Skip to main content

ACCESS

Mentors and Regional Facilitators
Name Region Skills Interests
Kevin Brandt Campus Champions, Great Plains, CCMNet
Chris Reidy Campus Champions, CCMNet
Daniel Benedict CCMNet
Daniel Morales Campus Champions
Deborah Penchoff Campus Champions
David Liu CCMNet
Elizabeth Kwon Campus Champions, CCMNet
Elizabeth Leake CCMNet
Feseha Abebe-Akele CCMNet
Vikram Gazula ACCESS CSSN, CCMNet, Campus Champions, Kentucky
Jeho Park CCMNet, Campus Champions
Jacob Fosso Tande ACCESS CSSN, Campus Champions, CCMNet
Jonathan Komperda Campus Champions
Jennifer Armstrong Campus Champions
Od Odbadrakh ACCESS CSSN
Dr. Nabeel Alzahrani Campus Champions, CCMNet
Nandan Tandon CCMNet, Campus Champions
Nannan Shan CCMNet, ACCESS CSSN
Rebecca Belshe Campus Champions, CCMNet
Widodo Samyono Campus Champions, CCMNet
Liwen Shih Campus Champions, ACCESS CSSN, CCMNet
Mohammad Al-Tahat CAREERS, Campus Champions, CCMNet

Affinity Groups

Logo Name Description Tags Join
ACCESS System Status News Enables ACCESS researchers, resource providers, project staff, developers, and anyone in the community to view and receive news and outage emails about ACCESS central systems and online… Login to join

Topics from Ask.CI

Loading topics from Ask.CI ...

Engagements

Bayesian nonparametric ensemble air quality model predictions at high spatio-temporal daily nationwide  1 km grid cell
Columbia University

I aim to run a Bayesian Nonparametric Ensemble (BNE) machine learning model implemented in MATLAB. Previously, I successfully tested the model on Columbia's HPC GPU cluster using SLURM. I have since enabled MATLAB parallel computing and enhanced my script with additional lines of code for optimized execution. 

I want to leverage ACCESS Accelerate allocations to run this model at scale.

The BNE framework is an innovative ensemble modeling approach designed for high-resolution air pollution exposure prediction and spatiotemporal uncertainty characterization. This work requires significant computational resources due to the complexity and scale of the task. Specifically, the model predicts daily air pollutant concentrations (PM2.5​ and NO2 at a 1 km grid resolution across the United States, spanning the years 2010–2018. Each daily prediction dataset is approximately 6 GB in size, resulting in substantial storage and processing demands.

To ensure efficient training, validation, and execution of the ensemble models at a national scale, I need access to GPU clusters with the following resources:

  • Permanent storage: ≥100 TB
  • Temporary storage: ≥50 TB
  • RAM: ≥725 GB

In addition to MATLAB, I also require Python and R installed on the system. I use Python notebooks to analyze output data and run R packages through a conda environment in Jupyter Notebook. These tools are essential for post-processing and visualization of model predictions, as well as for running complementary statistical analyses.

To finalize the GPU system configuration based on my requirements and initial runs, I would appreciate guidance from an expert. Since I already have approval for the ACCESS Accelerate allocation, this support will help ensure a smooth setup and efficient utilization of the allocated resources.

Status: Complete

People with Expertise

Matt Ferguson

Boise State University

Programs

At-Large

Roles

researcher/educator, cssn

picture of Matt Ferguson

Expertise

Anas Alsobeh

Programs

CCMNet

Roles

CCMNet

Dr.Anas Alsobeh

Expertise

Rebecca Belshe

Arizona State University

Programs

Campus Champions, CCMNet

Roles

research computing facilitator, CCMNet

Placeholder headshot

Expertise

People with Interest

Timothy Middelkoop

Internet2

Programs

ACCESS CSSN, Campus Champions, CCMNet, Great Plains

Roles

mentor, regional facilitator, researcher/educator, research computing facilitator, CCMNet

Timothy Middelkoop (white male with short dark hair and glasses, he/him,his)

Interests

Vikram Gazula

University of Kentucky

Programs

ACCESS CSSN, CCMNet, Campus Champions, Kentucky

Roles

mentor, regional facilitator, research computing facilitator, Affinity Group Leader, KB PM, CCMNet PM, CCMNet

Vikram

Interests

Elizabeth Kwon

Columbia University in the City of New York

Programs

Campus Champions, CCMNet

Roles

CampusChampionsAdmin, research computing facilitator, Affinity Group Leader, CCMNet

Placeholder headshot

Interests