Skip to main content

Sofia Broomé

Profile picture of Sofia Broomé





Researcher ID

About me

I'm a PhD student in machine learning and computer vision since August 2017, supervised by prof. Hedvig Kjellström, at the division of Robotics, perception and learning (RPL) at KTH. Our project concerns the automation of detecting horses' different pain expressions from video data, in collaboration with veterinarians at the Swedish University of Agricultural Sciences (SLU).

Learning to detect pain in horses automatically is important because it is difficult for humans, even for veterinarian experts. Horses are prey animals and tend to hide their pain, not wanting to show when they are vulnerable. Currently, many horses in Sweden are euthanized prematurely due to disorders which are not really lethal, such as problems with joints, because we detect the conditions too late for treatment.

Student representation

I’m member of the PhD Chapter board, representing KTH doctoral students centrally, for example in the Ethics committee, and member of the PhD student council of the EECS school.


Before I started my PhD, I was in the engineering physics program at KTH, with my MSc in machine learning. My BSc thesis from 2014 was on the use of partial differential equations in climate modeling.


Artificial Intelligence (DD2380), assistant | Course web

Deep Learning in Data Science (DD2424), assistant | Course web