Technical Short Course

Strain Accumulation and Release from GNSS

June 15-17, 2026
Virtual

About

Program Overview

Coming soon.

Course GitHUB: PowerPoints & Jupyter Notebooks

Important Dates

  • Applications Open

Late February

  • Applications Close

April 15

  • Notifications Sent

Mid-May

Learning Objectives

Coming soon.

By the end of this short course, participants will be able to: 

  • Explain the role of machine learning in earthquake detection, association, and location. 
  • Select appropriate neural network architectures for earthquake detection and phase picking. 
  • Train models using labeled seismic datasets and evaluate their performance. 
  • Implement trained models to detect and associate seismic events in real-world data. 
  • Optimize model parameters for accuracy and efficiency in earthquake cataloging. 
  • Integrate machine learning outputs into earthquake location algorithms. 
  • Assess model predictions and refine event catalogs through quality control methods. 
  • Design end-to-end machine learning workflows tailored to specific seismic networks or research needs. 
  • Collaborate on participant-led exercises to improve catalog quality and reliability. 

Highlight Your Skills with a Digital Badge: Participants earn a credential through Credly issued by EarthScope Consortium that verifies your achievements. The badge showcases the knowledge and skills you’ve gained and can be shared online, added to resumes, or displayed on professional and social media profiles to support your career growth.

Geodesy Engagement-Level credential

Brief Agenda

Coming soon.

Tentative agenda is listed below, and subject to change. Full agenda will be sent along with a participant packet closer to the start of the course.

Day 1:

  • Curating machine learning datasets with a focus on the Pacific Northwest 
  • Introduction to Seisbench
  • Build and train deep learning models for detecting, picking, using Seisbench
  • Research talks by Yiyu Ni (UW) and Amanda Thomas (UC Davis) 
  • Hackathon: Detect on continuous data 

Day 2:

  • Phase Association  
  • Application to Picks from Day 1 
  • Event Discrimination 
  • Research talks by Ian McBreatry (Stanford) & Akash Kharita (UW) 
  • Hackathon: Associate on Day 1 detection 

Day 3:

  • Earthquake Location & Relocation 
  • Research talks by Felix Waldhauser (Columbia University)  
  • Hackathon: Quality-control on machine learning catalogs 

Application

Coming soon.

This course is for graduate students, postdocs, and professionals  in the field of earthquake science who have specific research or application needs for machine learning in earthquake detection, association, and/or location. They should have intermediate python skills and a current interest in utilizing this technology.

Space is limited to 20 participants.

Prerequisites  

1. Need to have intermediate python skills including: 

  • Core Python Proficiency – Comfortable with syntax, functions, and best practices. 
  • Data Handling – Uses pandas and NumPy for data manipulation and analysis. 
  • Automation & File Handling – Reads/writes files, automates tasks, and web scrapes with requests. 
  • Debugging & Exception Handling – Uses try-except, logging, and debugging tools. 
  • Data Visualization – Creates plots using Matplotlib, Seaborn, or plotly. 
  • Algorithms & Data Structures – Implements sorting and searching 
  • Version Control – Works with Git/GitHub, branches, and pull requests. 
  • Python Packages & Environments – Creates/imports modules, manages dependencies with venv/conda.

2. Must have a laptop computer capable of accessing the internet. 

3. Applicants are currently based at a U.S. institution. 

Apply Now

The application closes April 15, 2026 at 11:59 pm Pacific Daylight Time. 

For questions contact GEI Program Manager Shannon Fasola (sfasola@uoregon.edu).

Instructors

Jack Loveless: Smith College
Brendan Crowell: Ohio State University
Kaj Johnson: Indiana University Bloomington 
Tim Melbourne: Central Washington University

Skip to content