BIDMaP is happy to be jointly hosting this year's seminar series with colleagues in computational physical sciences, including collaborators from the departments of Physics and Astronomy, and the Lawrence Berkeley National Laboratory.
The unique structural diversity of metal-organic frameworks (MOFs) makes them very promising for applications in many environmental and industrial fields, such as carbon capture, drug delivery and generation of renewable energies...
Heterogeneous catalysis plays central role in energy and materials production thus transforming it holds the key for clean energy, clean air, clean water, and sustainable chemical production. The critical issue is that we still do not know exactly in most cases...
Agents for Scientific Discovery We will present how multi-agent systems can be designed to perform scientific research. We will show how we are using them to solve hard open-ended research problems, in some cases outperforming humans operating without them. The agents and systems we develop...
Stay tuned for more information about this seminar. Speaker Bio: Phiala Shanahan grew up in Adelaide, Australia, and obtained her BSc from the University of Adelaide in 2012 and her PhD, also from the University of Adelaide, in 2015. Before joining the MIT physics faculty in July 2018, Prof. Shanahan...
In this talk I will trace our trajectory through the use of machine learning in catalysis and machine learning through the development of machine learned potentials as fast surrogate models for quantum chemical calculations, the development of new generative machine learning approaches to optimization, and finally to the integration of LLMs...
Join BIDMaP for a seminar featuring three postdoctoral fellows whose work spans AI-driven materials discovery—from generative models that explore reaction pathways, to high-throughput computation that maps material phase diagrams, to experimental platforms that close the loop with autonomous, ML-guided synthesis and characterization.
Gradient-based Markov Chain Monte Carlo (MCMC) methods are an essential tool for high dimensional sampling, used in a number of applications, from Chemistry and Materials Science to Statistical Physics, Solid State Physics and Lattice QCD, as well as in Bayesian Inference...
There will be tremendous advances in AI for Chemistry and Materials Science in the coming years. However, many AI models and simulations are currently not running efficiently on GPUs...
Computational materials science has seen tremendous progress since the early days of density functional theory. Stable algorithms enabled high-throughput computing, which in turn enabled machine-learned potentials (MLPs) that...
Machine learning in transition metal chemistry has historically lagged behind other areas of chemistry due to the combination of diverse chemical bonding and limitations in high-quality...
Optimal Transport: A Unifying Language for Physics and Machine Learning Optimal transport (OT) theory, first conceived to solve problems of moving dirt, has since evolved into a powerful mathematical framework with...
The design of new materials has always been a slow process taking decades from problem formulation to initial discovery to commercialization. Today, advances in high-throughput...
Berend Smit, a professor at EPFL and Foreign Member of the Royal Netherlands Academy of Arts and Sciences, is known for his pioneering work in molecular simulation techniques for energy applications. His career spans...
Artificial Intelligence and Machine Learning are transforming scientific discovery. Wahid Bhimji, who leads NERSC’s Data and AI Services Group, will discuss applying deep learning and generative models at scale to...
Machine-learning techniques are often applied to perform "end-to-end" predictions, making black-box estimates of a property of interest using only a coarse description of...
Developing fast and efficient methods for simulating our observable Universe is a key challenge in maximizing information extraction from cosmological datasets. Current simulations are too slow to scale...
Artificial Intelligence and Machine Learning (AI/ML), especially deep learning, are becoming increasingly popular across scientific fields, with many believing they will have transformational impacts...
