Using a neural network to find a stable region within a set of data?

Question

I am working on a machine learning problem in which I am attempting to find a stable region in a spiral galaxy. I have created some visualizations of my data, for instance:

In this image, you can see there is a flat region between 0 and roughly 30 pixels, and between 90 pixels and 110 pixels. I have received suggestions to use an RNN LSTM model that can identify flat regions, but I wanted to hear other suggestions of other neural network models as well.

Answer 1

As @SamMason commenters already stated RNN LSTM is going to be overkill for this model. It will lead to worse results than manually coding the detection of a straight region which would be very easy to do if all the images look like this graph. You can follow the black line and if the black line changes position in the next column it's not straight.

https://www.semanticscholar.org/paper/ACOUSTIC-SCENE-CLASSIFICATION-USING-PARALLEL-OF-AND-Bae-Choi/abea9615a8b021a29c05e4b7f3ef9e7514fac39d

Maybe your pi actually wants to make a model for examining regions then determining if it is worth continuing to look at the region to search for a more stable regions and or create a directionality function where they will decide the ideal direction to move the sensor to search for a new flat region automatically. This would automate the process of looking for possible life supporting galaxies. Is the sun the right (color_temp metric)->does it have stable regions at this location? where could a stable region be based on the incoming signal, etc.