We built a sol-gel synthesis database with phase-purity outcomes: precursors, temperatures, times, pH and impurity phases from ~53,000 papers, ~148,000 records. Free to download as a single JSONL file.
Chen et al, Sci. Data
doi.org/10.1038/s41597-026-0…
Hi all,
Postdoc position open on DOE Genesis and ARPA-e projects to accelerate materials design for catalysis, ionic conductors, and general materials synthesis!
In interested, please apply here:
lbl.taleo.net/careersection/…
Grad students: DOE's SCGSR program can fund you to work with our lab at Berkeley. US citizens/permanent residents only.
Nov 4 deadline, but email me your interests well before that so we can coordinate. We hosted an SCGSR student before and it went well.
lnkd.in/gkpXqDYQ
3
264
We’re hiring a postdoctoral scholar at Lawrence Berkeley National Laboratory to analyze degradation of solar modules, expanding our pvtools.lbl.gov resource.
If interested, please see the job posting here: lbl.taleo.net/careersection/…
Application deadline is Aug 31.
2
298
Multimodal LLMs can serve as a training-free tool for PV inspection: 97.3% accuracy classifying soiling/snow/hail, cell cracks (EL), and hotspots (IR) with GPT-5.1 few-shot. Dataset + web demo released.
Li et al, Solar Energy
doi.org/10.1016/j.solener.20…
pvtools.lbl.gov/pv-image
1
177
A "virtual furnace" maps DFT energies to real synthesis atmospheres (air, Ar, H₂, CO) and predicts which oxides reduce under specific conditions. Most binary oxides land within ~10% of experimental reduction temperatures.
Walters et al, J. Phys. Chem. C
doi.org/10.1021/acs.jpcc.6c0…
5
441
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.
1
218
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.
newscenter.lbl.gov/2026/02/0…
3
214
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!
4
207
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
doi.org/10.1038/s41597-025-0…
8
251
Our group's longstanding involvement in building the Materials Project database in collaboration with researchers worldwide was recently featured in LBL news:
newscenter.lbl.gov/2026/01/1…
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):
science.osti.gov/wdts/scgsr
3
195
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:
jobs.lbl.gov/jobs/duramat-po…
4
201
Laser-written rotating-lattice crystals of Sb₂S₃ enable microscale orientation-dependent thermal conductivity patterning; κ from 0.6 → 2.5 W m⁻¹ K⁻¹. DFT + Wigner transport show lone-pair-induced anisotropy.
Isotta et al.,
Adv. Funct. Mater.
doi.org/10.1002/adfm.2025178…
2
252
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.
doi.org/10.21105/joss.08412
205
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
doi.org/10.1038/s41524-025-0…
1
184
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: lnkd.in/gkpXqDYQ
If interested and eligible, please reach out!
1
177
🚀 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 👉 jobs.lbl.gov/jobs/postdoctor…
#AI #MaterialsScience #PostdocJobs
7
536
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.
doi.org/10.1088/3050-287X/ad…
200


