AdaptiveWorkflow for PixInsight

Welcome to AdaptiveWorkflow!

AdaptiveWorkflow runs a sequence of processes the way an operator would. It runs a process, asks which way to go, measures the image and chooses by the result, and carries on. We design that sequence once, as a workflow blueprint, blueprint for short, and run it whenever it is needed.

PixInsight offers a way to run several processes in a row, using the ProcessContainer. However, a ProcessContainer runs the same steps in the same way every time – it’s a sequential, static pipeline – and a real processing session is not like that. It depends on the data: is there a gradient, how noisy is the image, is it stretched already, is the star halo too large? Of course, ProcessContainer is mostly meant to be used to save some static recipes, or as a way to save a static sequence of processes, but it’s not a tool designed to offer real workflows. AdaptiveWorkflow is.

An AdaptiveWorkflow blueprint puts those typical processing questions into the sequence. Some can be asked to us when the workflow reaches them, and some the workflow answers by itself, by measuring the image whenever we need. We choose when or if a question is asked (or no questions at all), when and what to measure, etc.

A blueprint is drawn as a flowchart, and the chart arranges itself, so there are no wires to cross and nothing to align by hand. We can drag process blocks to place them at any running spot in the chart, but everything else in the chart is automatically linked and arranged.

AdaptiveWorkflow can also be used as an excellent teaching and learning tool, as every workflow blueprint can be saved and shared. A small certificate signature helps validating authorship of blueprint files, so students know the files came from their instructors, for example.

AdaptiveWorkflow comes with eleven (11) different pre-written blueprints defining typical workflows for different kind of data sets:

• Simple OSC, RGB, dual and tricolor narrowband post-processing workflows.
• Quick post-processing workflows for both, noisy data, and space telescope quality data.
• Preprocessing workflows for both, OSC and mono data sets.
• A batch processing workflow to reduce measured noise with either NoiseX or MLDenoise.
• A single-task blueprint to increase color saturation on stars.
• A workflow to run MultiscaleGradientCorrection (MGC). It runs a solver if needed, applies SpectrophotometricFluxCalibration, verifies the MARS database, and finally runs MGC.

These blueprints are meant to be a learning resource, and a starting point for each of us, not as recipes that will give us a NASA APOD by running them on our images. For example, we should not expect that the preprocessing mono blueprint would calibrate every mono data set we throw at it, without some tweaks. Modify them to better suit your needs, or simply use them as templates to create your brand-new workflow blueprints.