Artificial Intelligence for Science

by Prof. Saso Dzeroski (Jozef Stefan Institute)

Wednesday 5 Nov 2025, 14:00 → 15:00 Europe/Zurich

CERN

Artificial intelligence is already transforming science, with its future impact expected to be even greater. Realizing this potential requires addressing key scientific challenges, such as ensuring explainability (of models and their predictions), learning effectively from limited data, and integrating data with prior domain knowledge. It also requires the provision of support for open and reproducible science through formalizing and sharing scientific knowledge.

I will present an overview of my research on the development of AI methods suitable for use in science. These include methods for explainable machine learning — including multi-target prediction and relational learning — that deliver accurate yet interpretable models suitable for complex scientific domains. These methods have been applied in environmental science, life science and materials science.

Learning from limited data is critical in science. I will discuss two complementary approaches: semi-supervised learning, which leverages unlabeled data directly, together with labeled data, and foundation models, which use representations learned from vast unlabeled data to support downstream tasks with minimal supervision, i.e., limited amounts of labeled data. Both paradigms expand AI’s reach into data-scarce scientific problems.

I will then present our work on automated scientific modeling, where we learn interpretable models of dynamical systems — such as process-based models and differential equations — from time series data and domain knowledge. Finally, I will highlight the role of ontologies and semantic technologies in experimental computer science, including machine learning and optimization. In these areas, we have developed ontologies for the representation and annotation of both data and other artefacts produced by science, such as algorithms, models, and results of experiments.

Sašo Džeroski is Head of the Department of knowledge technologies at the Jozef Stefan Institute and full professor at the Jozef Stefan International Postgraduate School, both in Ljubljana, Slovenia. He is a fellow of EurAI, the European Association of AI, in recognition of his "Pioneering Work in the field of AI”. He is a member of the Macedonian Academy of Sciences and Arts and a member of Academia Europea. He is past president and current vice-president of SLAIS, the Slovenian Artificial Intelligence Society.

His research interests focus on explainable machine learning, computational scientific discovery, and semantic technologies, all in the context of artificial intelligence for science. His group has developed machine learning methods that learn explainable models from complex data in the presence of domain knowledge: These include methods for multi-target prediction, semi-supervised and relational learning, and learning from data streams, as well as automated modelling of dynamical systems.

Professor Džeroski has lead (as coordinator) many national and international (EU-funded ) projects and has participated in many more. He is also the technical coordinator of the Slovenian Artificial Intelligence Factory. The work of professor Džeroski has been extensively published and is highly cited: With more than 27000 citations and an h-index of 75 (in the GoogleScholar database), prof. Džeroski is the most frequently cited computer scientist in Slovenia (according to the 2025 ranking by Research.com).