Spring 2025 LEAP Research Updates: DION HO / MATTHIEU BLANKE

LEAP’s primary research strategy is to improve near-term climate projections by merging physical modeling with machine learning across a continuum from expertise in climate science and climate modeling to cutting-edge machine learning algorithms. The benefits will be significant for both the climate and data sciences communities. Climate scientists and modelers struggle to fully integrate the wealth of existing datasets into their models, while machine learning algorithms have been good at emulating and interpolating but have difficulties extrapolating or predicting extremes. By combining both approaches, LEAP will trigger a significant advancement for data science algorithms applied to physical problems. LEAP will incorporate physics and causal mechanisms into machine learning algorithms for better generalization and extrapolation, while optimally using the wealth of data available to climate science, in order to better predict the future.

LEAP Center

JOIN THE LEARNING THE EARTH WITH ARTIFICIAL INTELLIGENCE + PHYSICS (LEAP) CENTER AT COLUMBIA FOR A SEMINAR ON CLIMATE DATA SCIENCE.

Columbia Engineering Innovation Hub

<h3>LEAP RESEARCH UPDATES</h3><h3>Speakers: Dion Ho (Columbia University), Matthieu Blanke (NYU)</h3><h3> Date: February 20, 2025</h3><h3>Time: 12:00 p.m.</h3><h3>Format: Hybrid</h3><h3>Virtual: Zoom link provided upon registration</h3><h3>In-person: Columbia Innovation Hub, 2276 12th Avenue, Second Floor, New York, NY 10027</h3> *Please note that in-person space is limited.*__________________________________________________________________________________DION HO (Columbia University) "Data-Enhanced Two-Stream Methods for Computing Atmospheric Flux Transfer"Abstract: The two‐stream equations are the most parsimonious general models for radiative flux transfer with one equation to model each of upward and downward fluxes. This framework undergirds almost every weather and climate model worldwide for it enables blisteringly fast computations, and it is applicable to both longwave and shortwave radiation though our focus is on the latter. Current methods under the two-stream framework are, however, known to be inaccurate in many circumstances, for example, when modeling shortwave flux transfer through arctic aerosols. Consequently, we seek to use data to enhance two-stream methods while preserving their computational efficiency. We will present our new methods which involve spline interpolation, symbolic regression and neural networks as well as present both empirical and theoretical evidence for our improvements.Bio: Dion is a PhD candidate in the Department of Applied Mathematics and Applied Physics advised by Lamont Research Professor Robert Pincus. He is interested in PDEs, numerics, and their applications to atmospheric radiation. He graduated from Yale-NUS (NUS stands for the National University of Singapore) College with a Bachelor of Science and a major in Mathematical, Computational and Statistical Sciences. In his undergraduate years he worked with the Unified Transform Lab to further develop the Unified Transform (Fokas) Method for solving high-order PDEs, and separately also researched on the nonlinear Schrodinger equation.***MATTHIEU BLANKE (NYU) "Interpretable Meta-Learning of Physical System"Abstract: Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in multi-task learning, but they rely on black-box neural networks, resulting in high computational costs and limited interpretability. We introduce a new meta-learning model capable of learning efficiently from multiple environments, with an affine structure with respect to the learning task. We prove that this architecture can identify the physical parameters of the system, enabling interpretable learning. We demonstrate the competitive generalization performance and the low computational cost of our method by comparing it to state-of-the-art algorithms on physical systems, ranging from toy models to complex, non-analytical systems. The interpretability of our method is illustrated with applications to parameter identification and to adaptive control and system identification.Bio: Matthieu Blanke is a Postdoctoral Associate at NYU Courant Institute, working with Sara Shamekh on deep learning for parameterizations in climate models. He received his PhD from Ecole Normale Supérieure (ENS) in Paris. Learn More: <a href="https://leap.columbia.edu" title="https://leap.columbia.edu" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">LEAP</a>

DION HO Columbia UniversityMATTHIEU BLANKE ENS Paris

Summer 2026 Lecture in Climate Data Science: COURTNEY COGBURN

Columbia Innovation Hub - Tang Family Hall

Spring 2026 Lecture in Climate Data Science: Research Update by KARA LAMB

Summer 2026 Lecture in Climate Data Science: ANN LEE

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

Spring 2025 LEAP Research Updates: DION HO / MATTHIEU BLANKE

More events from LEAP Center

Discover more events from LEAP Center, from Science & Tech to other experiences you might love.

Summer 2026 Lecture in Climate Data Science: COURTNEY COGBURN

Spring 2026 Lecture in Climate Data Science: Research Update by KARA LAMB

Summer 2026 Lecture in Climate Data Science: ANN LEE

Still looking for the right event?

Explore all events in New York and filter by date, category, and more to find the perfect fit.

Spring 2025 LEAP Research Updates: DION HO / MATTHIEU BLANKE

More events from LEAP Center

Discover more events from LEAP Center, from Science & Tech to other experiences you might love.

Summer 2026 Lecture in Climate Data Science: COURTNEY COGBURN

Spring 2026 Lecture in Climate Data Science: Research Update by KARA LAMB

Summer 2026 Lecture in Climate Data Science: ANN LEE

You might also like...

Browse more events with different dates, prices, and formats to find your next great experience.

Still looking for the right event?

Explore all events in New York and filter by date, category, and more to find the perfect fit.