Modeling spatiotemporal abundance of mobile wildlife in highly variable environments using boosted GAMLSS hurdle models

Distributional regression modeling via generalized additive models for location, scale, and shape: An overview through a data set from learning analytics

The advent of technological developments is allowing to gather large amounts of data in several research fields. Learning analytics (LA)/educational data mining has access to big observational unstructured data captured from educational settings and relies mostly on unsupervised machine learning (ML) algorithms to make sense of such type of data. Generalized additive models for location, scale, and shape (GAMLSS) are a supervised statistical learning framework that allows modeling all the parameters of the distribution of the response variable with respect to the explanatory variables. This article overviews the power and flexibility of GAMLSS in relation to some ML techniques. Also, GAMLSS' capability to be tailored toward causality via causal regularization is briefly commented. This overview is illustrated via a data set from the field of LA. This article is categorized under:Application Areas > Education and LearningAlgorithmic Development > StatisticsTechnologies > Machine Learning.

Black Scoter habitat use along the southeastern coast of the United States

While the Atlantic Coast of the United States and Canada is a major wintering area for sea ducks, knowledge about their wintering habitat use is relatively limited. Black Scoters have a broad wintering distribution and are the only open water species of sea duck that is abundant along the southeastern coast of the United States. Our study identified variables that affected Black Scoter (Melanitta americana) distribution and abundance in the Atlantic Ocean along the southeastern coast of the United States. We used aerial survey data from 2009 to 2012 provided by the United States Fish and Wildlife Service to identify variables that influenced Black Scoter distribution. We used indicator variable selection to evaluate relationships between Black Scoter habitat use and a variety of broad- and fine-scale oceanographic and weather variables. Average time between waves, ocean floor slope, and the interaction of bathymetry and distance to shore had the strongest association with southeastern Black Scoter distribution.

A Review of Spatiotemporal Models for Count Data in R Packages. A Case Study of COVID-19 Data

Spatiotemporal models for count data are required in a wide range of scientific fields, and they have become particularly crucial today because of their ability to analyze COVID-19-related data. The main objective of this paper is to present a review describing the most important approaches, and we monitor their performance under the same dataset. For this review, we focus on the three R-packages that can be used for this purpose, and the different models assessed are representative of the two most widespread methodologies used to analyze spatiotemporal count data: the classical approach and the Bayesian point of view. A COVID-19-related case study is analyzed as an illustration of these different methodologies. Because of the current urgent need for monitoring and predicting data in the COVID-19 pandemic, this case study is, in itself, of particular importance and can be considered the secondary objective of this work. Satisfactory and promising results have been obtained in this second goal. With respect to the main objective, it has been seen that, although the three models provide similar results in our case study, their different properties and flexibility allow us to choose the model depending on the application at hand.

Ecological correlates of blue whale movement behavior and its predictability in the California Current Ecosystem during the summer-fall feeding season

BACKGROUND

Species distribution models have shown that blue whales (Balaenoptera musculus) occur seasonally in high densities in the most biologically productive regions of the California Current Ecosystem (CCE). Satellite telemetry studies have additionally shown that blue whales in the CCE regularly switch between behavioral states consistent with area-restricted searching (ARS) and transiting, indicative of foraging in and moving among prey patches, respectively. However, the relationship between the environmental correlates that serve as a proxy of prey relative to blue whale movement behavior has not been quantitatively assessed.

METHODS

We investigated the association between blue whale behavioral state and environmental predictors in the coastal environments of the CCE using a long-term satellite tracking data set (72 tagged whales; summer-fall months 1998-2008), and predicted the likelihood of ARS behavior at tracked locations using nonparametric multiplicative regression models. The models were built using data from years of cool, productive conditions and validated against years of warm, low-productivity conditions.

RESULTS

The best model contained four predictors: chlorophyll-a, sea surface temperature, and seafloor aspect and depth. This model estimated highest ARS likelihood (> 0.8) in areas with high chlorophyll-a levels (> 0.65 mg/m³), intermediate sea surface temperatures (11.6-17.5 °C), and shallow depths (< 850 m). Overall, the model correctly predicted behavioral state throughout the coastal environments of the CCE, while the validation indicated an ecosystem-wide reduction in ARS likelihood during warm years, especially in the southern portion. For comparison, a spatial coordinates model (longitude × latitude) performed slightly better than the environmental model during warm years, providing further evidence that blue whales exhibit strong foraging site fidelity, even when conditions are not conducive to successful foraging.

CONCLUSIONS

We showed that blue whale behavioral state in the CCE was predictable from environmental correlates and that ARS behavior was most prevalent in regions of known high whale density, likely reflecting where large prey aggregations consistently develop in summer-fall. Our models of whale movement behavior enhanced our understanding of species distribution by further indicating where foraging was more likely, which could be of value in the identification of key regions of importance for endangered species in management considerations. The models also provided evidence that decadal-scale environmental fluctuations can drive shifts in the distribution and foraging success of this blue whale population.