Jordan Limperis
0/ 100

03Research

Two peer-reviewed papers on transformer architectures for spatiotemporal air-pollution forecasting, from my time running the compute and modeling pipeline at Georgia Southern.

0

peer-reviewed publications

0×

GSU Research Competition wins

PM2.5

spatiotemporal forecasting focus

Publications

How I work

I built and ran a Weights & Biases–integrated GCP environment for high-compute PyTorch Lightning transformer models, the infrastructure that made the experiments reproducible enough to publish.

The through-line to my applied work is the same instinct: rigorous evaluation, honest baselines, and models that hold up when the data shifts. It’s why I trust an RCT before I trust an offline metric.

Recognition

1st & 2nd Place, GSU Research Competition
GSU Research Scholarship