Explore posts
Discover research notes, tutorials, announcements, and discussions from the community.
Browse by topic
Find posts on specific subjects
Materials Science
21 items
Research and data related to materials science, crystallography, and solid-state physics
Data Science
4 items
General data science, machine learning, and analytics
AI & Machine Learning
2 items
Artificial Intelligence, Neural Networks, and Machine Learning models
Chemistry
2 items
Chemical compounds, reactions, and molecular data
Energy & Sustainability
2 items
Renewable energy, battery research, and sustainable technologies
Economics & Finance
1 item
Incentive structures, market modeling, and economic simulations
Popular
Most used assets this week
Having a little fun generating some visuals in Midjourney to represent the superconductors team. So many cool styles to test out.
Came across this workflow researching some permanent magnet work. I haven't fully explored the code or how much this work will help, but sharing here to reference later because stuff is hard to find o
Extending the comparison to a different model CHGNet, this time a proper MLIP. Similar to the Orb model, this model predicts energy, force, and stress, but with the addition of the magnetic moment for
In this study, we explore how different aggregation methods affect the performance of a Machine Learning Force Field (MLFF) model when predicting various material properties. When using graph-based re
Community & discussion
Join the conversation and see what others are building
Updates & proposals
Stay informed about project progress and new ideas
Education & research
Learn from tutorials and stay up to date with the latest papers
Quick filters
Latest
Recently added
is a post describing the next steps after an initial pipeline run. The goal is to find materials with strong magnetocrystalline anisotropy energy (MAE) to validate candidates further. The text notes a model that predicts FePt around 3.07 meV and literature values for Nd2Fe14B near 2.9 meV per unit cell, suggesting values above about 2.5 meV are promising, since most materials have MAE below 0.1 meV. Several candidate results are shared, The notes mention exploring MnBi as a non-rare alternative and plan more testing later.
Try it with your own structures here:
This week I added two new services for crystal (CIF) generation. I took some time to test out Modal and it turns out it was exactly what I've been looking for. Many of these models are GPU intensive a
Automated recap of the latest activity in #permanent-magnets, created by @hermes.
Came across this workflow researching some permanent magnet work. I haven't fully explored the code or how much this work will help, but sharing here to reference later because stuff is hard to find o
Having a little fun generating some visuals in Midjourney to represent the superconductors team. So many cool styles to test out.