Team
BIOSTAT brings together researchers interested in statistical methods and their interplay with AI. Through collaborations with bio-engineers, we develop innovative data-driven approaches to study some of the most pressing challenges facing our planet, including biodiversity loss, climate change and environmental pollution.
Group leader

Stijn Luca
Associate Professor
Stijn works at the interface of mathematical statistics and its applications in bioscience engineering. His research interests include extreme value theory, sampling design, spatio-temporal modelling and their connections to AI.
Team members

Bastiaan Van Velthoven
Research & Teaching Assistant

Muhammad Ajmal
PhD Student

Max Savery
PhD Student

Qing Yu
PhD Student

Francesco Bartoli
PhD Student

Rutendo Musimwa
PhD Student
Affiliated PhD students

Amber Van Reepingen
Affiliated PhD Student
Former PhD students
Lixuan An
Analysis of Exceedance Patterns in Distributional Tails based on Extreme Value Theory | PDF
Ghent University
Date of defence: 05 February 2026
Yonas Yehualashet Tefera
Data-Driven Health Assessment and Prognostics of Assets with Limited Data | PDF
Supervised in collaboration with KU Leuven
Date of defence: 05 December 2025
Matthys Lucas Steyn
Open-Set Recognition using Extreme Value Theory
Supervised in collaboration with Stellenbosch University
Date of defence: 31 January 2025
Camille Van Eupen
Integrating opportunistic citizen science data and species distribution models for biodiversity conservation policy and management | PDF
Supervised in collaboration with KU Leuven and INBO
Date of defence: 09 June 2023
Hee Reen Shim
Data-Efficient Methods for Natural Language Processing: Applications in Healthcare | PDF
Supervised in collaboration with KU Leuven and Philips Eindhoven
Date of defence: 27 January 2023
Chetanya Puri
Building personalised machine learning models in health informatics with limited datasets | PDF
Supervised in collaboration with KU Leuven and Philips Eindhoven
Date of defence: 13 January 2023
Ahmed Youssef Ali Amer
Machine learning for human health : from activity and vital-sign monitoring to mortality prediction | PDF
Supervised in collaboration with KU Leuven
Date of defence: 12 May 2021