We think there are important implications for anyone using ML to guide #polymer design or build a #SelfDrivingLab.
English
Data-Driven Organic Materials Lab
18 posts
Data-Driven Organic Materials Lab
@ddom_lab
Seifrid research group in MSE at NC State
Raleigh, NC Katılım Kasım 2023
40 Takip Edilen46 Takipçiler
Good in-distribution performance is the easy part. The harder question is when and why models fail on new polymers and formulations, and the answer isn't as simple as "more data."
English
Out now in @aplmachinelearn: the group's first-ever publication!! 🥳
doi.org/10.1063/5.0303…
English
Data-Driven Organic Materials Lab retweetledi
Not to toot my own horn, but I think this is incredibly important and a very difficult challenge to overcome quickly. Hopefully our call to action can spur faster progress!
Charles Yang@charlesxjyang
I’m excited to share a Call To Action I organized with @RenPhilanthropy "On the Need for Autonomous Science Instruments" Signed by 25 leading researchers across the U.S., U.K., Canada, and Japan, we call for a new generation of autonomous science instruments based on three core pillars: ⚙️ Open Data & Software APIs 🤖 Design-for-Automation 🧩 Instrument Modularity We also published a press release supporting the Call To Action, which includes endorsing quotes from AI & science leaders: @Kevinweil (OpenAI), @AndyHickl (Allen Institute), @jrkelly (Gingko), @teresasmeyer (Carnegie Mellon), @smc_ (Acceleration Consortium), and Michael Brenner (Harvard/Deepmind).
English
We explore how model performance can be assessed in this scenario, and use conjugated polymer conformation as a test case.
English
Conventional or #selfdrivinglab experiments can be informed by data gathered from the literature.
Important scientific challenges often require the development of previously unknown materials: materials discovery.
#machinelearning models are not designed for this scenario...
English
🚨🚨 The group's first preprint is up on
@ChemRxiv! 🥳🥳
Robust Learning from Literature Data: Model Generalizability and Uncertainty for Predicting Conjugated Polymer Solution Conformation
📝 doi.org/10.26434/chemr…
English
Data-Driven Organic Materials Lab retweetledi
Do you know of any papers that have datasets of organic materials (polymers, molecules) with experimental parameters–not material properties, but stuff like concentration, temperature, whatever?
English
Data-Driven Organic Materials Lab retweetledi
Congrats to #Scialog AUT awardees Mark Hendricks @whitmancollege, Jessica Sampson @jesstheligand @UDResearch @ChemistryUD & Martin Seifrid @M_Seifrid @ddom_lab @ncstatemse @NCStateEngr @NCState!
English
Another instrument is up and running! We set up our @GyrosProteinTec PurePep Chorus last Friday. Keep an eye out for exciting developments on this front 👀
English
Data-Driven Organic Materials Lab retweetledi
RCSA, @BeckmanFnd & Frederick Gardner Cottrell Foundation announce awards to 7 multidisciplinary teams in the 1st year of #Scialog: Automating Chemical Laboratories, which aims to accelerate innovation & broaden access within the chemical enterprise. bit.ly/4bMpWru
English
Data-Driven Organic Materials Lab retweetledi
Congratulations to @M_Seifrid @ddom_lab @ncstatemse @NCStateEngr & @CoryMSimon @EngineeringOSU & @cgbischak @UtahChemistry @uofu_science for “Reducing the Cost of Device Development with Closed-Loop Proxy Measurements and Supplemental Characterization.”
English
Data-Driven Organic Materials Lab retweetledi
Our exploration of machine learning to predict #OPV device performance from molecular structure of the materials *and* processing data is now officially published in @JMaterChem A as part of their 2024 Emerging Investigators series!
doi.org/10.1039/D4TA01…
English
English
English
First semester at @ncstatemse is in the books! Not only is @NCStateEngr building the future of #SelfDrivingLabs, but there's an awesome self-driving library
English