and lastly, there were a lot of rabbit holes that didn't make it into the paper, so I outlined (most of) them here: jrymart.github.io/blog/2026-08...
jrymart.github.io
Everything /not/ in "Can Neural Networks Think Like Geomorphologists"
phd candidate at cu boulder earth science. working on surface processes, interpretable machine learning, and spatial data jrymart.github.io