https://xitter.cf/t.co/qHA6A73gFX
Joined July 2019
- Tweets307
- Following544
- Followers506
- Likes2.1K
Pinned Tweet
Our Perspective on 'Machine Learning for Analysis of Experimental Scattering and Spectroscopy Data in Materials Chemistry' is now on @ChemRxiv 👇
doi.org/10.26434/chemrxiv-20…
@kirsten_mj @raghavian @keeeto2000
A thread 🧵1/8
Jake Sullivan retweeted
Excited to explore how #compchem & AI are advancing amorphous material design in our latest @NatRevMater Perspective.
Big thanks to @vl_deringer, Ata, @SodeAndy, & @thesiminegroup for the great collaboration!
Read more: rdcu.be/d3JD6
Jake Sullivan retweeted
Can we “design” amorphous materials with useful properties? In a Perspective in @NatRevMater, we argue that #compchem and AI are bringing us closer towards this ambitious goal.
Thank you @YuanbinLiu2, Ata, @SodeAndy, & @thesiminegroup! 🙂
Read more here: rdcu.be/d3JD6
Jake Sullivan retweeted
Thrilled to have our work on #operando X-ray total scattering combined with #SAXS and #EXAFS analysis to study Ir NPs for #OER published in @J_A_C_S it has been such a fantastic and exciting collaborative effort!@jensengroup_cph @ArenzLab @HEAcatalysis @CHEMUCPH @esrfsynchrotron
Monitoring Structural Changes in Iridium Nanoparticles during Oxygen Evolution Electrocatalysis with Operando X-ray Total Scattering | JACS @unibern @UCPH_Research @koebenhavns_uni #Ir #Nanoparticles #Oxygen #Electrocatalysis #Operando #XRay #Scattering pubs.acs.org/doi/10.1021/jac…
Jake Sullivan retweeted
Happy to see this one out in @JApplCryst. Result of international collaboration during my PhD, high quality data from @p021_desy @desynews, and support @DanScatt_DK. @dorthe_ravn @RavnsbaekGroup @NATsdu @Chemistry_AU @ResearchUGent @billingegroup @Columbia doi.org/10.1107/S16005767240… – at Padua, Veneto
Jake Sullivan retweeted
It is @kdd_news week! If you are #KDD2024 do check out our work on a new large-scale inorganic materials dataset for graph ML. First authos on this work @UlrikFJ1 and @fupperlidt will be there!
Paper: dl.acm.org/doi/10.1145/36375…
Are you looking for a challenging dataset to put your #graph #ML (or LLM) methods to test? Check out CHILI: our latest work where we curate a large-scale (>183M nodes, >1.2B edges) and a medium-scale graph dataset (>6M nodes, >49M edges) for #Inorganic #Nano #Materials modelling.
Jake Sullivan retweeted
Great spirit and impressive turnout at our workshop for Democratisation of self-driving labs @acceleration_c 2024 conference @UBC! Impressive hands-on demonstrations of low-cost SDL solutions 🙌#TeamCAPeX @toniobuonassisi @SterlingBaird1 @BrendenPelkie @GrundforskFond @DTUtweet
Jake Sullivan retweeted
#KDD2024 🚀
I'm delighted to share that our latest paper, featuring #CHILI, a graph #ML dataset for inorganic materials chemistry, will be presented at @kdd_news!
Kudos to @UlrikFJ1 @SodeAndy @raghavian @kirsten_mj !🎉
🚨Our recent work on chemically-informed large-scale inorganic (CHILI) nanomaterial datasets is now on arXiv!
Presenting the first large-scale nanomaterial datasets with high structural and elemental diversity.
📝Preprint: bit.ly/CHILI-preprint
🔗Code: bit.ly/CHILI-code
Jake Sullivan retweeted
#KDD2024
Excited that our paper that introduces #CHILI: a new, large-scale graph #ML dataset for inorganic materials chemistry will be presented at @kdd_news!
Congratulations to @UlrikFJ1, @fupperlidt for a strong effort.
@kirsten_mj @SodeAndy
Are you looking for a challenging dataset to put your #graph #ML (or LLM) methods to test? Check out CHILI: our latest work where we curate a large-scale (>183M nodes, >1.2B edges) and a medium-scale graph dataset (>6M nodes, >49M edges) for #Inorganic #Nano #Materials modelling.
Jake Sullivan retweeted
What a start to the #CAPeXPioneerLecture series 🙌🏻 A fully packed lecture room @DTUtweet and our virtual #TeamCAPeX hubs at @aalborg_uni etc for @toniobuonassisi @MIT amazing lecture “Towards Realizing Self-Driving Laboratories: A strategic checklist” -fantastic! @GrundforskFond
Jake Sullivan retweeted
Congratulations to @SodeAndy @dtutweet, recently named as one of @ForbesUnder30 Europe (Science and Healthcare) and currently working with @vl_deringer @OxfordChemistry
chem.ox.ac.uk/article/andy-s…
ALT Portrait photo of Andy Sode Anker, a smiling man with brown hair and a beard who is wearing a navy button-up shirt standing against a grey background.
Jake Sullivan retweeted
Big congrats to @SodeAndy - Another young scientist on the Forbes list of 30 under 30 Europe. Andy is collaborating with our Pioneer Center #TeamCAPeX, @DTUtweet 👇 dtu.dk/english/news/news-abo…
Jake Sullivan retweeted
🚀 Huge congratulations to @SodeAndy for landing on the prestigious Forbes list!
His AI-driven 'self-driven lab' revolutionizes material discovery. Collaborating with #TeamCAPeX, he's accelerating progress in nanomaterials synthesis.
🌟 Keep inspiring, Andy! #Power2Xperts – at Lyngby-Taarbæk, Danmark
Congratulations to Andy Sode Anker, who is included in @Forbes '30 under 30 Europe' in the Science and Healthcare category. #30under30 #EnergyTechnology #NanoTechnology #MachineLearning @SodeAndy dtu.dk/english/news/news-abo…
Jake Sullivan retweeted
Congratulations to Andy Sode Anker, who is included in @Forbes '30 under 30 Europe' in the Science and Healthcare category. #30under30 #EnergyTechnology #NanoTechnology #MachineLearning @SodeAndy dtu.dk/english/news/news-abo…
Jake Sullivan retweeted
Congratulations to @SodeAndy, a former student at @koebenhavns_uni, @CHEMUCPH with the fine acknowledgment by @Forbes making it on the list "30 under 30" in #SCIENCE & #HEALTHCARE forbes.com/30-under-30/2024/… – at Copenhagen, Denmark
Surreal to be mentioned on the @ForbesUnder30 Europe 2024 list. 🧑🔬
Thanks to the organisers of this amazing Bayesian optimisation hackathon. I learned a lot! ☺️
Our team developed a simulation of a self-driving laboratory for materials discovery serving to benchmark the efficiency of various BO algorithms 🤖 @gabe__graves @AppiahAmpofoSa1
I'm pumped for the BO hackathon tomorrow! Nearly 400 registrants and 36 confirmed projects and counting 🚀 The hackathon website with all the necessary info is at ac-bo-hackathon.github.io/. See you soon!
We constructed two different baseline algorithms which find the optimal synthesis parameters through a bruteforce approach in 4808 and 6400 steps.
Using Bayesian optimisation we can improve this to tens of experiments.
If you find BO for materials discovery interesting, take a look at our GitHub:
github.com/AndySAnker/ScattB…
Here, you can find examples of how to use the benchmark and follow the scoreboard.
