Explore the vast range of titles available.

Citizen science databases are increasing in importance as sources of ecological information, but variability in effort across locations is inherent to such data. Spatially biased data—data not sampled uniformly across the study region—is expected. A further introduction of bias is variability in the level of sampling activity across locations. This motivates our work: with a spatial dataset of visited locations and sampling activity at those locations, we propose a model-based approach for assessing effort at these locations. Adjusting for potential spatial bias both in terms of sites visited and in terms of effort is crucial for developing reliable species distribution models (SDMs). Using data from eBird, a global citizen science database dedicated to avifauna, and illustrative regions in Pennsylvania and Germany, we model spatial dependence in both the observation locations and observed activity. We employ point process models to explain the observed locations in space, fit a geostatistical model to explain observation effort at locations, and explore the potential existence of preferential sampling, i.e., dependence between the two processes. Altogether, we offer a richer notion of sampling effort, combining information about location and activity. As SDMs are often used for their predictive capabilities, an important advantage of our approach is the ability to predict effort at unobserved locations and over regions. In this way, we can accommodate misalignment between point-referenced data and say, desired areal scale density. We briefly illustrate how our proposed methods can be applied to SDMs, with demonstrated improvement in prediction from models incorporating effort.

A frequent challenge encountered with ecological data is how to interpret, analyze, or model data having a high proportion of zeros. Much attention has been given to zero-inflated count data, whereas models for non-negative continuous data with an abundance of 0s are much fewer. We consider zero-inflated data on the unit interval and provide modeling to capture two types of 0s in the context of a Beta regression model. We model 0s due to missing by chance through left-censoring of a latent regression and 0s due to unsuitability using an independent Bernoulli specification. We extend the model by introducing spatial random effects. We specify models hierarchically, employing latent variables, and fit them within a Bayesian framework. Our motivating dataset consists of percent cover abundance of two plant families at a collection of sites in the Cape Floristic Region of South Africa. We find that environmental features enable learning about both types of 0s as well as positive percent cover. We also show that the spatial random effects model improves predictive performance. The proposed modeling enables ecologists to extract a better understanding of an organism’s absence due to unsuitability vs. missingness by chance, as well as abundance behavior when present. Supplementary materials accompanying this paper appear online.

In this dissertation, we present models that are developed to accommodate challenges and advance insights from modeling ecological abundance data. All the models presented in this work are fit within a Bayesian hierarchical framework. Species distribution models (SDMs) relate observed species abundance or occurrence data to geographically referenced environmental variables. In this dissertation, we focus mainly on multi-species or joint SDMs to incorporate the dependence between multiple species. We provide a dynamic mechanistic modeling framework that combines several biological and physiological processes that are known to operate within a species community. More specifically, we include the processes of local species growth as well as species movement within a geographic region. The mechanisms are represented as parameters to be estimated in our model. As an illustrative example, we first apply our model to the citizen science dataset eBird. We then provide an application to fisheries data from the Northeast Fisheries Science Center that develops a richer model for species redistribution that incorporates time-varying environmental covariates. As ecological data often exhibit a high incidence of zeros, we also develop models that address the issue of zero-inflation. While there is a wealth of literature on zero-inflated models for count data, we focus on data with continuous support. The familiar Tobit model accommodates positive continuous data with an excess of zeros, but does not allow for multiple interpretations of a zero as the also-familiar zero-inflated Poisson model does. We address this gap in the literature by first providing spatial and non-spatial zero-inflated Beta (ZIB) regression models for data that lie on the unit interval. We also provide a multivariate zero-inflated Tobit (MVT ZI-Tobit) regression model that can capture dependence between elements at a given observation index at multiple stages of the model. For both the ZIB and MVT ZI-Tobit, we present model comparison metrics for predictive performance that specifically target a model’s ability to capture zeros or dependence between observation elements. We apply our ZIB and MV ZI-Tobit models to percent cover of plant species in the Cape Floristic Region and total basal area of trees using Forest Inventory Analysis data, respectively.

Understanding how communities respond to environmental change is frustrated by the fact that both species interactions and movement affect biodiversity in unseen ways. To evaluate the contributions of species interactions on community growth, dynamic models that can capture nonlinear responses to the environment and the redistribution of species across a spatial range are required. We develop a time-series framework that models the effects of environment–species interactions as well as species–species interactions on population growth within a community. Novel aspects of our model include allowing for species redistribution across a spatial region, and addressing the issue of zero inflation. We adopt a hierarchical Bayesian approach, enabling probabilistic uncertainty quantification in the model parameters. To evaluate the impacts of interactions and movement on population growth, we apply our model using data from eBird, a global citizen science database. To do so, we also present a novel method of aggregating the spatially biased eBird data collected at point-level. Using an illustrative region in North Carolina, we model communities of six bird species. The results provide evidence of nonlinear responses to interactions with the environment and other species and demonstrate a pattern of strong intraspecific competition coupled with many weak interspecific species interactions. Supplementary materials accompanying this paper appear online.

This chapter addresses how the author navigated the transition from teaching assistant to instructors of record (IoR), a real trial by doing. It presents examples of challenges the author faced: the struggle to implement the author's ideal teaching style and a lack of student enthusiasm and engagement with the course material. The chapter provides several pieces of advice, with the hope of smoothing the transition for future IoRs. One of the largest challenges the author faced while teaching was how to gauge the appropriate speed and difficulty level for his students. Despite the class being predominantly female, the female students and the students of color were the most reluctant to volunteer or ask questions. The author attempted to synthesize what he learned from some experiences in order to create a final exam that allowed students the opportunity to demonstrate their statistical understanding within a space that allowed for positive feedback.

Bayesian Optimization (BO) is a powerful method for optimizing black-box functions by combining prior knowledge with ongoing function evaluations. BO constructs a probabilistic surrogate model of the objective function given the covariates, which is in turn used to inform the selection of future evaluation points through an acquisition function. For smooth continuous search spaces, Gaussian Processes (GPs) are commonly used as the surrogate model as they offer analytical access to posterior predictive distributions, thus facilitating the computation and optimization of acquisition functions. However, in complex scenarios involving optimization over categorical or mixed covariate spaces, GPs may not be ideal. This paper introduces Simulation Based Bayesian Optimization (SBBO) as a novel approach to optimizing acquisition functions that only requires sampling-based access to posterior predictive distributions. SBBO allows the use of surrogate probabilistic models tailored for combinatorial spaces with discrete variables. Any Bayesian model in which posterior inference is carried out through Markov chain Monte Carlo can be selected as the surrogate model in SBBO. We demonstrate empirically the effectiveness of SBBO using various choices of surrogate models in applications involving combinatorial optimization. choices of surrogate models.

A frequent challenge encountered with ecological data is how to interpret, analyze, or model data having a high proportion of zeros. Much attention has been given to zero-inflated count data, whereas models for non-negative continuous data with an abundance of 0s are lacking. We consider zero-inflated data on the unit interval and provide modeling to capture two types of 0s in the context of the Beta regression model. We model 0s due to missing by chance through left censoring of a latent regression, and 0s due to unsuitability using an independent Bernoulli specification to create a point mass at 0. We first develop the model as a spatial regression in environmental features and then extend to introduce spatial random effects. We specify models hierarchically, employing latent variables, fit them within a Bayesian framework, and present new model comparison tools. Our motivating dataset consists of percent cover abundance of two plant species at a collection of sites in the Cape Floristic Region of South Africa. We find that environmental features enable learning about the incidence of both types of 0s as well as the positive percent covers. We also show that the spatial random effects model improves predictive performance. The proposed modeling enables ecologists, using environmental regressors, to extract a better understanding of the presence/absence of species in terms of absence due to unsuitability vs. missingness by chance, as well as abundance when present.

Re: The recent school-board decision to close Garratt, Kilgour and Rideau Park elementary schools (Richmond News, March 5). Neighbourhood schools were created for the children's safety. School trustees are just putting their responsibilities on parents by shutting these schools down. What we need are more trustees like Mr. Chak Kwong Au who actually cares for the safety of the children.

Tools for rapid identification of novel and/or emerging viruses are urgently needed for clinical diagnosis of unexplained infections and pandemic preparedness. Here we developed and clinically validated a largely automated metagenomic next-generation sequencing (mNGS) assay for agnostic detection of respiratory viral pathogens from upper respiratory swab and bronchoalveolar lavage samples in <24 h. The mNGS assay achieved mean limits of detection of 543 copies/mL, viral load quantification with 100% linearity, and 93.6% sensitivity, 93.8% specificity, and 93.7% accuracy compared to gold-standard clinical multiplex RT-PCR testing. Performance increased to 97.9% overall predictive agreement after discrepancy testing and clinical adjudication, which was superior to that of RT-PCR (95.0% agreement). To enable discovery of novel, sequence-divergent human viruses with pandemic potential, de novo assembly and translated nucleotide algorithms were incorporated into the automated SURPI+ computational pipeline used by the mNGS assay for pathogen detection. Using in silico analysis, we showed that after removal of all human viral sequences from the reference database, 70 (100%) of 70 representative human viral pathogens could still be identified based on homology to related animal or plant viruses. Our assay, which was granted breakthrough device designation from the US Food and Drug Administration (FDA) in August of 2023, demonstrates the feasibility of routine mNGS testing in clinical and public health laboratories, thus facilitating a robust and rapid response to the next viral pandemic. Metagenomic next-generation sequencing has the potential to support diagnosis of unknown infections as it can identify all potential pathogens without requiring a prior suspected cause. Here, the authors develop and clinically validate a metagenomics-based assay for common and novel respiratory viral pathogens.

Alcohol consumption accounts for ~3 million annual deaths worldwide, but uncertainty persists about its relationships with many diseases. We investigated the associations of alcohol consumption with 207 diseases in the 12-year China Kadoorie Biobank of >512,000 adults (41% men), including 168,050 genotyped for ALDH2 - rs671 and ADH1B - rs1229984 , with >1.1 million ICD-10 coded hospitalized events. At baseline, 33% of men drank alcohol regularly. Among men, alcohol intake was positively associated with 61 diseases, including 33 not defined by the World Health Organization as alcohol-related, such as cataract ( n  = 2,028; hazard ratio 1.21; 95% confidence interval 1.09–1.33, per 280 g per week) and gout ( n  = 402; 1.57, 1.33–1.86). Genotype-predicted mean alcohol intake was positively associated with established ( n  = 28,564; 1.14, 1.09–1.20) and new alcohol-associated ( n  = 16,138; 1.06, 1.01–1.12) diseases, and with specific diseases such as liver cirrhosis ( n  = 499; 2.30, 1.58–3.35), stroke ( n  = 12,176; 1.38, 1.27–1.49) and gout ( n  = 338; 2.33, 1.49–3.62), but not ischemic heart disease ( n  = 8,408; 1.04, 0.94–1.14). Among women, 2% drank alcohol resulting in low power to assess associations of self-reported alcohol intake with disease risks, but genetic findings in women suggested the excess male risks were not due to pleiotropic genotypic effects. Among Chinese men, alcohol consumption increased multiple disease risks, highlighting the need to strengthen preventive measures to reduce alcohol intake. Observational analyses from the China Kadoorie Biobank found that alcohol consumption was associated with higher risks of 61 diseases in Chinese men, with most of these associations confirmed by genetic analyses.