Geospatial Research Working Group Annual Workshop
Machine Learning and Deep Learning for Geospatial Research - September 25-28, 2023.
Register for the Workshop
How to Participate
All members of the working group are welcome to participate! We also welcome anyone interested in learning about the working group, SCINet, or geospatial research. Please register by 9/22/2023 to ensure you will receive event updates and be added to the workshop project space on SCINet.
Get Started with SCINet
For this workshop, you will need to have a SCINet account and be able to successfully log in. We recommend applying for an account as soon as possible.
Register for SCINetWorkshop Itinerary
-
Session 1: Kickoff with lightning talks
Introduction to the workshop plus lightning presentations from ARS researchers and SCINet Fellows on their research
-
Session 2: Spatial modeling with machine learning
An overview of machine learning methods for spatial modeling
-
Session 3: Geospatial deep learning with Raster Vision
An introduction to deep learning computer vision tasks with geospatial data
-
Session 4: An introduction to GPU-based computing
What are GPUs, how they differ from CPUs, and what kinds of computing tasks can benefit from GPUs
-
Session 5: Closing discussion and future planning
Discussions on how to use the tools and methods covered in the workshop in your own research and what should the working group focus on in the next year
The SCINet Geospatial Research Working Group’s Annual Workshop is set to take place September 25-28, 2023. This year’s theme is Machine Learning and Deep Learning with Geospatial Data and will feature lightning talks, interactive tutorials, and community discussions around research topics.
Workshop Goals
The two overarching goals of the Geospatial Workshop are to:
- Provide hands-on tutorials on workflows to access the SCINet high-performance computing (HPC) systems and conduct geospatial research at scale.
- Foster research efforts that had previously been un-attainable due to computational limitations or technical bottlenecks.
Organizing Committee
- Heather Savoy, SCINet Computational Biologist and working group co-lead, Las Cruces, NM
- Amy Hudson, Research Ecologist and working group co-lead, Manhattan, KS
- Brian Stucky, SCINet Computational Biologist and acting CSIO, Gainesville, FL
- Sarah Goslee, Research Ecologist, University Park, PA
- Pat Clark, Range Scientist, Boise, ID
- Noa Mills, SCINet Fellow, Sacramento, CA
- Edwin Winzeler, Research Associate, Booneville, AR
How to Participate
You may register for any or all workshop sessions using the registration form here.
The workshop is split over 5 separate Zoom sessions (as well as a pre-workshop assistance session) that will include:
- Lightning talks on the intersection of geospatial analyses, machine learning, and deep learning in ARS research
- Presentations on fundamental material related to machine learning, deep learning, and GPU-based computing
- Hands-on tutorials to assist researchers in using machine learning, deep learning, and GPU-based computing on SCINet resources
- Facilitated discussions on using machine learning and deep learning in our geospatial research
To follow along with the tutorials you need to already have or apply for a SCINet account, and be able to successfully login to your account. We recommend applying for an account ASAP, as the process can take time for final approval. Please note, if you need help accessing your SCINet account, you should plan on attending the pre-workshop login assistance session on 9/21/2023 (Session 0), but make sure you have applied for an account in advance of this session.
Please register for the sessions so we can have an idea of how many people will be present at each event. Note, each session will have a separate Zoom link and passcode, so you must register for each session you would like to attend. Calendar events with Zoom links will be sent out automatically based on registration form submissions.
We are committed to making this workshop accessible to everybody. If we can help making learning easier for you (e.g., sign-language interpreters), please get in touch (Heather Savoy, heather.savoy@usda.gov) and we will attempt to do so.