My Webpage

BIDMaP Leadership is excited to collaborate with our colleagues in Physics, Astronomy, and EPS, to include additional seminars in AI + Physical Sciences as part of this series.

We are adding speaker dates all the time - please check back frequently.

This seminar series is intended for UC Berkeley researchers, in particular, BIDMaP faculty, physical science affiliates, and trainees. Please send inquiries and registration requests to

Upcoming Seminars

Image of Biwei Dai

Feb. 22, 2024 – Biwei Dai: Deep Probabilistic Models for Cosmological Analysis and Beyond

Current and future weak lensing surveys contain significant information about our universe, but their optimal cosmological analysis is challenging, with traditional analyses often resulting in information loss due to reliance on summary statistics like two-point correlation functions. While deep learning methods offer promise in capturing...
William Collins

Apr. 4, 2024 - William Collins: Studies of Extreme Weather using Machine Learning and Climate Emulators

Studying low-likelihood high-impact climate events in a warming world requires massive ensembles of hindcasts to capture their statistics. It is currently not feasible to generate these ensembles using traditional weather or climate models, especially at sufficiently high spatial resolution. We describe how to bring the...
omar yaghi

May 3, 2024 - Omar Yaghi

Our final seminar of the academic year will is jointly sponsored by BIDMaP and the Kavli Energy NanoScience Institute. Please note that this seminar will be held on a Friday rather than Thursday, still 12-1pm, and it will be in the Banatao Auditorium rather than...

Past Seminars

Dennis Noll

Feb. 15, 2024 – Dennis Noll: From Particle to Paper: Machine Learning for High-Energy Physics

The analysis of particle collisions at the Large Hadron Collider at CERN helps us to understand the fundamental building blocks of our universe. After years of data taking, the extraction of fundamental insights often requires intricate data analyses. Due to the large volume and complex...
Max Welling

Feb. 8, 2024 – Max Welling: Opportunities for ML in the Natural Science

Some of the most powerful techniques developed in ML are rooted in physics, such as MCMC, Belief Propagation, and Diffusion based Generative AI. We have recently witnessed that the flow of information has also reversed, with new tools developed in the ML community impacting physics...
Tess Smidt

Feb. 1, 2024 - Tess Smidt: Harnessing the properties of equivariant neural networks to understand and design atomic systems

Atomic systems (molecules, crystals, proteins, etc.) are naturally represented by a set of coordinates in 3D space labeled by atom type. This poses a challenge for machine learning due to the sensitivity of coordinates to 3D rotations, translations, and inversions (the symmetries of 3D Euclidean...
Daniel King

Jan. 25, 2024 – Daniel King: Moving Beyond Density Functional Theory with Multiconfigurational Methods and Machine Learning

Density functional theory (DFT) lies at the heart of all practical applications of theoretical chemistry. However, it is well-known that DFT often provides unsatisfactory descriptions of many important systems: non-equilibrium geometries, such as transition states, and strongly correlated systems, such as transition metals and excited...
Ocean waves

Jan. 18, 2024: Fireside chat with Théo Jaffrelot Inizan and Saumil Chheda

Please join us for an interdisciplinary discussion of scientific themes addressed in this series. We'll have lightning talks by Saumil and Théo (BIDMaP Fellows) to start, and then an informal meeting in the seminar space with tables for small or large group discussions.
Mona Abdelgaid

Jan. 11, 2024 – Mona Abdelgaid: Catalyst Design for Dehydrogenation of Light Alkanes to Olefins

Propylene is an important building block for the manufacturing of various chemicals and plastic products. The ever-increasing propylene demand is hardly met by traditional oil-based cracking processes, known for their high energy consumption and substantial CO 2 emissions. Leveraging the abundance of light alkanes from...
Peichen Zhong

Dec. 7, 2023 - Peichen Zhong: Advancing simulation and learning for complex energy materials

The pursuit of carbon neutrality has become a global imperative in the face of climate change, driving the transition to renewable energy sources and the widespread adoption of electric vehicles. Designing new cathode materials for energy storage is one promising avenue. Modern battery materials such...
Ping Tuo

Nov. 30, 2023 – Ping Tuo: Simulating the degradation of photovoltaic perovskites with extended time and length scale

Perovskite is one of the most promising photovoltaic materials for the future. While low stability has long been the bottleneck issue limiting their commercialization. In the past, by using enhanced sampling coupled with machine learning (ML) potential model, I have unraveled the degradation mechanism of...
Zach Zheng

Nov. 16, 2023 - Zach Zheng: ChatGPT for Reticular Chemistry

The advent of advanced large language models like ChatGPT marks a transformative era in scientific research, particularly in the field of reticular chemistry. This seminar focuses on how ChatGPT's natural language processing capabilities enable scientists to accelerate and innovate in their research endeavors. We will...
Weiqiang Zhu

Nov. 9, 2023 - Weiqiang Zhu: Deep Learning for Earthquake Monitoring

Seismic networks have consistently improved across extensive temporal and spatial scales, enhancing our capability to record subtle shaking signals of the Earth. The vast seismic archive poses a challenge for efficient data analysis, but also presents an opportunity to uncover many hidden signals from small...
Abby Doyle

Nov. 2, 2023 - Abby Doyle: Enabling chemical synthesis with machine learning

Abby Doyle is a professor of chemical and biomolecular engineering at the University of California, Los Angeles (UCLA). Her research is focused on tackling unresolved issues in the field of organic synthesis by creating innovative catalysts, catalytic reactions, and synthetic techniques. Recently, the Doyle group...
Alán Aspuru-Guzik

Oct. 26, 2023 - Alán Aspuru-Guzik

Bio Alán Aspuru-Guzik is a professor of Chemistry and Computer Science at the University of Toronto and is also the Canada 150 Research Chair in Theoretical Chemistry and a Canada CIFAR AI Chair at the Vector Institute. He is a CIFAR Lebovic Fellow in the...
Shyue Ong

Oct. 19, 2023 – Shyue Ping Ong: Universal Graph Deep Learning Models for Unconstrained Materials Design

In silico materials design often involves the exploration of vast, diverse chemical spaces. While ab initio methods have been phenomenally successful in materials simulations, their scope of application has always been constrained by their high cost and poor scaling. In this talk, I will highlight...
Jascha Sohl-Dickstein

Oct. 12, 2023 - Jascha Sohl-Dickstein: Learned optimizers: why they’re the future, why they’re hard, and what they can do now

The success of deep learning has hinged on learned functions dramatically outperforming hand-designed functions for many tasks. However, we still train models using hand designed optimizers acting on hand designed loss functions. I will argue that these hand designed components are typically mismatched to the...
Larry Zitnick

Oct. 4, 2023 - Larry Zitnick: Modeling Atoms to Address Our Climate Crisis

Please join for this EECS Colloquium (not part of the regular BIDMaP series; please note different day/time/location ). Many thanks to EECS for welcoming the BIDMaP community to this exciting talk. See more on the EECS website , including a remote participation option.