Ashby Prize in Computational Science University of Illinois at Urbana-Champaign
This competition is co-organized by the Center for Artificial Intelligence Innovation at the National Center for Supercomputing Applications and researchers from the Department of Atmospheric Sciences and Department of Mechanical Science and Engineering. The main goal of the hackathon is to let talented UIUC students showcase their skills in a friendly competition while working on challenging problem involving computational science and machine learning on a state-of-the-art compute platform designed for AI. The competition problem statement can be found HERE.
The competition will take place on April 23-24 at the National Center for Supercomputing Applications with the final presentation of the competition results on April 25 at 3:00pm.
How: To participate, we ask interested students to sign up at https://forms.gle/k5XC34kJQNbvFhGW8 by Friday, April 15, and to setup user account on HAL system. The competition problem statement can be found HERE and the relevant dataset will be available on HAL on April 18.
Eligibility: Teams must have two or more students (undergraduate and/or graduate) with at least one currently enrolled in the Computer Science Department. Students are encouraged to form teams of up to five students.
Criteria: Teams will be evaluated on the following:
- Innovative approach with respect to modeling of the problem and its numerical solution, as well as the use of machine learning, information visualization, and other computational techniques.
- Effective use of NCSA computing resources, including performance on its flagship AI platform.
- Quality of a written project summary and oral presentation.
- Relevance of the problem chosen.
Prize: 1st place $3000, 2nd place $1500, 3rd place $750
HACKATHON PROJECT
Learning models to predict climate-relevant properties of atmospheric aerosols
Science team contact: Dr. Jeffrey Curtis jcurtis2@illinois.edu
Technical team contact: Dr. Dawei Mu dmu@illinois.edi
Problem: The objective of this project is to create a machine learning model trained on accurate WRF-PartMC data that predicts climate-relevant aerosol properties from only the features that current GCMs can output. For more details, see THIS problem description and this website.
HACKATHON PROJECT
Learning models to predict climate-relevant properties of atmospheric aerosols
Science team contact: Dr. Jeffrey Curtis jcurtis2@illinois.edu
Technical team contact: Dr. Dawei Mu dmu@illinois.edi
Problem: The objective of this project is to create a machine learning model trained on accurate WRF-PartMC data that predicts climate-relevant aerosol properties from only the features that current GCMs can output. For more details, see THIS problem description and this website.
Dataset: Data will be provided on HAL cluster at the time of the competition.
SCHEDULE
FRIDAY, April 15
Deadline to sign up for the hackathon
Monday, April 18
8:00am — Teams are announced (on-line)
4:00pm — Overview of the Hackathon rules, challenge problem, and a brief intro to HAL computing environment (1030 NCSA)
Saturday, April 23
8:30am — Teams work on the problem (light breakfast will be provided) (1104 NCSA)
Noon — Lunch (pizza will be provided) (1104 NCSA)
1:00pm — Teams continue to work on the challenge problems (snacks will be provided) (1104 NCSA)
4:00pm — Teams briefing (1104 NCSA)
SUNDAY, April 24
8:30am — Teams work on the problem (light breakfast will be provided) (1104 NCSA)
Noon — Lunch (pizza will be provided) (1104 NCSA)
1:00pm — Teams continue to work on the challenge problems (snacks will be provided) (1104 NCSA)
4:00pm — Teams briefing (1104 NCSA)
Monday, April 25
3:00pm — Teams present results (1030 NCSA)
Wednesday, April 27
Winning teams are announced
