Chaim Elchik

Lancaster University

Email: c.elchik@lancaster.ac.uk

Chaim Chai Elchik is a PhD student at Lancaster University, funded by an ExaGeo PhD studentship and supervised by Dr Sally Keith, Prof Christopher Nemeth, Dr David Roy, and Dr Christopher Cooney (University of Sheffield).

He holds an MSc in Data Science from The University of Amsterdam, where his thesis developed a framework for multi-view, multiple object tracking using fish data. He has also worked as a researcher with ConservationAI (University of Liverpool) on detecting and tracking elephants in drone videos for automated behavioural data extraction. His research at LEC focuses on decoding biological colour by leveraging AI to analyse big data on animal images in a changing world, questioning whether habitat degradation disrupts the evolutionary match between animal colouration and its background.

Research Interests

Chaim’s research interests lie at the intersection of data science, artificial intelligence, and ecology. He is particularly interested in how novel computational techniques can be applied to large-scale visual datasets to answer fundamental questions about adaptation and biodiversity in the face of environmental change. His work explores the potential of AI to automate the extraction of ecological data from images and videos, providing new avenues for monitoring and understanding the natural world.

Currently, his PhD project focuses on decoding biological colour and its evolutionary significance. By leveraging AI to analyse vast datasets of animal images, Chaim aims to investigate whether habitat degradation disrupts the evolutionary match between an animal’s colouration and its background. This research seeks to provide critical insights into how anthropogenic pressures are impacting adaptive traits, ultimately developing powerful new tools for assessing ecological change at a global scale.

Selected Publications

  • Elchik CC, Burger A, Wich S (2025) A Framework for Detecting and Tracking Elephants in Drone Videos. Drone Systems and Applications.
  • Elchik CC, Nejadasl FK, Ziabari SSM, Alsahag AMM (2025) A Framework for Multi-View Multiple Object Tracking using Single-View Multi-Object Trackers on Fish Data. arXiv: 2505.17201.