Transfer learning for forecasting short environmental time series using process- guided neural networks (B02)

• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing ; Ecology and Biodiversity of Plants and Ecosystems
• Term: since 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 499552394

We want to expand approaches for process models in neural networks by augmenting neural networks with existing biophysical process knowledge and using explainable AI to improve process models. We will specifically consider augmentation data by simulations from a process model, and direct uses of process models by regularization, post-processing of process-model output with a neural network, or by embedding the process model into a series of neural networks to combine process-model fitting with prediction optimization.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1597: Small Data
• Applicant Institution: Albert-Ludwigs-Universität Freiburg
• Project Heads: Professor Dr. Joschka Bödecker; Professor Dr. Carsten Dormann