Search for: All records

ABSTRACT AimHalting widespread biodiversity loss will require detailed information on species' trends and the habitat conditions correlated with population declines. However, constraints on conventional monitoring programs and commonplace approaches for trend estimation can make it difficult to obtain such information across species' ranges. Here, we demonstrate how recent developments in machine learning and model interpretation, combined with data sources derived from participatory science, enable landscape‐scale inferences on the habitat correlates of population trends across broad spatial extents. LocationWorldwide, with a case study in the western United States. MethodsWe used interpretable machine learning to understand the relationships between land cover and spatially explicit bird population trends. Using a case study with three passerine birds in the western U.S. and spatially explicit trends derived from eBird data, we explore the potential impacts of simulated land cover modification while evaluating potential co‐benefits among species. ResultsOur analysis revealed complex, non‐linear relationships between land cover variables and species' population trends as well as substantial interspecific variation in those relationships. Areas with the most positive impacts from a simulated land cover modification overlapped for two species, but these changes had little effect on the third species. Main ConclusionsThis framework can help conservation practitioners identify important relationships between species trends and habitat while also highlighting areas where potential modifications to the landscape could bring the biggest benefits. The analysis is transferable to hundreds of species worldwide with spatially explicit trend estimates, allowing inference across multiple species at scales that are tractable for management to combat species declines. 

Abstract Citizen and community science datasets are typically collected using flexible protocols. These protocols enable large volumes of data to be collected globally every year; however, the consequence is that these protocols typically lack the structure necessary to maintain consistent sampling across years. This can result in complex and pronounced interannual changes in the observation process, which can complicate the estimation of population trends because population changes over time are confounded with changes in the observation process.Here we describe a novel modelling approach designed to estimate spatially explicit species population trends while controlling for the interannual confounding common in citizen science data. The approach is based on Double machine learning, a statistical framework that uses machine learning (ML) methods to estimate population change and the propensity scores used to adjust for confounding discovered in the data. ML makes it possible to use large sets of features to control for confounding and to model spatial heterogeneity in trends. Additionally, we present a simulation method to identify and adjust for residual confounding missed by the propensity scores.To illustrate the approach, we estimated species trends using data from the citizen science project eBird. We used a simulation study to assess the ability of the method to estimate spatially varying trends when faced with realistic confounding and temporal correlation. Results demonstrated the ability to distinguish between spatially constant and spatially varying trends. There were low error rates on the estimated direction of population change (increasing/decreasing) at each location and high correlations on the estimated magnitude of population change.The ability to estimate spatially explicit trends while accounting for confounding inherent in citizen science data has the potential to fill important information gaps, helping to estimate population trends for species and/or regions lacking rigorous monitoring data.