Ensemble predictions are essential for accurate bird migration forecasts for conservation and flight safety

Abstract

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. 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.

Geographic barriers and season shape the nightly timing of avian migration

“…However, for many ecological and societal questions, these macroecological patterns are key (Kelly & Horton, 2016), for example, in the setup of mitigation measures for aerial conflicts. Quantifying and understanding when biomass flows are generally expected to be most intense can assist in the development of curtailment regimes for wind turbine operations and the planning of flight schedules to avoid bird‐aircraft collisions (Kranstauber et al, 2022; Van Gasteren et al, 2019) or lights out procedures to reduce the effects of light pollution. When local and near real‐time information is lacking, long‐term, seasonal and regional patterns could be a first step in focusing mitigation measures to relevant and sensitive periods.…”

“…However, for many ecological and societal questions, these macroecological patterns are key (Kelly & Horton, 2016), for example, in the setup of mitigation measures for aerial conflicts. Quantifying and understanding when biomass flows are generally expected to be most intense can assist in the development of curtailment regimes for wind turbine operations and the planning of flight schedules to avoid bird-aircraft collisions (Kranstauber et al, 2022;Van Gasteren et al, 2019)…”

“…Seasonal trends are generally driven by the birds' annual cycle (Gwinner & Helm, 2003), modulated by environmental conditions such as weather (e.g. Erni et al, 2002; Haest et al, 2020; Kranstauber et al, 2022) and resource availability as well as the internal state of migrants (Deppe et al, 2015).…”

Learning to predict spatiotemporal movement dynamics from weather radar networks

“…We compared the predictive performance of our modelling framework to three baseline models, ranging from a simple historical average (HA), to a generalised additive model (GAM) similar to Kranstauber et al (2022), capturing daily and seasonal trends based on temporal features alone, to a more complex species distribution model based on gradient‐boosted regression trees (GBT) similar to van Doren and Horton (2018). For GBT, we performed a cross‐validated grid search to determine the best hyper‐parameter settings (see Supporting Information B).…”

Automatic detection of migrating soaring bird flocks using weather radars by deep learning

“…Consequently, weather radars around the world are exploited to better understand different broad scale behaviours and movement of aerial organisms in detail, including quantification of biomass fluxes (Dokter et al, 2018; Farnsworth et al, 2016; Hu et al, 2016; Nilsson et al, 2019; Van Doren & Horton, 2018) and mapping of stopover sites along migration flyways (Buler & Dawson, 2014; Cohen et al, 2021; Schekler et al, 2022). In addition, extracting biological data from weather radars allows us to manage human‐wildlife conflicts such as flight safety (Ginati et al, 2010; Kranstauber et al, 2022; Van Gasteren et al, 2018), crop damage (Markkula et al, 2008), risks due to collision with wind energy facilities (Cohen et al, 2022), and the dispersal of pathogens (Acosta et al, 2021) and pollinators (Wotton et al, 2019). These efforts minimize financial consequences, provide economic incentives, decrease risks to human lives and conserve aerial animals (Bauer et al, 2017).…”