Geology topics

Jun Zhu

Publications and source records attributed to Jun Zhu.

10 recordsLinked to original sources

USGS2025

Animal trajectory imputation and uncertainty quantification via deep learning

Imputing missing data in animal trajectories is crucial for understanding animal movements during unobserved periods. However, the traditional methods, such as linear interpolation and the continuous-time correlated random walk model, are often inadequate to capture the complexity of animal movements. Here, we develop a deep learning approach to animal trajectory imputation by a conditional diffusion model. Unlike the traditional methods, our deep learning method uses observed data and external covariates to impute missing positions along an animal trajectory, capturing periodic patterns and the influence of covariates, which leads to more accurate imputations. In a case study of imputing deer trajectories, our method not only provides more accurate deterministic imputations than existing approaches but also achieves uncertainty quantification through probabilistic imputation.

Environmetrics↗

USGS2025

Learning complex spatial dynamics of wildlife diseases with machine learning-guided partial differential equations

Emerging wildlife pathogens often display geographic variability due to landscape heterogeneity. Modeling approaches capable of learning complex, non-linear spatial dynamics of diseases are needed to rigorously assess and mitigate the effects of pathogens on wildlife health and biodiversity. We propose a novel machine learning (ML)-guided approach that leverages prior physical knowledge of ecological systems, using partial differential equations. We present our approach, taking advantage of the universal function approximation property of neural networks for flexible representation of the underlying dynamics of the geographic spread and growth of wildlife diseases. We demonstrate the benefits of our approach by comparing its forecasting power with commonly used methods and highlighting the obtained insights on disease dynamics. Additionally, we show the theoretical guarantees for the approximation error of our model. We illustrate the implementation of our ML-guided approach using data from white-nose syndrome (WNS) outbreaks in bat populations across the US. WNS is an infectious fungal disease responsible for significant declines in bat populations. Our results on WNS are useful for disease surveillance and bat conservation efforts. Our methods can be broadly used to assess the effects of environmental and anthropogenic drivers impacting wildlife health and biodiversity.

Environmental Data Science↗

USGS2025

Spatiotemporal causal inference with mechanistic ecological models: Evaluating targeted culling on chronic wasting disease dynamics in cervids

Spatiotemporal causal inference methods are needed to detect the effect of interventions on indirectly measured epidemiological outcomes that go beyond studying spatiotemporal correlations. Chronic wasting disease (CWD) causes neurological degeneration and eventual death to white-tailed deer ( Odocoileus virginianus ) in Wisconsin. Targeted culling involves removing deer after traditional hunting seasons in areas with high CWD prevalence. The evaluation of the causal effects of targeted culling in the spread and growth of CWD is an important unresolved research and CWD management question that can guide surveillance efforts. Reaction–diffusion partial differential equations (PDEs) can be used to mechanistically model the underlying spatiotemporal dynamics of wildlife diseases, like CWD, allowing researchers to make inference about unobserved epidemiological quantities. These models indirectly regress spatiotemporal covariates on diffusion and growth rates parameterizing such PDEs, obtaining associational conclusions. In this work we develop an innovative method to obtain causal estimators for the effect of targeted culling interventions on CWD epidemiological processes using an inverse-probability-of-treatment-weighted technique by means of marginal structural models embedded in the PDE fitting process. Additionally we establish a novel scheme for sensitivity analysis under unmeasured confounder for testing the hypothesis of a significant causal effect in the indirectly measured epidemiological outcomes. Our methods can be broadly used to study the impact of spatiotemporal interventions and treatment exposures in the epidemiological evolution of infectious diseases that can help to inform future efforts to mitigate public health implications and wildlife disease burden.

Wisconsin↗

USGS2024

Spatio-temporal ecological models via physics-informed neural networks for studying chronic wasting disease

To mitigate the negative effects of emerging wildlife diseases in biodiversity and public health it is critical to accurately forecast pathogen dissemination while incorporating relevant spatio-temporal covariates. Forecasting spatio-temporal processes can often be improved by incorporating scientific knowledge about the dynamics of the process using physical models. Ecological diffusion equations are often used to model epidemiological processes of wildlife diseases where environmental factors play a role in disease spread. Physics-informed neural networks (PINN) are deep learning algorithms that constrain neural network predictions based on physical laws and therefore are powerful forecasting models useful even in cases of limited and imperfect training data. In this paper, we develop a novel ecological modeling tool using PINNs, which fits a feedforward neural network and simultaneously performs parameter identification in a partial differential equation (PDE) with varying coefficients. We demonstrate the applicability of our model by comparing it with the commonly used Bayesian stochastic partial differential equation method and traditional machine learning approaches, showing that our proposed model exhibits superior prediction and forecasting performance when modeling chronic wasting disease in deer in Wisconsin. Furthermore, our model provides the opportunity to obtain scientific insights into spatiotemporal covariates affecting spread and growth of diseases. This work contributes to future machine learning and statistical methodology development by studying spatio-temporal processes enhanced by prior physical knowledge.

Spatial Statistics↗

USGS2023

Bayesian spatio-temporal survival analysis for all types of censoring with application to a wildlife disease study

In this article, we consider modeling arbitrarily censored survival data with spatio-temporal covariates. We demonstrate that under the piecewise constant hazard function, the likelihood for uncensored or right-censored subjects is proportional to the likelihood of multiple conditionally independent Poisson random variables. To address left- or interval-censored subjects, we propose to impute the exact event times and convert them into uncensored subjects, enabling the application of the integrated nested Laplace approximation to update model parameters using the imputed data. We introduce an iterative algorithm that alternates between imputing event times for left- and interval-censored subjects and re-estimating model parameters. The proposed method is assessed through a simulation study and applied to analyze a spatio-temporal survival dataset in a wildlife disease study investigating bovine tuberculosis in white-tailed deer in Michigan.

Environmetrics↗

USGS2019

Artificial intelligence and avian influenza: Using machine learning to enhance active surveillance for avian influenza viruses

Influenza A viruses are one of the most significant viral groups globally with substantial impacts on human, domestic animal and wildlife health. Wild birds are the natural reservoirs for these viruses, and active surveillance within wild bird populations provides critical information about viral evolution forming the basis of risk assessments and countermeasure development. Unfortunately, active surveillance programs are often resource‐intensive, and thus, enhancing programs for increased efficiency is paramount. Machine learning, a branch of artificial intelligence applications, provides statistical learning procedures that can be used to gain novel insights into disease surveillance systems. We use a form of machine learning, gradient boosted trees, to estimate the probability of isolating avian influenza viruses (AIV) from wild bird samples collected during surveillance for AIVs from 2006 to 2011 in the United States. We examined several predictive features including age, sex, bird type, geographic location and matrix gene rRT‐PCR results. Our final model had high predictive power and only included geographic location and rRT‐PCR results as important predictors. The highest predicted viral isolation probability was for samples collected from the north‐central states and the south‐eastern region of Alaska. Lower rRT‐PCR Ct‐values are associated with increased likelihood of AIV isolation, and the model estimated 16% probability of isolating AIV from samples declared negative (i.e., ≥35 Ct‐value) using the rRT‐PCR screening test and standard protocols. Our model can be used to prioritize previously collected samples for isolation and rapidly evaluate AIV surveillance designs to maximize the probability of viral isolation given limited resources and laboratory capacity.

Transboundary and Emerging Diseases↗

USGS2015

Human and bovine viruses and bacteria at three Great Lakes beaches: Environmental variable associations and health risk

Waterborne pathogens were measured at three beaches in Lake Michigan, environmental factors for predicting pathogen concentrations were identified, and the risk of swimmer infection and illness was estimated. Waterborne pathogens were detected in 96% of samples collected at three Lake Michigan beaches in summer, 2010. Samples were quantified for 22 pathogens in four microbial categories (human viruses, bovine viruses, protozoa, and pathogenic bacteria). All beaches had detections of human and bovine viruses and pathogenic bacteria indicating influence of multiple contamination sources at these beaches. Occurrence ranged from 40 to 87% for human viruses, 65–87% for pathogenic bacteria, and 13–35% for bovine viruses. Enterovirus, adenovirus A, Salmonella spp. , Campylobacter jejuni , bovine polyomavirus, and bovine rotavirus A were present most frequently. Variables selected in multiple regression models used to explore environmental factors that influence pathogens included wave direction, cloud cover, currents, and water temperature. Quantitative Microbial Risk Assessment was done for C. jejuni , Salmonella spp. , and enteroviruses to estimate risk of infection and illness. Median infection risks for one-time swimming events were approximately 3 × 10 –5 , 7 × 10 –9 , and 3 × 10 –7 for C. jejuni , Salmonella spp., and enteroviruses, respectively. Results highlight the importance of investigating multiple pathogens within multiple categories to avoid underestimating the prevalence and risk of waterborne pathogens.

Wisconsin↗

USGS2014

Movement-based estimation and visualization of space use in 3D for wildlife ecology and conservation

Advances in digital biotelemetry technologies are enabling the collection of bigger and more accurate data on the movements of free-ranging wildlife in space and time. Although many biotelemetry devices record 3D location data with x, y , and z coordinates from tracked animals, the third z coordinate is typically not integrated into studies of animal spatial use. Disregarding the vertical component may seriously limit understanding of animal habitat use and niche separation. We present novel movement-based kernel density estimators and computer visualization tools for generating and exploring 3D home ranges based on location data. We use case studies of three wildlife species – giant panda, dugong, and California condor – to demonstrate the ecological insights and conservation management benefits provided by 3D home range estimation and visualization for terrestrial, aquatic, and avian wildlife research.

PLoS ONE↗

USGS2013

Source and transport of human enteric viruses in deep municipal water supply wells

Until recently, few water utilities or researchers were aware of possible virus presence in deep aquifers and wells. During 2008 and 2009 we collected a time series of virus samples from six deep municipal water-supply wells. The wells range in depth from approximately 220 to 300 m and draw water from a sandstone aquifer. Three of these wells draw water from beneath a regional aquitard, and three draw water from both above and below the aquitard. We also sampled a local lake and untreated sewage as potential virus sources. Viruses were detected up to 61% of the time in each well sampled, and many groundwater samples were positive for virus infectivity. Lake samples contained viruses over 75% of the time. Virus concentrations and serotypes observed varied markedly with time in all samples. Sewage samples were all extremely high in virus concentration. Virus serotypes detected in sewage and groundwater were temporally correlated, suggesting very rapid virus transport, on the order of weeks, from the source(s) to wells. Adenovirus and enterovirus levels in the wells were associated with precipitation events. The most likely source of the viruses in the wells was leakage of untreated sewage from sanitary sewer pipes.

Wisconsin↗

USGS2013

Mapping behavioral landscapes for animal movement: a finite mixture modeling approach

Because of its role in many ecological processes, movement of animals in response to landscape features is an important subject in ecology and conservation biology. In this paper, we develop models of animal movement in relation to objects or fields in a landscape. We take a finite mixture modeling approach in which the component densities are conceptually related to different choices for movement in response to a landscape feature, and the mixing proportions are related to the probability of selecting each response as a function of one or more covariates. We combine particle swarm optimization and an Expectation-Maximization (EM) algorithm to obtain maximum likelihood estimates of the model parameters. We use this approach to analyze data for movement of three bobcats in relation to urban areas in southern California, USA. A behavioral interpretation of the models revealed similarities and differences in bobcat movement response to urbanization. All three bobcats avoided urbanization by moving either parallel to urban boundaries or toward less urban areas as the proportion of urban land cover in the surrounding area increased. However, one bobcat, a male with a dispersal-like large-scale movement pattern, avoided urbanization at lower densities and responded strictly by moving parallel to the urban edge. The other two bobcats, which were both residents and occupied similar geographic areas, avoided urban areas using a combination of movements parallel to the urban edge and movement toward areas of less urbanization. However, the resident female appeared to exhibit greater repulsion at lower levels of urbanization than the resident male, consistent with empirical observations of bobcats in southern California. Using the parameterized finite mixture models, we mapped behavioral states to geographic space, creating a representation of a behavioral landscape. This approach can provide guidance for conservation planning based on analysis of animal movement data using statistical models, thereby linking connectivity evaluations to empirical data.

Ecological Applications↗