Themed collection 2023 and 2024 Accelerate Conferences

We share the results of a survey on automation and autonomy in materials science labs, which highlight a variety of researcher challenges and motivations. We also propose a framework for levels of laboratory autonomy from L0 to L5.

Low-cost self-driving labs (SDLs) offer faster prototyping, low-risk hands-on experience, and a test bed for sophisticated experimental planning software which helps us develop state-of-the-art SDLs.

We benchmark GNN models for MLFF-MD and introduce new metrics beyond conventional force and energy errors. Our approach, demonstrated on lithium-ion conductors, aims to broaden ionic conductor screening for batteries.

SynCoTrain is a PU-learning framework using dual GNN classifiers to predict material synthesizability. It leverages co-training to mitigate model bias and enhance generalizability.

ADEL is an automated setup for preparing high-loading electrodes in battery research. Integrated into the MAITENA platform, it provides reliable, high-quality datasets for fast screening of battery materials, significantly accelerating research and development efforts.

An improved high-throughput proxy viscometer based on the Opentrons (OT-2) automated liquid handler.

PBO is a human-in-the-loop optimization algorithm that expedites the search for combinations of parameters that achieve a printing goal that is difficult to measure with sensors but can be readily evaluated from human judgment.

The superior efficiency of multi-objective Bayesian optimization (blue) in optimizing 6 parameters to FDM print the Air Force logo quickly and accurately. Orange: simulated annealing. Green: random sampling.

Archerfish is a low-cost, high-throughput tool for combinatorial materials research. Retrofitted with in situ mixing, Archerfish prints 250 unique compositions per min—a 100× acceleration factor—for aqueous, nanoparticle, and crystalline materials.

We introduce a computational materials discovery framework that integrates conditional generation, molecular dynamics simulations, evaluation, and feedback components to design polymer electrolytes with improved ionic conductivity.

We benchmark the performance of space-filling and active learning algorithms on classification problems in materials science, revealing trends in optimally data-efficient algorithms.

An AI Agent for autonomous development of materials dataset from scientific literature.

We present a simple and fast linear model for discovering organometallic catalysts for the Suzuki–Miyaura cross-coupling reaction, using a combinatorial approach.

We present a two-step prompting approach to streamline literature reproduction, transforming published methods into detailed protocols and then into executable experimental steps for the Mettler Toledo EasyMax automated lab reactor.

We present do-it-yourself instruments that can be both adopted and adapted to fit your self-driving lab.