Explore the vast range of titles available.

1. Collisions of large soaring raptors with wind turbines and other infrastructures represent a growing conservation concern. We describe a way to leverage knowledge about raptor soaring behaviour to forecast the probability that raptors fly in the rotor-swept zone. Soaring raptors are theoretically expected to select energy sources (uplift) optimally, making their flight height dependent on uplift conditions. This approach can be used to forecast collision hazard when planning or operating wind farms. Empirical investigations of the factors influencing flight height have, however, so far been hindered by observation error. 2. We propose a two-pronged approach. First, we fitted state-space models to z-axis GPS tracking data to filter heavy-tailed observation error and estimate the relationship between vertical movement parameters and weather variables describing the energy landscape (thermal and orographic uplift potential). Second, we fitted a mechanistic model of flight height above ground based on aerodynamics and resource selection theories. The approach was replicated for five GPS-tracked Andean condors Vultur gryphus, eight griffon vultures Gyps fulvus, and six golden eagles Aquila chrysaetos. 3. In all individuals, movement parameters correlated with thermal uplift potential in the expected direction. In all species, collision hazard was lowest for high thermal uplift potential values. Species specificities in the presence of a peak in collision hazard for medium values of thermal uplift potential could be explained by differences in wing loading and aspect ratio. 4. Synthesis and applications. Our fitted models convert weather data (thermal uplift potential) into a prediction of collision hazard (probability to fly in the rotor-swept zone), making it possible to prioritize different wind development projects with respect to the relative hazard they would pose to raptors. However, our model should be combined with post-construction monitoring to document, and eventually account for turbine avoidance behaviours in collision rate predictions.

The extent to which populations in nature are regulated by density-dependent processes is unresolved. While experiments increasingly find evidence of strong density dependence, unmanipulated population time series yield much more ambiguous evidence of regulation, especially when accounting for effects of observation error. Here, we reexamine the evidence for density dependence in time series of population sizes in nature, by conducting an aggregate analysis of the populations in the Global Population Dynamics Database (GPDD). First, following the conventional approach, we fit a density-dependent and a density-independent variant of the Gompertz state-space model to each time series. Then, we conduct an aggregate analysis of the entire database by considering two random-effects density-dependent models that leverage information across data sets. When individual time series are tested independently, we find very little evidence for density dependence. However, in the aggregate, we find very strong evidence for density dependence, even though, paradoxically, estimated strengths of density dependence for individual time series tend to be weaker than when each individual time series is analyzed independently. Furthermore, a hierarchical model that accounts for taxonomic variation in the strength of density dependence reveals that density dependence is consistently stronger in insects and fish than in birds and mammals. Our findings resolve apparent inconsistencies between observational and experimental studies of density dependence by revealing that the observational record does indeed contain strong support for the hypothesis that density dependence is widespread in nature.

1. Altitude measurements from wildlife tracking devices, combined with elevation data, are commonly used to estimate the flight altitude of volant animals. However, these data often include measurement error. Understanding this error may improve estimation of flight altitude and benefit applied ecology. 2. There are a number of different approaches that have been used to address this measurement error. These include filtering based on GPS data, filtering based on behaviour of the study species, and use of state-space models to correct measurement error. The effectiveness of these approaches is highly variable. 3. Recent studies have based inference of flight altitude on misunderstandings about avian natural history and technical or analytical tools. In this Commentary, we discuss these misunderstandings and suggest alternative strategies both to resolve some of these issues and to improve estimation of flight altitude. These strategies also can be applied to other measures derived from telemetry data. 4. Synthesis and applications. Our Commentary is intended to clarify and improve upon some of the assumptions made when estimating flight altitude and, more broadly, when using GPS telemetry data. We also suggest best practices for identifying flight behaviour, addressing GPS error, and using flight altitudes to estimate collision risk with anthropogenic structures. Addressing the issues we describe would help improve estimates of flight altitude and advance understanding of the treatment of error in wildlife telemetry studies.

Various approaches have been developed to analyze univariate semicontinuous time series data in the literature, whereas analysis of multivariate semicontinuous data has recently become an area of active research. However, there is apparently little, if any, literature on combining these two aspects to model multivariate semicontinuous time series data with covariates. In this paper, we introduce a family of multivariate state space models for semicontinuous time series data by incorporating serially correlated multivariate distribution-free random effects into Tweedie compound Poisson regression model. This model can flexibly accommodate unstructured covariance structures, skewness and zero-inflation. Unlike two-part modelling models, our model maintains natural temporal and multivariate structures of the data and characterizes the effects of covariates on the overall mean of the multivariate semicontinuous time series directly. An optimal estimation of our model has been developed using the orthodox best linear unbiased predictors of the serially correlated multivariate random effects. The usefulness of our approach is illustrated through the analysis of monthly national financing data in China and simulation studies.

Near-term ecological forecasts provide resource managers advance notice of changes in ecosystem services, such as fisheries stocks, timber yields, or water quality. Importantly, ecological forecasts can identify where there is uncertainty in the forecasting system, which is necessary to improve forecast skill and guide interpretation of forecast results. Uncertainty partitioning identifies the relative contributions to total forecast variance introduced by different sources, including specification of the model structure, errors in driver data, and estimation of current states (initial conditions). Uncertainty partitioning could be particularly useful in improving forecasts of highly variable cyanobacterial densities, which are difficult to predict and present a persistent challenge for lake managers. As cyanobacteria can produce toxic and unsightly surface scums, advance warning when cyanobacterial densities are increasing could help managers mitigate water quality issues. Here, we fit 13 Bayesian state-space models to evaluate different hypotheses about cyanobacterial densities in a low nutrient lake that experiences sporadic surface scums of the toxin-producing cyanobacterium, Gloeotrichia echinulata. We used data from several summers of weekly cyanobacteria samples to identify dominant sources of uncertainty for near-term (1- to 4-week) forecasts of G. echinulata densities. Water temperature was an important predictor of cyanobacterial densities during model fitting and at the 4-week forecast horizon. However, no physical covariates improved model performance over a simple model including the previous week's densities in 1-week-ahead forecasts. Even the best fit models exhibited large variance in forecasted cyanobacterial densities and did not capture rare peak occurrences, indicating that significant explanatory variables when fitting models to historical data are not always effective for forecasting. Uncertainty partitioning revealed that model process specification and initial conditions dominated forecast uncertainty. These findings indicate that long-term studies of different cyanobacterial life stages and movement in the water column as well as measurements of drivers relevant to different life stages could improve model process representation of cyanobacteria abundance. In addition, improved observation protocols could better define initial conditions and reduce spatial misalignment of environmental data and cyanobacteria observations. Our results emphasize the importance of ecological forecasting principles and uncertainty partitioning to refine and understand predictive capacity across ecosystems.

Probably because of their interpretability and transparent nature, synthetic controls have become widely applied in empirical research in economics and the social sciences. This article aims to provide practical guidance to researchers employing synthetic control methods. The article starts with an overview and an introduction to synthetic control estimation. The main sections discuss the advantages of the synthetic control framework as a research design, and describe the settings where synthetic controls provide reliable estimates and those where they may fail. The article closes with a discussion of recent extensions, related methods, and avenues for future research.

The event study model is a powerful econometric tool used for the purpose of estimating dynamic treatment effects. One of its most appealing features is that it provides a built-in graphical summary of results, which can reveal rich patterns of behavior. Another value of the picture is the estimated pre-event pseudo-\"effects\", which provide a type of placebo test. In this essay I aim to provide a framework for a shared understanding of these models. There are several (sometimes subtle) decisions and choices faced by users of these models, and I offer guidance for these decisions.

In this article, we aim to improve the prediction from experts’ aggregation by using the underlying properties of the models that provide the experts involved in the aggregation procedure. We restrict ourselves to the case where experts perform their predictions by fitting state-space models to the data using Kalman recursions. Using exponential weights, we construct different Kalman recursions Aggregated Online (KAO) algorithms that compete with the best expert or the best convex combination of experts in a more or less adaptive way. When the experts are Kalman recursions, we improve the existing results on experts’ aggregation literature, taking advantage of the second-order properties of the Kalman recursions. We apply our approach to Kalman recursions and extend it to the general adversarial expert setting by state-space modeling the experts’ errors. We apply these new algorithms to a real-data set of electricity consumption and show how they can improve forecast performances compared to other exponentially weighted average procedures.

Structured state space models (SSM) have recently emerged as a new class of deep learning models, particularly well‐suited for processing long sequences. Their constant memory footprint, in contrast to the linearly scaling memory demands of transformers, makes them attractive candidates for deployment on resource‐constrained edge‐computing devices. While recent works have explored the effect of quantization‐aware training (QAT) on SSMs, they typically do not address its implications for specialized edge hardware, for example, analog in‐memory computing (AIMC) chips. In this work, it is demonstrated that QAT can significantly reduce the complexity of SSMs by up to two orders of magnitude across various performance metrics. The relation between model size and numerical precision is analyzed, and it is shown that QAT enhances robustness to analog noise and enables structural pruning. Finally, these techniques are integrated to deploy SSMs on a memristive AIMC substrate and highlight the resulting benefits in terms of computational efficiency. Quantization‐aware training creates resource‐efficient structured state space sequential S4(D) models for ultra‐long sequence processing in edge AI hardware. Including quantization during training leads to efficiency gains compared to pure post‐training quantization. Motivated by increased noise tolerance of quantized models, deployment on analog in‐memory computing hardware is discussed to overcome the von‐Neumann bottleneck in conventional computers.

We prove that local projections (LPs) and Vector Autoregressions (VARs) estimate the same impulse responses. This nonparametric result only requires unrestricted lag structures. We discuss several implications: (i) LP and VAR estimators are not conceptually separate procedures; instead, they are simply two dimension reduction techniques with common estimand but different finite-sample properties. (ii) VAR-based structural identification—including short-run, long-run, or sign restrictions—can equivalently be performed using LPs, and vice versa. (iii) Structural estimation with an instrument (proxy) can be carried out by ordering the instrument first in a recursive VAR, even under noninvertibility. (iv) Linear VARs are as robust to nonlinearities as linear LPs.