Postdoc within Computer Vision methods for real-time classification of microfluidic droplets

NTNU is a broad-based university with a technical-scientific profile and a focus in professional education. The university is located in three cities with headquarters in Trondheim.

At NTNU, 9,000 employees and 42,000 students work to create knowledge for a better world.

You can find more information about working at NTNU and the application process here .

(Video unable to load from YouTube. Accept cookie and refresh page to watch video, or click here to open video)

Ugelstad Laboratory (https://www.ntnu.edu/chemeng/research/ugelstad ) at Department of Chemical Engineering (https://www.ntnu.edu/chemen g) has a vacant 32 months Postdoctoral position within development of Computer Vision methods for real-time detection and classification of microfluidic generated droplets, bubbles and solids.

The postdoctoral fellowship position is a temporary position where the main goal is to qualify for work in senior academic positions.  

Ugelstad Laboratory covers a range of fundamental and applied research within surface, colloid and polymer chemistry. The group is active within topics such as characterisation of complex fluids and interfaces, surfactants and biopolymers, particle synthesis, gas flotation and multiphase flow in porous media. In recent years microfluidic platforms have been used to prepare and characterise dispersed systems, and image-based analyses have provided information about coalescence in emulsions (https://doi.org/10.1016/j.colsurfa.2019.124265 ), drop-bubble attachments (10.1021/acs.energyfuels.8b02236 ), transport of emulsions in porous media (https://doi.org/10.1016/j.ces.2021.117152 ) and synthesis of nanoparticles (https://doi.org/10.1021/acsaem.9b00952 ). In parallel, deep neural networks have been shown to be even more effective at feature extraction than widely used tools within Matlab/Python libraries and ImageJ for the detection and classification of droplets (https://doi.org/10.1016/j.mlwa.2021.100222 ).

We are now looking for a Postdoctoral fellow that can continue to develop the synergies between machine-/deep learning methods and high-throughput imaging on microfluidic platforms. The goal is to develop real-time computer vision tools for detection, classification and tracking of drops, bubbles and solids.

The Postdoctoral fellow will work in close collaboration with other researchers in the group that will carry out experimental microfluidic work related to i) controlling interfacial properties to optimise drop/bubble stability/separation, ii) controlling synthetic conditions to optimise nanoparticle properties, and iii) following transport and retention of drops and particles flowing in porous media. Hence, we primarily want a postdoctoral fellow with strong programming skills and good understanding of experimental work that can collaborate with one or more of these researchers and utilise their data for the development of analytical tools. Candidates with ability to combine strong programming skills with own experimental work, on the other hand, should have good knowledge in optical methods for describing transport and deformation of dispersed systems, and will focus on applying AI/ML/DL methods for the formulation and characterisation of droplet or particle systems stabilised by macromolecules like nanocellulose and proteins.

You will report to Professor Gisle Øye.