07 Postdoctoral Fellowship at Heriot-Watt University, Edinburgh, United Kingdom

We are looking for outstanding candidates with a PhD in electrical engineering, applied mathematics, physics, computer science, or a related discipline. The ideal candidates will have expertise in computational imaging, with a theory focus (algorithms for image reconstruction, including calibration and uncertainty quantification), with particular interest in deep learning, optimisation, or Bayesian sampling methods and/or an application focus (from astronomical to medical imaging, specifically radio-astronomical, magnetic resonance, or ultrasound imaging), including simulation work and real data processing.

The successful candidates are expected to develop cutting edge deep learning models for multi-scale flow modelling of CO2 in subsurface reservoirs. Two aspects are of special interests (a) pore-to-core scale upscaling (b) upscaling of reactive flow processes. In addition, the successful candidates will contribute to a wide range of AI applications in subsurface flow modelling including (a) stochastic generation of porous media realizations using deep generative models (b) deep learning based property prediction using various architectures (c) Deep learning based proxy modelling with physics based losses and built-in model constrains (e) Effective optimization techniques for physics constrained implicit neural models (f) Efficient coupling of deep learning models to numerical solvers for hybrid CO2 flow modelling. The developed machine learning techniques will be open-sourced and be validated across a wide range of applications and on experimental data and direct numerical simulations generated by the project team.

We are seeking a highly motivated Postdoctoral Research Associate (PDRA) with experience of analysing animal spatial distributions and/or electronic signal processing. The successful candidate will be trained in acoustic signal processing and/or spatial distribution modelling respectively.  The candidate will then analyse the high spatial resolution datasets to estimate fish density as a function of distance from AMS, as well as other ecologically relevant parameters such as fish size and school statistics (number, size, depth, density etc.).  The role requires strong organisational, large dataset handling and analytical skills, preferably in a statistical programming language such as R or Matlab. The role commences on 4 Sep 2023 or soon thereafter and is full time for a fixed term period of 9 months. The successful candidate will be based in Edinburgh, but may be required to undertake both national and international travel.

We are seeking a highly motivated Research Associate (RA) with experience of working at sea to test the integration of the Smartrawl components. The successful candidate will be trained in the marine sciences and/or marine engineering and will deploy the system in the lab and at sea.  They will be required to analyse the resulting camera datasets to improve the performance of the system, working with engineers and other researchers on the project.  The role requires strong organisational, large dataset handling and analytical skills, preferably in a statistical programming language such as R or Matlab or Python. The role commences on 4 Sep 2023, or soon thereafter, and is full time for a fixed term period of 13 months. The successful candidate will be based in Edinburgh, but may be required to undertake both national and international travel.

Biodiversity is declining at an alarming rate. Multiple stressors are driving many of these declines with freshwater (FW) ecosystems particularly impacted. Ephemeral FWs (e.g. marshes, ponds) are exceptionally biodiverse and highly exposed to varied environmental stressors. Amphibians have been a major faunal component of these habitats for at least 350 million years, being highly evolved to these ecosystems. Amphibians and wetlands are some of the most highly threatened Phyla/ecosystems globally, with wetland health key to the climate crisis, including in relation to the high methane levels emitted from human impacted systems. Using both field and laboratory approaches, here we will investigate the environmental stressor combinations driving negative impacts in amphibians (common frog, Rana temporaria) and seek to develop a biomonitoring approach to assess the health of these vital ecosystems. The use of both toxicogenomics and alterations to physiology to assess impacts on tadpoles allows both the anchoring of molecular initiating events to physiological endpoints and adversity as well as mapping responses to stressor combinations. Here pollutant mixture formulations will be based directly on measured levels in ephemeral FWs and combined with other ubiquitous stressors (salinity, heat wave and/or invasive crayfish – Pacifasticus leniusculus cue), all applied at environmentally relevant levels and combinations. These laboratory exposures will be highly novel and of vital importance to understand the true impacts of multiple stressors on iconic amphibian biota that inhabit vital ephemeral FWs. In contrast to the single-endpoint approach, here we propose to use ecological modelling to investigate effects on whole organisms and their populations in order to drastically improve the utility of these data for conservation. 

We are looking for a highly experienced and skilled PDRA who will work on the EPSRC (Part of the UK national research council) project EP/Y017307/1, “Autonomous and Intelligent Laparoscopy Trainer with Real-Time Feedback (AILap)”, funded through UKRI’s “£13 million for 22 AI for health research projects”.  The project aims to develop the next-generation laparoscopy training platform by bringing together physical realism and digital computation and developing automated real-time feedback along with the assessment; overall eliminating the need for supervision and enabling self-training with immediate and effective feedback for laparoscopy training. We will use AI techniques for monitoring and identifying human movements in real-time, by empowering the AI with advanced machine vision. We will develop a fully autonomous laparoscopy self-training system that provides insightful, intuitive, and timely feedback for improvement. We will develop machine vision and machine learning techniques and integrate those with physical box trainers. Our techniques will also be compatible with virtual reality trainers to equip them with automated immediate feedback. AILap system will be tested on a commonly performed laparoscopic procedure associated with proficiency-gain/learning curve and that involves laparoscopic suturing as an unreplaceable skill.