During recent decades, pathogens that originated in bats have become an increasing public health concern. A major challenge is to identify how those pathogens spill over into human populations to generate a pandemic threat¹. Many correlational studies associate spillover with changes in land use or other anthropogenic stressors^2,3, although the mechanisms underlying the observed correlations have not been identified⁴. One limitation is the lack of spatially and temporally explicit data on multiple spillovers, and on the connections among spillovers, reservoir host ecology and behaviour and viral dynamics. We present 25 years of data on land-use change, bat behaviour and spillover of Hendra virus from Pteropodid bats to horses in subtropical Australia. These data show that bats are responding to environmental change by persistently adopting behaviours that were previously transient responses to nutritional stress. Interactions between land-use change and climate now lead to persistent bat residency in agricultural areas, where periodic food shortages drive clusters of spillovers. Pulses of winter flowering of trees in remnant forests appeared to prevent spillover. We developed integrative Bayesian network models based on these phenomena that accurately predicted the presence or absence of clusters of spillovers in each of the 25 years. Our long-term study identifies the mechanistic connections between habitat loss, climate and increased spillover risk. It provides a framework for examining causes of bat virus spillover and for developing ecological countermeasures to prevent pandemics.

Measles is an important infectious disease system both for its burden on public health and as an opportunity for studying nonlinear spatio-temporal disease dynamics. Traditional mechanistic models often struggle to fully capture the complex nonlinear spatio-temporal dynamics inherent in measles outbreaks. In this paper, we first develop a high-dimensional feed-forward neural network model with spatial features (SFNN) to forecast endemic measles outbreaks and systematically compare its predictive power with that of a classical mechanistic model (TSIR). We illustrate the utility of our model using England and Wales measles data from 1944-1965. These data present multiple modeling challenges due to the interplay between metapopulations, seasonal trends, and nonlinear dynamics related to demographic changes. Our results show that while the TSIR model yields similarly performant short-term (1 to 2 biweeks ahead) forecasts for highly populous cities, our neural network model (SFNN) consistently achieves lower root mean squared error (RMSE) across other forecasting windows. Furthermore, we show that our spatial-feature neural network model, without imposing mechanistic assumptions a priori, can uncover gravity-model-like spatial hierarchy of measles spread in which major cities play an important role in driving regional outbreaks. We then turn our attention to integrative approaches that combine mechanistic and machine learning models. Specifically, we investigate how the TSIR can be utilized to improve a state-of-the-art approach known as Physics-Informed-Neural-Networks (PINN) which explicitly combines compartmental models and neural networks. Our results show that the TSIR can facilitate the reconstruction of latent susceptible dynamics, thereby enhancing both forecasts in terms of mean absolute error (MAE) and parameter inference of measles dynamics within the PINN. In summary, our results show that appropriately designed neural network-based models can outperform traditional mechanistic models for short to long-term forecasts, while simultaneously providing mechanistic interpretability. Our work also provides valuable insights into more effectively integrating machine learning models with mechanistic models to enhance public health responses to measles and similar infectious disease systems.

SARS-CoV-2 spreads quickly in dense populations, with serious implications for universities, workplaces, and other settings where exposure reduction practices are difficult to implement. Rapid screening has been proposed as a tool to slow the spread of the virus; however, many commonly used diagnostic tests (e.g., RT-qPCR) are expensive, difficult to deploy (e.g., require a nasopharyngeal specimen), and have extended turn-around times. We evaluated testing regimes that combined diagnostic testing using qPCR with high-frequency screening using a novel reverse-transcription loop-mediated isothermal amplification (RT-LAMP, herein LAMP) assay. We used a compartmental susceptible-exposed-infectious-recovered (SEIR) model to simulate screening of a university population. We also developed a Shiny application to allow administrators and public health professionals to develop optimal testing strategies given site-specific assumptions about testing investment, target population, and cost. The frequency of screening, especially when pooling samples, was more important for minimizing epidemic size than test sensitivity, behavioral compliance, contact tracing capacity, and time between testing and results. Our results suggest that when testing budgets are limited, it is safer and more cost-effective to allocate the majority of funds to screening. Rapid, cost-effective, and scalable screening tests, like LAMP, should be viewed as critical components of SARS-CoV-2 testing in high-density populations.

Food availability determines where animals use space across a landscape and therefore affects the risk of encounters that lead to zoonotic spillover. This relationship is evident in Australian flying foxes ( Pteropus spp; fruit bats), where acute food shortages precede clusters of Hendra virus spillovers. Using explainable artificial intelligence, we predicted months of food shortages from climatological and ecological covariates (1996-2022) in eastern Australia. Overall accuracy in predicting months of low food availability on a test set from 2018 up to 2022 reached 93.33% and 92.59% based on climatological and bat-level features, respectively. Seasonality and Oceanic El Niño Index were the most important environmental features, while the number of bats in rescue centers and their body weights were the most important bat-level features. These models support predictive signals up to nine months in advance, facilitating action to mitigate spillover risk.

Ambient fine particulate matter of size less than 2.5 μm in aerodynamic diameter (PM_2.5) is a key ambient air pollutant that has been linked to numerous adverse health outcomes. Reliable estimates of PM_2.5 are important for supporting epidemiological and health impact assessment studies. Precise measurements of PM_2.5 are available through networks of monitors; however, these are spatially sparse and temporally incomplete. Chemical transport model (CTM) simulations and satellite-retrieved aerosol optical depth (AOD) measurements are two data sources that have been used to develop prediction models for PM_2.5 at fine spatial resolutions with increased spatial coverage. As part of the Multi-Angle Imager for Aerosols (MAIA) project, a geostatistical regression model has been developed to bias-correct AOD, followed by Bayesian ensemble averaging to gap-fill missing AOD values with CTM simulations. Here, we present a suite of statistical software (available in the R package ensembleDownscaleR) to facilitate the adaptation of this modeling approach to other settings and air quality modeling applications. We describe the Bayesian ensemble averaging approach, model specifications, estimation methods, and evaluation via cross-validation that is implemented in the software. We also provide a case study of estimating PM_2.5 using 2018 data from the Los Angeles metropolitan area with an accompanying tutorial. All code is fully reproducible and available on GitHub, data are made on Zenodo, and the ensembleDownscaleR package is available for download on GitHub.

Food availability determines where and how animals use space across a landscape and, therefore, affects the risk of encounters leading to zoonotic spillover. This relationship is evident in Australian flying foxes (Pteropus spp.; fruit bats), where acute food shortages precede clusters of Hendra virus spillovers. Using machine learning, we predicted months of food shortages from climatological and ecological covariates (1996–2022) in subtropical Australia. Overall accuracy in predicting months of low food availability on a test set from 2018 up to 2022 reached 93.33 and 92.59% based on climatological and bat-level features, respectively. Seasonality and the Oceanic El Niño Index were the most important environmental features, while the number of bats in rescue centres and their body weights were the most important bat-level features. These models support predictive signals up to nine months in advance, facilitating action to mitigate spillover risk.