From Atmospheric Physics to Machine Learning and Back
We explore a two-way synergy between ML and physical knowledge, with Tom Beucler, Assistant Professor of Environmental Data Science.
Science Machine Learning
Search results for “”
Results 1 to 10 of 12
Rapid Spatio-Temporal Flood Modeling: Hydraulic GNN Approach
Abstract: Numerical modelling is a reliable tool for flood simulations, but accurate solutions are computationally expensive. In the recent years, researchers have explored data-driven methodologies based on neural networks to overcome this limitation. However, most models are used only for a specific case study and disregard the dynamic evolution of the flood wave. This limits...
Forecasting Global Weather with Graph Neural Networks
Abstract: Deep learning offers innovative approaches to modeling complex physical dynamics. This talk will focus on the application of a specific deep learning approach, graph neural networks, to the problem of forecasting global weather. A data-driven model was trained to step forward the current 3D atmospheric state by six hours, and multiple steps are chained...
Hands-On SCiML - SINDy
Bring your laptop to the hands-on ML session on SINDy, run by Alasdair Roy and hosted by the SciML community! Alasdair will give a 45-minute introduction to SINDy. After a break for coffee and cake, we'll tackle the coding challenges that Alasdair has prepared for us. (Note: This is an in-person event. Only the first...
Could deep learning methods replace numerical weather models?
Over the last year, there has been a rise in deep learning methods being used to produce highly accurate weather predictions. These methods include deep learning techniques such as Transformers and Graph Neural Networks amongst others, and have been applied by some of the world's leading tech companies. Some works have made claims that these...
SciML Leeds Hackathon
Welcome to the SciML Leeds Hackathon! This exciting event will focus on using machine learning to identify the dominant ice-water interface via a fusion of SAR and optical imagery. This hackathon is designed to be accessible to participants of all disciplines and skill levels. Whether you're a machine learning enthusiast or simply curious about its...
Physics-based domain adaptation for dynamical systems forecasting; towards a generalizable and interpretable machine learning for applied engineering
Data-driven models, especially machine learning-based models such as recurrent neural networks, are a popular choice for time-series forecasting because they can capture spatiotemporal structures from timeseries data, without reference to the mechanics governing the underlying phenomenon. However, their ability to generalize robustly depends on how well-represented the governing dynamics are in the data. This is...
Weights and Biases Workshop - Machine Learning
The Weights and Biases workshop is a hands-on event designed for researchers seeking to stay up-to-date with the latest developments in machine learning. The workshop will be led by an experienced ML engineer who will guide participants through practical applications of Weights and Biases in their ML projects. Attendees will have the opportunity to learn...
Hands-On SciML: Reinforcement Learning
This event is primarily an in-person event, however an online option is available to attend the talk in the first hour (3-4pm). REGISTER NOW Speaker: Alhanof Alolyan, Ph.D. candidate at School of Computing Reinforcement learning (RL) might serve as an investigative way to explore unexpected and valuable findings in your work. Have you ever considered...
Hands-On SciML: PINNs
Friday 17th February 2023 2-4pm In person only event Room 11.87, Leeds Institute for Data Analytics (LIDA), Level 11, Worsley Building Speaker: Fergus Shone, PhD Researcher, University of Leeds Do you have sparse, low-quality data, but a good understanding of the physical system you are modelling? Then physics-informed neural networks (PINNs) might be the machine learning...