Atul Agrawal

ML Researcher @proximafusion || PhD @TU_Muenchen || UQ/ML + Physics/engineering || Alumnus @IITBHU_Varanasi @CentraleNantes

[Atul Agrawal @Atul_Ag07]

I'll be at @NeurIPSConf 2025 in San Diego presenting our new work from @proximafusion:

ConStellaration - a dataset of QI-like stellarator boundaries + optimization benchmarks.

Poster #2211, Exhibit Hall C/D/E Dec 4, 11am-2pm
Paper: https://t.co/s4mRE8a1B5... #fusion #Al #AI4Sci

[Atul Agrawal @Atul_Ag07]

New paper alert. "Stochastic black-box optimization using multifidelity score function estimator," published in @MLSTjournal (@IOPPublishing ) w\ @mandrakeMojito @SKoutsourelakis prof. Hans Bungartz. https://t.co/4X504ceoNe
#BlackBoxOptimization #SciML #UQ #ML

[Data-Centric Engineering @DCE_Journal]

ARTICLE: From concrete mixture to structural design—a holistic optimization procedure in the presence of uncertainties

✍️@Atul_Ag07, @SKoutsourelakis (@TU_Muenchen), Erik Tamsen and J.F. Unger (@BAMResearch)

👉https://t.co/5XrYaCFXmR

[Atul Agrawal @Atul_Ag07]

Have an optimization problem involving a real-world physics-based simulator? The simulator is stochastic, 💵💵, black-box, multi-modal, and high dimensional? We might have a solution. Check out: https://t.co/4XJ9FhI4YM
(w Kislaya Ravi, @SKoutsourelakis , J.H. Bungartz)

[Atul Agrawal @Atul_Ag07]

New paper on probabilistic data driven model for turbulence closure with @SKoutsourelakis in @ElsevierPhysics Journal of Computational Physics. Open Source link: https://t.co/NzirJQjxNc @TU_Muenchen #RANS #turbulence #DataDriven #SciML

[PS Koutsourelakis @SKoutsourelakis]

New work with @Atul_Ag07 on a probabilistic, data-driven closure model for RANS equations https://t.co/P6dtz1yw6n

[Atul Agrawal @Atul_Ag07]

I will be attending #NeurIPS2023 in person. Would love to chat on probabilistic machine learning + engineering/physics.

[Atul Agrawal @Atul_Ag07]

Our submissions in @NeurIPSConf @ML4PhyS got accepted.
(1/3) When a stochastic, high-dimensional, black-box physics-based simulator is involved in constrained optimization, there are not many viable options out there. We attempt to propose one.
(collab. with @SKoutsourelakis)

[Stat.ML Papers @StatMLPapers]

Multi-fidelity Constrained Optimization for Stochastic Black Box Simulators. (arXiv:2311.15137v1 [math.OC]) https://t.co/YCr3B6rfGf

[Atul Agrawal @Atul_Ag07]

(3/3)
We proposed a physics-based inductive bias term in a popular ML model for the unclosed term in the Reynolds-Averaged Navier-Stokes #RANS equations, leading to improved predictions.
https://t.co/M3JOXAEAgg

[ISRO @isro]

LVM3 M4/Chandrayaan-3 Mission:
LVM3 M4 vehicle🚀 successfully launched Chandrayaan-3🛰️ into orbit.

[PS Koutsourelakis @SKoutsourelakis]

Model uncertainty remains one the most difficult topics in #Uncertainty_Quantification. Here is our attempt to quantify it in the context of the Reynolds-Averaged Navier-Stokes model #RANS, in a physically meaningful manner that still allows probabilistic predictive estimates.

[Atul Agrawal @Atul_Ag07]

Interested in learning a probabilistic, #data-driven #turbulence closure model from sparse velocity/pressure observations, while quantifying the model form error?
(Joint work with prof. @SKoutsourelakis )
#turbulence #RANS #datadriven #probabilisticmachinelearning #UQ

[Statistics (Machine Learning) Papers @StatsPapers]

A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty. https://t.co/puZO1IcmW8

[Atul Agrawal @Atul_Ag07]

Check out our new #JCP paper about:
Simple computational strategies for more effective physics-informed neural networks modeling of turbulent natural convection
The paper is freely available for next 50 days, click below.
https://t.co/0uoWCEleTs
#turbulence #AI #PINN #fluid

[Atul Agrawal @Atul_Ag07]

@RailMinIndia @AshwiniVaishnaw @IRCTCofficial Train 03170 takes 16.5 hours to traverse 560 Kms. Mean speed ~34 kph. Being a customer, I believe I deserve the right to know why so slow even in 21st century.

[Atul Agrawal @Atul_Ag07]

Interested about efficient surrogate for turbulent thermal convection? Or ML for fluid mechanics in general 👇
Work from my time in @LisnLab ( @UnivParisSaclay)
#ML #turbulence #PINNs

[cs.LG Papers @arxiv_cs_LG]

Physics-aware deep neural networks for surrogate modeling of turbulent natural convection. Didier Lucor, Atul Agrawal, and Anne Sergent https://t.co/iZrWALpix5

[PS Koutsourelakis @SKoutsourelakis]

Interested in using unlabeled data (i.e. just inputs) and physical constraints in constructing efficient surrogates for PDEs with high-dimensional parametric inputs in the Small-Data regime? More information in the newly-published J. of Comp. Phys. paper https://t.co/1QHDPLDULO

[Atul Agrawal @Atul_Ag07]

Congratulations prof @SKoutsourelakis and Sebastian.

[PS Koutsourelakis @SKoutsourelakis]

Our paper on "Physics-aware, probabilistic model order reduction with guaranteed stability" has been accepted to #ICLR2021. Congratulations to Sebastian Kaltenbach for putting in all the hard work!
More details: https://t.co/PRycrtF0u8

[Atul Agrawal @Atul_Ag07]

@airindiain What about customer service. I didn't get refund of the tickets cancelled between Germany to India flight. Not even a confirmation mail.

[IndiaAI @OfficialINDIAai]

#RAISE2020 is all set to take place from Oct 5 to 9, 2020 in a virtual avatar. The summit will host some of the world's most renowned AI leaders and decision makers - to understand how AI can be mobilised for greater social good.

Register NOW: https://t.co/I7V7elb8r7

#AIforAll