PI: Nicola Ferrier, CELS
Description: This project is to contribute to the existing (already accepted) A21 ESP proposal, Enabling Connectomics at Exascale to Facilitate Discoveries in Neuroscience. The goal is to develop a computational pipeline for neuroscience that will extract brain-image-derived mappings of neurons and their connections from electron microscope datasets too large for today’s most powerful systems. Ultimately the pipeline will be used to analyze an entire cubic centimeter of electron microscopy data.
Testbed: PetrelKube and DGX1
Schedule: We will be using PetrelKube as a server for Visualization and Segmentation of data stored in petrel. The serverkube will be running constantly but the usage is not high.
The DGX1 will be used to train networks. Around 5 days a month continuously, this will dwindle with the integration of TensorFlow on theta/Aurora.