Congratulations to Alison Rhoads, an undergraduate researcher with our group, on winning a prestigious DOE CSGF Award!
Alison will be heading off to U. Chicago next to pursue her PhD and continue her great work in materials theory.
Congratulations to Hrushikesh Sahasrabuddhe in winning the best poster award at MRS Spring!
Hrushikesh along with our collaborators have been generating a database of DFT phonon data (PBEsol level, 2nd order, 26K+ entries). We hope to share this work with the community soon.
About FORUM-AI, our new Berkeley Lab project to use AI agents to solve materials problems. We're now starting to ramp up and I'd be happy to chat about our efforts.
https://t.co/7VUlVJFmKl
Congratulations to Baojie Li from our group on winning a best poster award at the recent Photovoltaic Reliability Workshop for his work on using LLMs to analyze solar PV degradation!
Solid-state synthesis rarely reports “failures.” We used LLMs to report 80,806 syntheses, including 18,869 impurity-phase reactions. ~15% of cases form impurity phases even when the target phase is thermodynamically more stable.
Lee et al., Sci Data
https://t.co/MLs2JUcUd3
Our group's longstanding involvement in building the Materials Project database in collaboration with researchers worldwide was recently featured in LBL news:
https://t.co/o0g70linxX
If you're a current graduate student and want to spend time working with our lab in Berkeley (funded), please look at the SCGSR program and reach out to me with your interests (check full eligibility requirements first):
https://t.co/aXxjHfsiPX
We’re hiring a postdoctoral scholar at Lawrence Berkeley National Laboratory to work at the frontier of AI-enabled synthesis science and materials degradation.
Please apply by Feb 19 for full consideration:
https://t.co/DVvOhd7Lwz
Happy to collaborate on hashin_shtrikman_mp, a Python tool that combines theoretical bounds, genetic ML optimization, and Materials Project data to design optimal composite formulations from desired properties.
Becker et al., J. Open Source Softw.
https://t.co/1JOpEn8g4X
Can machines learn microscopy without labels?
Work with KIT/UCB on self-supervised ConvNeXtV2 achieves ~41% error reduction over untrained models (15% vs ImageNet) for particle segmentation using 25k SEM images.
Rettenberger et al., npj Comp Mater
https://t.co/hc1EzqeIia
U.S. PhD students: interested in spending time at Berkeley Lab working with us on AI agents, computational materials design, data-driven synthesis, or the Materials Project?
Check out the DOE SCGSR program: https://t.co/SG2vnDqBOn
If interested and eligible, please reach out!
🚀 We’re hiring a Materials AI Postdoc at Berkeley Lab! Join us in building the next generation of AI for materials discovery, spanning simulations, autonomous labs & DOE supercomputers via AI agents.
Apply here 👉 https://t.co/fYMTd3G1Xa
#AI#MaterialsScience#PostdocJobs
Electrocatalysts can treat tough water contaminants, but discovery is slow. We review how ML potentials + autonomous screening platforms can accelerate catalyst design for next-gen water purification.
Wang et al., AI for Sci.
https://t.co/EqiIsSTYef
With ~180K materials and millions of calculated properties, the Materials Project enables inverse design, synthesis screening, and discovery. Examples include phosphors, thermoelectrics, electrides, and battery electrolytes.
Horton et al, Nature Materials
https://t.co/cLuFg01mmA
Atomate2 is a fully modular workflow platform for high-throughput DFT and MLIP calculations. Supports ~30 workflows, hybrid DFT/MLIP chaining, defect and phonon automation, & more - collaboration amongst multiple groups!
Ganose et al., Digital Discovery
https://t.co/pjXDSoKQI8
MLIP evaluation: Matbench Discovery focuses on predicting stability; universal interatomic potentials (UIPs) are top performers w/ ~5X improvement in discovery efficiency. Regression accuracy not the same as discovery!
@jrib_ et al., Nat. Mach. Intell.
https://t.co/xwNSuIiHNF
PV-Pro detects off-MPP behavior in solar arrays using real-time modeling that accounts for system degradation. Analyzing a 271 kW array, ~5% of points are detected as off-MPP, largely due to current loss.
Li et al, IEEE PVSC
https://t.co/f767qK7gn1
RuO₂-based catalysts remove >90% Se(IV) in wastewater (8 hours). DFT shows Sn doping lowers the energy barrier for reduction by stabilizing intermediates, explaining the superior activity of Ru₀.₉Sn₀.₁Oₓ/TP over pure RuO₂.
Hao et al, Nano Lett.
https://t.co/pPwTKCgb4h
BiFeO3 synthesis: simulations indicate that Bi nitrate + 2ME form stable dimers via nitrite bridges, contrary to the assumed full solvation route. Text mining shows precursors most often leading to phase-purity.
Baibakova & Cruse et al, Digital Discovery
https://t.co/NCDxGZQQaL