

ARS scientists/collaborators:
Register for an account

Get Started

Upcoming Trainings and Events

  • Introduction to HPC Environments and Project Management and Organization

    This workshop provides hands-on training in using SCINet’s high-performance computing (HPC) clusters for bioinformatics workflows. Participants will learn how to access and navigate SCINet’s systems as well as command line basics for managing and analyzing bioinformatics data including running BLAST and handling FASTA and FASTQ files. The workshop also covers project management and organization strategies to improve data organization and workflow efficiency.

    • Thursday, April 17, 1 – 5 PM ET
      • Registration: Register Here
      • Prerequisites:
        • Familiarity with basic command-line concepts.
  • Transfer Learning

    This workshop provides the foundational concepts and practical applications of transfer learning, a powerful technique in deep learning that allows AI models to leverage pre-trained knowledge to improve performance on new tasks. The sessions will cover different types of transfer learning techniques, such as feature extraction and fine-tuning. This includes hands-on experience in applying these techniques to computer vision and language models.

  • Animal Behavior AI - Working Group Meeting

    This SCINet working group aims to explore the potential benefits of Artificial Intelligence (AI) in animal behavior research.

    • SCINet discussion, focusing on how to use globus and Juno for hosting data.
    • Brad A. Freking, Research Geneticist from the U.S. Meat Animal Research Center (USMARC) at ARS will present their on-going challenge about detecting sheep maternal behavior from camera images. We will discuss possible AI approaches to address this challenge.