NORMAN

21 October 2024 – Day 1

Werner Brack, UFZ
Introduction AI Workshop (0,8 MB)

Valeria Dulio, INERIS, France
The Norman Network (1,3 MB)

Leo Posthuma, RIVM, The Netherlands
A small thought on combining expertise – a big step for Component-Based biodiversity impact assessments of chemical pollution? (2,2 MB)

Erik Kristiansson, Chalmers Univ. of Technology, Sweden 
The use of AI to predict chemical toxicity (1,8 MB)

Jana Schor, UFZ, Germany
AI-driven Chemical-effect association with deepFPlearn, including enhanced credibility measures, graph neural networks, classification, and regression (1,7 MB)

Jan Siegismund, German environment agency, Germany
NTS use case for UBA application lab for AI and Big Data (1,3 MB)

Anneli Kruve, Stockholm University, Sweden
ML based methods to support suspect and non-target data (3 MB)

Teofana Chonova, Eawag, Switzerland
Data Science approaches to uncover contamination sources from Rhine Monitoring Data (2,2 MB)

Nadin Ulrich, UFZ, Germany
Deep learning models to predict physico-chemical properties for risk assessment of chemicals (0,3 MB)

Saer Samanipour, University of Amsterdam, The Netherlands
Probabilistic approaches to mapping the exposome chemical space (3,8 MB)

Nikiforos Alygizakis - Environmental Institute, Slovakia
First results from ML based toxicity prediction trial in NORMAN (1,9 MB)

Ilhan Mutlu, UFZ, Germany
Automated Curation of Spatial Data in Environmental Monitoring: Enhancing the NORMAN Chemical Occurrence Database for Big Data Analytics and AI Applications (1,7 MB)

Reza Aalizadeh, NKUA, Greece and Peter von der Ohe, UBA, Germany
Using innovative ML techniques to predict the risk of chemicals for multiple species (4,3 MB)