Towards detailed and interpretable hybrid modeling of continental-scale bird migration

TL;DR

This paper enhances a hybrid bird migration model by increasing spatial resolution and interpretability, enabling detailed ecological insights and better predictions across the U.S. radar network.

Contribution

It introduces two major modifications to FluxRGNN, improving spatial detail and interpretability of bird migration predictions at continental scale.

Findings

Enhanced model predicts migration patterns with higher spatial resolution.

Model effectively extrapolates to unobserved locations.

Improved interpretability of migration decision processes.

Abstract

Hybrid modeling aims to augment traditional theory-driven models with machine learning components that learn unknown parameters, sub-models or correction terms from data. In this work, we build on FluxRGNN, a recently developed hybrid model of continental-scale bird migration, which combines a movement model inspired by fluid dynamics with recurrent neural networks that capture the complex decision-making processes of birds. While FluxRGNN has been shown to successfully predict key migration patterns, its spatial resolution is constrained by the typically sparse observations obtained from weather radars. Additionally, its trainable components lack explicit incentives to adequately predict take-off and landing events. Both aspects limit our ability to interpret model results ecologically. To address this, we propose two major modifications that allow for more detailed predictions on any desired tessellation while providing control over the interpretability of model components. In experiments on the U.S. weather radar network, the enhanced model effectively leverages the underlying movement model, resulting in strong extrapolation capabilities to unobserved locations.