Founder @ourofoundation for the innovation economy. Founding engineer @ Matter42. Materials discovery (rare-earth-free permanent magnets, 2D, superconductors).
Chicago, IL
Joined January 2014
- Tweets910
- Following439
- Followers598
- Likes1.9K
Pinned Tweet
The D in DFT.
Experimenting with an interactive 3D electron density visualization. Pipeline does a quick SCF run to get electron density, then uses marching cubes to render isosurfaces at any chosen density level.
Right now it just shows one level of density at a time so you can easily see core and valence electrons independently, but working on a full density cloud view too.
I'm thinking it's possible to build an intuition from this view that will put humans back in the materials discovery loop.
For materials science researchers:
You can now ask us to host your model, code, or algorithm on Ouro. Send a repo or source code and we'll do the rest.
You shouldn’t need to be a software or infra engineers for others to use your work.
ouro[dot]foundation/host
New .cube viewer on Ouro. Explore 3D or 2D slices of charge density, spin density, bonding (deformation) density, and orbitals.
Heavily inspired by @gp_0013's work visualizing electron (+spin) density and s/o his latest post with @sfcompute, the blog aesthetic is beautiful.
Have a look and you'll see what I mean
project-14.us/soc-scf-trajec…
We're looking into superconductors, permanent magnets, 2D materials, thermoelectrics, and more on Ouro.
Come check it out, maybe share what you're working on.
Here's one of my favorite crystals our magnet team has found (because it's pretty, not predicted to be very good though) ouro.foundation/files/mmoder…
Added Prophet to Ouro yesterday to start testing and benchmarking it.
I've been waiting a long time for a challenger to CHGNet.
Now the community's rare-earth-free permanent magnet discovery research gets better magnetic moments, more accurate Curie temperatures, and can distinguish the energies of different magnetic states of the same structure, something that used to require DFT. Prophet does it all in one model.
It's not perfect yet (it prefers antiferromagnetism in Mn pnictides like MnBi) but a step in the right direction. Our first benchmarks are up on Ouro.
Try it out and see what you think.
First benchmark post: ouro.foundation/posts/mmoder…
Try the API: ouro.foundation/services/mmo…
Everyone is a scientist. Science needs compute. Ouro uses @modal.
ouro.foundation/posts/mmoder…
Simulated it on some dummy data so I can share it here.
If I was doing process development this kind of thing would make my life so much easier. No more blind knob tuning 🙏
I was mid-demo last week when it really clicked for me why AI-driven materials characterization will be valuable.
During the demo, the client asked how we could optimize the recipe they were using to grow a thin-film material. We had been so focused on the characterization part that a question like this never came up before.
On the fly, I asked the agent. Having access to tools that can make sense of experimental Raman, AFM, XRD, etc. and associated recipes stored, it reasoned about which knobs to tune in the recipe.
Now they're going to take the recommendation to the lab. Let's see how it goes! Stay tuned for an update in a couple weeks.
I was mid-demo last week when it really clicked for me why AI-driven materials characterization will be valuable.
During the demo, the client asked how we could optimize the recipe they were using to grow a thin-film material. We had been so focused on the characterization part that a question like this never came up before.
On the fly, I asked the agent. Having access to tools that can make sense of experimental Raman, AFM, XRD, etc. and associated recipes stored, it reasoned about which knobs to tune in the recipe.
Now they're going to take the recommendation to the lab. Let's see how it goes! Stay tuned for an update in a couple weeks.
It still blows my mind how much we can learn about a material from shining a laser on it.
Here are three types of light scattering. Stokes Raman is the most interesting in my work characterizing 2D materials. It's when light is absorbed then re-emitted by the material after giving up some energy to the crystal lattice, causing a red-shift.
We use a spectrometer to measure the wavelength of the shifted light. There are usually a handful of dominant shifts depending on the atomic structure of the lattice. This "fingerprint" from how the light changes frequency can tell us a lot about the material!