Jon Duckworth

> 4\. Do I understand correctly that model_type needs to be a string listed in the section Model Type? How can three be required at the same time if it's...

That makes sense. I’ll go through and try to be consistent about that throughout the spec

> * For the unsupervised example, doesn't fall under "Dimensionality Reduction"? #21 changed the `model_type` field to a `prediction_type` field in the `model_type` object. We don't currently have `"Dimensionality Reduction"`...

cc: @sfoucher @calebrob6 I believe you had voiced a concern early on that PyTorch checkpoints might not capture enough information to be universally useful; maybe you can weigh in on...

From @m-mohr in response to above comments: > I was refering to STAC quite a lot because I've co-authored it and it is stable, so there's a lot to learn...

From @ymoisan in response to above comments: > > Are models "spatio-temporal assets"? (Would models be STAC Items ?) > > That's the issue :-). You could think by virtue...

> > Are models "spatio-temporal assets"? (Would models be STAC Items ?) > > That's the issue :-). You could think by virtue of being trained with images, which are...

cc: @sfoucher

For a point of reference, see the inputs defined by the STAC DLM Extension [here](https://github.com/sfoucher/dlm-extension/blob/c26f0e2c3507909fa6bf85988583ab7d676e6750/examples/item.json#L191) (thanks @ymoisan!)

For reference, here is the list from the Raster Extension: https://github.com/stac-extensions/raster#data-types