Sparks/Baird Materials Informatics

self-driving-lab-demo

Software and instructions for setting up and running a self-driving lab (autonomous experimentation) demo using dimmable RGB LEDs, an 8-channel spectrophotometer, a microcontroller, and an adaptive design algorithm, as well as extensions to liquid- and solid-based color matching demos.

auto-paper

The aim of auto-paper is to give you tips, tricks, and tools to accelerate your publication rate and improve publication quality.

mat_discover

A materials discovery algorithm geared towards exploring high-performance candidates in new chemical spaces.

xtal2png

Encode/decode a crystal structure to/from a grayscale PNG image for direct use with image-based machine learning models such as Palette.

matbench-genmetrics

Generative materials benchmarking metrics, inspired by guacamol and CDVAE.

dist-matrix

Fast Numba-enabled CPU and GPU computations of Earth Mover's (scipy.stats.wasserstein_distance) and Euclidean distances.

CrabNet

Predict materials properties using only the composition information!

matsci-opt-benchmarks

A collection of benchmarking problems and datasets for testing the performance of advanced optimization algorithms in the field of materials science and chemistry.

mp-time-split

Use time-splits for Materials Project entries for generative modeling benchmarking.

bayes-opt-particle-packing

Compactness Matters: Improving Bayesian Optimization Efficiency of Materials Formulations through Invariant Search Spaces

CBFV

Tool to quickly create a composition-based feature vector

chem_wasserstein

A high performance mapping class to construct ElM2D plots from large datasets of inorganic compositions.

optimization-benchmark

A high-dimensional property predictor framed as a pseudo-materials discovery benchmark with fake compositional (linear) and "no-more-than-X-components" (non-linear) constraints.

crabnet-hyperparameter

Using Bayesian optimization via Ax platform + SAASBO model to simultaneously optimize 23 hyperparameters in 100 iterations (set a new Matbench benchmark).

composition-based-stability-regression

Testing out the performance of CrabNet on predicting stability using only compositional features.

.github

Ax

Adaptive Experimentation Platform

cdvae

An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]

gridrdf

Code for calculating grouped representation of interatomic distances (GRID) from crystal structures, and applying this in machine learning models.

matbench

Matbench: Benchmarks for materials science property prediction

MLSummerSchoolVienna2022

ESI-DCAFM-TACO-VDSP Summer School on "Machine Learning for Materials Hard and Soft"

numba

NumPy aware dynamic Python compiler using LLVM

olympus

Olympus: a benchmarking framework for noisy optimization and experiment planning

packing-generation

Hard-sphere packing generation with the Lubachevsky–Stillinger, Jodrey–Tory, and force-biased algorithms and packing post-processing.

Palette-Image-to-Image-Diffusion-Models

Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

staged-recipes

A place to submit conda recipes before they become fully fledged conda-forge feedstocks

techblick-robotics-ai-notes

tox-debug

uh2pt-furnace

Ultra-high purity, ultra-high temperature furnace capable of up to 3000 °C

xtal2png-imagen-pytorch-notebooks

Saving notebooks as I run them, even if I might not end up using them for a manuscript and especially to preserve history when I overwrite them.