Local factors such as seasonal temperature, the year-dependent water and vegetation index, and data on animal density can be used to predict regional outbreaks of avian flu in Europe. This is the finding of a research team led by epidemiologist, mathematician, and statistician Prof. Dr. Joacim Rocklöv. The researchers at Heidelberg University developed a machine learning model that can predict highly pathogenic avian influenza outbreak patterns in Europe with great accuracy using various indicators. The modeling approach and targeted data collection could therefore contribute to proactive prevention measures.
The highly pathogenic avian influenza virus infection – commonly known as bird flu – primarily affects birds. Mammals, however, are also increasingly infected. This, the researchers report, increases the probability that the virus will cross over to humans. To better predict bird flu outbreaks and put early prevention measures into place, Prof. Rocklöv’s team at the Interdisciplinary Center for Scientific Computing and the Heidelberg Institute for Global Health developed a model that combines various indicators for a possible outbreak and uses machine learning methods for modeling.
The model was trained using data of bird flu outbreaks in Europe documented between 2006 and 2021. As potential indicators of an imminent event, the Heidelberg researchers identified local factors such as temperature and precipitation conditions, the wild bird species, poultry farm density, vegetation composition, and water levels. By combining these complex interdependent seasonal and regional variables, the researchers were able to model outbreak patterns with an accuracy of up to 94 percent.
“Combining our modeling approach and targeted data collection can help us to map more precisely the high-risk areas and seasons when outbreaks of bird flu are more likely,” stresses Joacim Rocklöv, an Alexander von Humboldt Professor conducting research on the effects of climate and environmental change on public health in a number of projects at the university and Heidelberg University Hospital. According to Prof. Rocklöv, the research results could be used to design regional surveillance programs throughout Europe and improve early detection.
The research work was funded by the Alexander von Humboldt Foundation within the Horizon Europe Program of the European Union. The results were published in the journal “Scientific Reports.”
Source:
Journal reference:
Opata, M. R., et al. (2025). Predictiveness and drivers of highly pathogenic avian influenza outbreaks in Europe. Scientific Reports. doi.org/10.1038/s41598-025-04624-x