Ecology informed machine learning
As biodiversity declines and anthropogenic pressure increases, there is a crucial need for accurate ecosystem models that can capture the dynamics of real ecosystems in order to predict and mitigate collapses. Yet it remains a daunting task to obtain an agreement between current ecosystem models and real world ecosystems. In this project we aim at bridging machine learning techniques and mechanistic models in order to extrapolate beyond data. By embedding prior scientific knowledge in the structure of mechanistic models, this approach should generalise better, be more interpretable and require less data than current techniques.