AI:X is an ambitious initiative at Aalborg University that aims to advance AI research and create real-world impact through interdisciplinary collaboration, and five labs will be initiated in 2025 with a total of 20 PhD stipends. The AI:EcoNet Lab is part of the AI:X initiative with four PhD stipends and is a collaboration between the Department of Chemistry and Bioscience, The Faculty of Engineering and Science, and the Department of Computer Science, The Technical Faculty of IT and Design. The four stipends are open for appointment from 01.08.2025 (or soon thereafter).

JOBBESKRIVELSE

Species interact in complex biological networks e.g. foodwebs, forming the foundation of natural ecosystems. Yet, we lack the tools to predict how these networks change in time and space. This is especially critical given the increased pressure from human activities that push species to extinction and potentially disrupts ecosystem functionality. Our interdisciplinary lab will develop novel Graph Representation Learning models to understand and predict interactions in dynamic ecological networks.
Our lab is looking for candidates for the following four stipends:

STIPEND 1: ENVIRONMENTAL AND BIOTIC DRIVERS OF ECOLOGICAL NETWORK STRUCTURE

A PhD stipend is available in network biology and biogeography. We seek a PhD candidate to investigate the role of environmental/macroecological factors and species traits in driving the structure of ecological networks. The candidate will use existing interaction databases and acquire networks from the literature, e.g. on seed-dispersal and pollination networks as well as food-webs. The candidate will use novel representation learning methods to study graph-structured ecological data. We are looking for a highly collaborative candidate to work closely with other members of the AI:EcoNet Lab.

REQUIREMENTS:

• Master’s degree in biology with a strong interest in data science
• Strong background in ecology and/or biogeography
• Experience with ecological networks, geospatial analysis and machine learning is advantageous
• Interest in data mining and database management
• Programming skills e.g. in R or Python
• Good analytical and communication skills. Proficiency in written and spoken English is mandatory

STIPEND 2: SPECIES INTERACTION NETWORKS IN A CHANGING WORLD

We seek a PhD candidate to develop methods for merging network ecology with species distribution modelling to investigate the impacts of environmental change on species interactions networks. Specifically, the project will explore how ecological networks change over time as species range shifts result in loss or gain of interactions. The candidate will also implement advanced graph-learning models to infer interactions within various ecological networks. We are looking for a highly collaborative candidate to work closely with other members of the AI:EcoNet Lab.

REQUIREMENTS:

• Master’s degree in biology with a strong interest in data science
• Strong background in ecology and/or biogeography
• Experience with species distribution models, ecological network analysis, and/or geospatial analysis is advantageous
• Programming skills e.g. in R or Python and machine learning experience
• Good analytical and communication skills. Proficiency in written and spoken English is mandatory

STIPEND 3: LEARNING THE STRUCTURE AND DYNAMICS OF COMPLEX NETWORKS

We seek a PhD candidate to develop novel representation learning methods on graphs for modeling temporal networks, with applications to ecological systems and beyond. The project will focus on advancing scalable approaches to capture how networks evolve over time. We are looking for a highly collaborative candidate to work closely with other members of the AI:EcoNet Lab.

REQUIREMENTS:

• Master’s degree in computer science, data science, mathematics, statistics, physics, software or relevant fields
• Strong background in machine learning, preferably experience in graph representation learning or time series analysis
• Programming skills (e.g., Python) and experience with deep learning frameworks (e.g. PyTorch)
• Interest in applications to ecological or biological networks
• Good analytical and communication skills. Proficiency in written and spoken English is mandatory

STIPEND 4: JOINT MODELING OF GRAPH-STRUCTURED DATA

This PhD project will develop novel methods for joint learning of network structure and node attributes in complex systems. The research will focus on learning unified representations that capture both interaction patterns and node features, with applications to ecological networks (e.g. species interaction networks) and other attributed network domains. We are looking for a highly collaborative candidate to work closely with other members of the AI:EcoNet Lab.

REQUIREMENTS:

• Master’s degree in computer science, data science, mathematics, statistics, physics, software or relevant fields
• Background in machine learning, preferably experience in graph representation learning or multimodal learning
• Programming skills (e.g., Python) and experience with deep learning frameworks (e.g. PyTorch)
• Interest in applications to ecological or biological networks
• Good analytical and communication skills. Proficiency in written and spoken English is mandatory

Please refer the Job description for details