[HTML][HTML] Artificial intelligence for materials research at extremes
Materials development is slow and expensive, taking decades from inception to fielding. For
materials research at extremes, the situation is even more demanding, as the desired …
materials research at extremes, the situation is even more demanding, as the desired …
AL4GAP: Active learning workflow for generating DFT-SCAN accurate machine-learning potentials for combinatorial molten salt mixtures
J Guo, V Woo, DA Andersson, N Hoyt… - The Journal of …, 2023 - pubs.aip.org
Machine learning interatomic potentials have emerged as a powerful tool for bypassing the
spatiotemporal limitations of ab initio simulations, but major challenges remain in their …
spatiotemporal limitations of ab initio simulations, but major challenges remain in their …
Autonomous x-ray scattering
Autonomous experimentation (AE) is an emerging paradigm that seeks to automate the
entire workflow of an experiment, including—crucially—the decision-making step. Beyond …
entire workflow of an experiment, including—crucially—the decision-making step. Beyond …
High Throughput Training of Deep Surrogates from Large Ensemble Runs
Recent years have seen a surge in deep learning approaches to accelerate numerical
solvers, which provide faithful but computationally intensive simulations of the physical …
solvers, which provide faithful but computationally intensive simulations of the physical …
Composition-transferable machine learning potential for LiCl-KCl molten salts validated by high-energy x-ray diffraction
Unraveling the liquid structure of multicomponent molten salts is challenging due to the
difficulty in conducting and interpreting high-temperature diffraction experiments. Motivated …
difficulty in conducting and interpreting high-temperature diffraction experiments. Motivated …
Online data analysis and reduction: An important co-design motif for extreme-scale computers
A growing disparity between supercomputer computation speeds and I/O rates means that it
is rapidly becoming infeasible to analyze supercomputer application output only after that …
is rapidly becoming infeasible to analyze supercomputer application output only after that …
Ai-coupled hpc workflows
Increasingly, scientific discovery requires sophisticated and scalable workflows. Workflows
have become the``new applications,''wherein multi-scale computing campaigns comprise …
have become the``new applications,''wherein multi-scale computing campaigns comprise …
Workflow Mini-Apps: Portable, Scalable, Tunable & Faithful Representations of Scientific Workflows
Workflows are critical for scientific discovery. However, the sophistication, heterogeneity,
and scale of workflows make building, testing, and optimizing them increasingly challenging …
and scale of workflows make building, testing, and optimizing them increasingly challenging …
Building the I (Interoperability) of FAIR for performance reproducibility of large-scale composable workflows in RECUP
Scientific computing communities increasingly run their experiments using complex data-
and compute-intensive workflows that utilize distributed and heterogeneous architectures …
and compute-intensive workflows that utilize distributed and heterogeneous architectures …
Towards a Science Exocortex
KG Yager - arXiv preprint arXiv:2406.17809, 2024 - arxiv.org
Artificial intelligence (AI) methods are poised to revolutionize intellectual work, with
generative AI enabling automation of text analysis, text generation, and simple decision …
generative AI enabling automation of text analysis, text generation, and simple decision …