Ensemble predictions are essential for accurate bird migration forecasts for conservation and flight safety.
Accurate predictions of the abundance of migrating birds are important to avoid aerial conflicts of birds, for example, with aviation or wind power installations. Here we develop a predictive model, using bird migration intensity extracted from operational weather data. We compare baseline phenological models to models incorporating both local and remote weather conditions using an ensemble approach. Single models are compared to ensemble models (average prediction of top 10 models). The models were evaluated by omitting single years from our 10-year dataset. In general, we find that wind conditions, in addition to seasonal and diurnal dynamics, are key for accurate predictions. The spring and fall migratory seasons differ, both with respect to the selected environmental variables and the contribution of the environmental model compared to the phenological model. In fall, the accumulation of migrants due to strong headwinds is an important predictor of migration. Because of the lower daily variation in migration intensity in spring, the phenological model performs better compared to fall. In fall, weather conditions contribute more to accurate predictions of migration intensity than in spring. 5. Overall, the ensemble approach produces more accurate predictions outperforming specific environmental models. We therefore recommend that ensemble models be used in operational settings such as flight planning to reduce bird aircraft collisions during intense bird migration.