- About me

Described as "Smart and Hardworking", I studied for my Ph.D.
in astrophysics and machine learning at the Open University
with excellent skills in machine learning, large scale data
extraction, manipulation and analysis as well as forming
mathematical computer models based on the available data

— Skills

Data Science
Machine learning
Data Analysis
Python
Creation and execution of numerical
mathematical models
Cloud computing
Teaching 
3D Modelling   

— Work experience

DATA SCIENTIST

The Alan Turing Institute, Project Bluebird | London | 2023
– Present

INTERN

The Alan Turing Institute, Project Bluebird | London | 2022
– 2023 (6 months)

As an intern on Project Bluebird, I worked on two different
projects. I first studied and combined a number of NATS en-
route datasets to create ATC complexity metrics and used
PCA, Random Forests and Neural Networks to study
correlations between these complexity features in the dataset
and data outputs from the NATS conflict detection tool. This
enabled focused training of the AI ATC controller and was
used to select scenarios for the project's 6-week AI agent
trials in the summer of 2023. I also used a range of
mathematical algorithms to group aircraft trajectories to
identify the most mathematically comparable routes though
ATC sectors.
 

MENTOR

MentorDanmark | Online, Denmark | 2019 – 2022

I worked on tutoring High School students in physics and
mathematics a couple of hours a week, as well as preparing
them ahead of exams.

— Education

The Open University

Ph. D, Astrophysics and Machine Learning / 2019 - 2025

I worked on using Convolutional Neural Networks to Super-
Resolve images from the Herschel Space Observatory in
order to obtain additional information from older data. To
achieve this task, I used a De-Noising Autoencoder. Further, I
worked to understand, cluster and combine the new dataset,
with older data to identify differences and similarities and
identify interesting targets for future observation. The name of
the project was "Super-resolving Herschel SPIRE images
using Convolutional Neural Networks". This project was
carried out under the supervision of Prof. Stephen Serjeant,
Dr. Jane Bromley and Dr. Hugh Dickinson.
 

University of Copenhagen

Master's degree, Astrophysics / 2016 - 2018
 

Durham University

Bachelor's Degree, Physics, 2012 - 2016

— Publications

Ph. D. Thesis

Super-resolving Herschel SPIRE images using Convolutional Neural Networks — Lynge Lauritsen

DOI: https://doi.org/10.21954/ou.ro.00104194

Wide-field sub-millimetre surveys have allowed many advances in galaxy evolution, but their lower angular resolution, compared to optical surveys, limits the science exploitation. Consequently, various deconvolution methods have been developed. In the last decade, Generative Adversarial Networks have been increasingly developed and used to attempt deconvolutions on optical data. This thesis presents an U-Net with a novel loss function to provide super-resolution on sub-millimetre observations. This approach is successfully demonstrated on Herschel SPIRE 500μm COSMOS data, with the super-resolving target being the corresponding JCMT SCUBA-2 450μm images. The JCMT SCUBA-2 image information is reproduced with good accuracy in both the point source positions and fluxes and good completeness and purity. This roughly doubles the de-convolved area in the COSMOS field compared to previous de-convolution work using multi-wavelength priors. The super-resolution results are cross-matched to existing mid-infrared and sub-millimetre surveys by associating them with their nearest neighbour and also using a statistically motivated association method referred to in this thesis as the likelihood ratio method. The associated source fluxes are either based on the cross-matched catalogue fluxes or calculated using forced photometry at the super-resolved position. These results are used to calculate associated photometric redshifts. Multiplicity calculations are made on the COSMOS field using the super-resolution results from this thesis, alternative de-convolution results provided by the Herschel Extragalactic Legacy Project, and the JCMT SCUBA-2 STUDIES survey. These are compared to theoretical predictions from the Empirical Galaxy Generator. Finally, foreground cirrus contamination is found to be the limiting factor in the expansion of the super-resolution algorithm to the fields studied by the JCMT SCUBA-2 RAGERS project. However, a boxcar background subtraction filter is developed that is partially successful in removing cirrus contamination and in improving the super-resolution.

Papers

• Superresolving Herschel imaging: a proof of concept using Deep Neural Networks, Lynge Lauritsen, Hugh Dickinson, Jane Bromley, Stephen Serjeant, Chen-Fatt Lim, Zhen-Kai Gao, Wei-Hao Wang, Monthly Notices of the Royal Astronomical Society, Volume 507, Issue 1, October 2021, Pages 1546–1556, https://doi.org/10.1093/mnras/stab2195.
• Super-resolving Herschel - a deep learning based deconvolution and denoising technique, Koopmans, Dennis & Wang, Liande & Margalef Bentabol, Berta & Marca, Antonio & Bethermin, M. & Bisigello, Laura & Gao, Zhen-Kao & Lagos, Claudia & Lauritsen, Lynge & Serjeant, Stephen & Tak, F. & Wang, Wei-Hao. (2025), https://doi.org/10.48550/arXiv.2512.13353.
  
• The RAdio Galaxy Environment Reference Survey (RAGERS) - Evidence of an anisotropic distribution of submillimeter galaxies in the 4C 23.56 protocluster at z = 2.48, D. Zhou, T. R. Greve, B. Gullberg, M. M. Lee, L. Di Mascolo, S. R. Dicker, C. E. Romero, S. C. Chapman, C.-C. Chen, T. Cornish, M. J. Devlin, L. C. Ho, K. Kohno, C. D. P. Lagos, B. S. Mason, T. Mroczkowski, J. F. W. Wagg, Q. D. Wang, R. Wang, M. Brinch, H. Dannerbauer, X.-J. Jiang, L. R. B. Lauritsen, A. P. Vijayan, D. Vizgan, J. L. Wardlow, C. L. Sarazin, K. P. Sarmiento, S. Serjeant, T. A. Bhandarkar, S. K. Haridas, E. Moravec, J. Orlowski-Scherer, J. L. R. Sievers, I. Tanaka, Y.-J. Wang, M. Zeballos, A. Laza-Ramos, Y. Liu, M. S. R. Hassan, A. K. M. Jwel, A. A. Nazri, M. K. Lim, U. F. S. U. Ibrahim, A&A 690 A196 (2024), https://doi.org/10.1051/0004-6361/202348500.

• A Probabilistic Digital Twin of UK en Route Airspace, Nick Pepper, Adam Keane, Amy Hodgkin, Dewi Gould, Edward Henderson, Lynge Lauritsen, Christos Vlahos, George De Ath, Richard Everson, Richard Cannon, Alvaro Sierra-Castro, John Korna, Benjamin J. Carvell and Marc Thomas, AIAA 2026-1794, Session: Air Traffic Management Simulation and Digital Twins II, https://doi.org/10.2514/6.2026-1794.