BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:62b9968cacdff5999adf737e10b1bb1d
DTSTAMP:20260715T025733Z
SUMMARY:I-X Seminar Series: Machine learning for the characterisation and d
 esign of battery electrodes with Sam Cooper
DESCRIPTION:Lecture Title \nMachine learning for the characterisation and 
 design of battery electrodes\nSpeaker \nSam Cooper is a Senior Lecturer i
 n the Dyson School of Design Engineering\, Imperial College London.\nTalk 
 Summary\nBattery companies want to know the relationship between their man
 ufacturing parameters and the performance of the resulting cells\, so that
  they can optimise their products for particular applications\, reduce cos
 ts\, and improve yield. The literature contains many examples of physics-b
 ased models of the various manufacturing processes (including mixing\, coa
 ting\, drying and calendaring)\, but these systems are hugely complex\, an
 d as a result they are expensive to simulate and hard to validate. Recent 
 advances in generative machine learning (ML) methods have allowed the rela
 tionship from manufacturing parameters to microstructure to be directly le
 arned from data. In this talk I will present a modular approach to the cel
 l optimisation cycle that makes use of these ML methods\, in combination w
 ith GPU accelerated metric extraction (TauFactor 2)\, electrochemical cell
  simulation (PyBaMM)\, and Bayesian optimisation. In addition\, I will be 
 introducing a new kintsugi SEM imaging method for accurately observing the
  nanostructure of the carbon binder domain\; “VoxCel” an open-source\,
  voxel-based\, GPU-accelerated\, multi-physics cell simulation\; ML method
 s for generating 3D data from 2D images\, as well as\, inpainting artefact
 s in image data\; and a data fusion method for combining multi-modal datas
 ets using GANs. Lastly\, I’ll present a webapp that normalises the data 
 obtained from testing cells in a lab for easy comparison to commercial cel
 ls: cell-normaliser.\nSpeaker Bio\nSam Cooper is a Senior Lecturer in the 
 Dyson School of Design Engineering\, where he lead the TLDR group (Tools f
 or Learning\, Design\, and Research). The TLDR group largely focus on the 
 development of methods for characterising\, simulating\, and optimising en
 ergy systems. Over the past five years\, the group have released a variety
  open-source software that enable the research community to rapidly analys
 e experimental data to extract materials’ properties. Their recently pap
 ers demonstrate how machine learning methods can be used for dimensionalit
 y expansion (2D to 3D image generation) and data fusion (combining high-re
 s 2D data with low-res 3D data). In this talk\, Sam Cooper will explain a 
 modular workflow for designing optimised battery electrodes.\nVisit the g
 roup’s webpage to find out more: If you would like to join the group an
 d collaborate – do get in touch via email. 
URL:https://www.imperial.ac.uk/events/167222/i-x-seminar-series-machine-lea
 rning-for-the-characterisation-and-design-of-battery-electrodes-with-sam-c
 ooper/
DTSTART;TZID=Europe/London:20231010T140000
DTEND;TZID=Europe/London:20231010T153000
LOCATION:I-X 5 | Level 5\, Translation and Innovation Hub (I-HUB)\, White C
 ity Campus\, Imperial College London\, London\, W12 0BZ\, United Kingdom
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
DTSTART:20231010T140000
TZNAME:BST
TZOFFSETTO:+0100
TZOFFSETFROM:+0100
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR