Important: Students should not restrict their search for a supervisor to those listed below. Use other sources of information on research groups to find out about possible supervisors. Most UROP research experiences are obtained with staff who do not advertise their availability. However, please also take note of the list of non-participating staff.

 

NEW (16 April 2024)

Application of AI in Empirical Analyses of Complex Atomic Spectra and Energy Level Structures

The spectra and energy levels of neutral and low ionisation stages of many-electron atoms (e.g. the iron-group and lanthanide elements) are of great interest in the spectroscopy of astronomical objects such as stars and kilonovae. For the meaningful interpretation of state-of-the-art high resolution astronomical spectra acquired with modern telescopes there is a requirement for highly accurate laboratory measured atomic level energies and spectral line wavelengths reference data. However, incompleteness in such atomic data still plagues astronomy.

An observed atomic spectral line gives us information on only the energy separation between two atomic energy levels and the likelihood of the transition. However, the level energies (relative to ground or ionisation) must be known in order to accurately determine the nature of the electron wavefunctions and produce meaningful spectral reference data. Empirically determining the exact level energies must be approached very carefully and theoretical calculations are used as guidance, because the complex spectra for a single ‘heavy’ element can contain up to tens of thousands of transitions.

This project will focus on exploring and developing novel machine learning methods to analyse high-resolution complex atomic emission spectra recorded in the laboratory. For example, investigating possible advantages of using neural networks over traditional methods in spectral line detection and fitting, or designing a reinforcement learning framework for determining level energies from matching simple sets of observed transition wavelengths and relative line intensities with corresponding theoretical predictions.

The candidate is expected to document the research and present significant or promising results to a wider audience. By the end of the project, the candidate should obtain a more holistic perception of scientific research, acquire background in atomic and experimental physics, and gain proficiencies in applying machine learning algorithms to complex real-world problems.

Skills and experience required: Programming skills in python (for PyTorch or TensorFlow) and knowledge/experience in machine learning algorithms are required. Knowledge/interests in atomic physics, high-resolution spectroscopy, uncertainties, and plasma physics would be bonuses.

Preferred timing of the UROP: Summer vacation or starting during summer term if all degree programme commitments have been concluded.

Bursary: a bursary will be available to the student who obtains the UROP.

Contact details: Mr Milan Ding and Prof. Juliet Pickering, Physics Department, Space, Plasma & Climate community, Imperial College, South Kensington campus.

Please send your CV and academic transcript in an email cover letter to milan.ding15@imperial.ac.uk