BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Andreas Döpp (Ludwig-Maximilians-Universität München)
DTSTART:20230601T160000Z
DTEND:20230601T170000Z
DTSTAMP:20260423T021137Z
UID:MPML/97
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/MPML/97/">Ma
 chine-learning strategies in laser-plasma physics</a>\nby Andreas Döpp (L
 udwig-Maximilians-Universität München) as part of Mathematics\, Physics 
 and Machine Learning (IST\, Lisbon)\n\n\nAbstract\n<p>The field of laser-p
 lasma physics has experienced significant advancements in the past few dec
 ades\, owing to the increasing power and accessibility of high-power laser
 s. Initially\, research in this area was limited to single-shot experiment
 s with minimal exploration of parameters. However\, recent technological a
 dvancements have enabled the collection of a wealth of data through both e
 xperimental and simulation-based approaches.</p>\n\n<p>In this seminar tal
 k\, I will present a range of machine learning techniques that we have dev
 eloped for applications in laser-plasma physics [1]. The first part of my 
 talk will focus on Bayesian optimization\, where I will showcase our lates
 t findings on multi-objective and multi-fidelity optimization of laser-pla
 sma accelerators and neural networks [2-4].</p>\n\n<p>In the second part o
 f the talk\, I will discuss machine learning solutions for tackling comple
 x inverse problems\, such as image deblurring or extracting 3D information
  from 2D sensors [5-6]. Specifically\, I will discuss various adaptations 
 of established convolutional network architectures\, such as the U-Net\, a
 s well as novel physics-informed retrieval methods like deep algorithm unr
 olling. These techniques have shown promising results in overcoming the ch
 allenges posed by these intricate inverse problems.</p>\n\n<p><strong>Refe
 rences:</strong></p>\n\n<p>[1] Data-driven Science and Machine Learning Me
 thods in Laser-Plasma Physics<br />\n<a href="https://arxiv.org/abs/2212.0
 0026">https://arxiv.org/abs/2212.00026</a></p>\n\n<p>[2] Expected hypervol
 ume improvement for simultaneous multi-objective and multi-fidelity optimi
 zation<br />\n<a href="https://arxiv.org/abs/2112.13901">https://arxiv.org
 /abs/2112.13901</a></p>\n\n<p>[3] Multi-objective and multi-fidelity Bayes
 ian optimization of laser-plasma acceleration<br />\n<a href="https://arxi
 v.org/abs/2210.03484">https://arxiv.org/abs/2210.03484</a></p>\n\n<p>[4] P
 areto Optimization of a Laser Wakefield Accelerator<br />\n<a href="https:
 //arxiv.org/abs/2303.15825">https://arxiv.org/abs/2303.15825</a></p>\n\n<p
 >[5] Measuring spatio-temporal couplings using modal spatio-spectral wavef
 ront retrieval<br />\n<a href="https://arxiv.org/abs/2303.01360">https://a
 rxiv.org/abs/2303.01360</a></p>\n\n<p>[6] Hyperspectral Compressive Wavefr
 ont Sensing<br />\n<a href="https://arxiv.org/abs/2303.03555">https://arxi
 v.org/abs/2303.03555</a></p>\n\n<p>&nbsp\;</p>\n
LOCATION:https://researchseminars.org/talk/MPML/97/
END:VEVENT
END:VCALENDAR