📄️ Introduction
Click here for a quick video guide for using Lt. Planckster! This video provides the most basic instructions for how to use Kubeflow in the context of Kernel Planckster. It may be sufficient on its own, but can be combined with the documentation provided in this section for a deeper understanding of the data processing machinery that supports Case Studies in Websat.
📄️ Run Kubeflow Pipelines
Kubeflow Pipelines is a platform for building and deploying portable, scalable machine learning (ML) workflows based on Docker containers. It is a part of the Kubeflow project, which aims to make running ML workloads on Kubernetes simple, portable, and scalable. This guide aims to explain and demonstrate how to run a Kubeflow Pipeline.
📄️ Sentinel Pipeline Reference
The data from the Sentinel Pipeline requires significantly more processing than most other scrapers. As a result, this Pipeline expects a more sophisticated set of parameters when configured for a run. Most of the parameters, such as longleft or latdown (two out of four parameters that define the geographical bounding box) are relatively straightforward. But dataset_evalscripts is more complex, identifying the specific types of data evaluation to use in a run of the Sentinel Pipeline.
📄️ Analyzing Scraped Data
This guide walks you through the Kernel-Planckster Tutorial Notebook. It aims to provide broader detail on how to view and analyze the scraped data obtained when running the kubeflow pipelines.
📄️ Custom Pipelines
How to create a Pipeline Notebook?