Jordi Bolibar

Is there any progress on an integrated solution within DifferentialEquations.jl to this problem? I'm also very interested in making this work with DiffEqFlux.jl, in order to train UDEs in parallel...

I have tried a workaround using `pmap` and manually implementing the ensemble for each batch, but using `@showprogress` with that only works with DifferentialEquations.jl. When using it with AD (e.g....

[This repo](https://github.com/Machine-Learning-in-Glaciology-Workshop/Project_MB_Regression/tree/main) from the ML workshop project can be a good baseline, since we already used OGGM and Hugonnet et al. (2021) applied in Scandinavia.

If I understood things correctly from the PR, that fix will only be effective for `batch_size = 1` for now? For my case I'm working with bigger batch files, so...

As discussed with @gaurav-arya, we have verified that his fix https://github.com/JuliaDiff/ChainRules.jl/pull/566 solves this issue with a couple of MWEs. I'll close this once it will be merged. Thanks Gaurav!!!

Following our discussion in Slack, here's a similar issue which might be related. I’m getting an error when re-running `workflow.init_glacier_directories()` on a Linux SSH server. I haven’t encountered this behaviour...

Hi @bearecinos and @fmaussion! What is the current situation of this? With ODINN we've hit a point where having this dataset available is pretty much necessary. I've seen it is...

Wow, that was fast! Thanks so much for working on this @nchampollion. I can volunteer to test the code with the look-up table and see if everything works smoothly, and...

Thanks for the comments @millanr1! Regarding the surface DEMs, I second that those would be extremely interesting! From a modelling perspective, having the surface altimetry that goes with the surface...

When working with the SIA, it's the surface elevation gradient that drives the diffusivity: And the surface velocities also depend on the surface elevation (code in Julia, too lazy to...