ML Processing Pipelines using CWL, Deployment in Context of Research Teams and OGC-API Integration

Presenter: Francis Charette Migneault, Computer Research Institute of Montréal (CRIM)
Session 3 (APAC- Americas) Wednesday, February 10th 00:25 UTC

Summary: "Overview of Machine Learning (ML) processing pipelines using Common Workflow Language (CWL) and their deployment in the context of research teams at the Computer Research Institute of Montréal (CRIM). A component developed by CRIM named Weaver is presented to demonstrate through examples the integration of containerized Docker applications to execute leading edge technologies and algorithms with Web Processing Service (WPS) interfaces and Open Geospatial Consortium (OGC) APIs.

The talk presents four examples, illustrating applications for object region proposals, satellite imagery classification, climate data analysis and LiDAR point cloud classification. Distributed server architecture and interoperability capabilities of Weaver are also presented with pre-deployed WPS providers. The examples demonstrate how advanced processing pipelines and rapidly move from research and development phases to deployed web services in production environments.

Weaver: GitHub - crim-ca/weaver: Weaver: Workflow Execution Management Service (EMS); Application, Deployment and Execution Service (ADES)"

Please leave your questions for the presenter below!

As an alternative to YouTube, this presentations is also available on ConfTube