Revealing Decision-Making Strategies of Americans in Taking COVID-19 Vaccination.

Efficient coverage for newly developed vaccines requires knowing which groups of individuals will accept the vaccine immediately and which will take longer to accept or never accept. Of those who may eventually accept the vaccine, there are two main types: success-based learners, basing their decisions on others' satisfaction, and myopic rationalists, attending to their own immediate perceived benefit. We used COVID-19 vaccination data to fit a mechanistic model capturing the distinct effects of the two types on the vaccination progress. We proved the identifiability of the population proportions of each type and estimated that 47 % of Americans behaved as myopic rationalists with a high variation across the jurisdictions, from 31 % in Mississippi to 76 % in Vermont. The proportion was correlated with the vaccination coverage, proportion of votes in favor of Democrats in 2020 presidential election, and education score.

Tackling data challenges in forecasting effluent characteristics of wastewater treatment plants.

In wastewater treatment plants (WWTPs), the stochastic nature of influent wastewater and operational and weather conditions cause fluctuations in effluent quality. Data-driven models can forecast effluent quality a few hours ahead as a response to the influent characteristics, providing enough time to adjust system operations and avoid undesired consequences. However, existing data for training models are often incomplete and contain missing values. On the other hand, collecting additional data by installing new sensors is costly. The trade-off between using existing incomplete data and collecting costly new data results in three data challenges faced when developing data-driven WWTP effluent forecasters. These challenges are to determine important variables to be measured, the minimum number of required data instances, and the maximum percentage of tolerable missing values that do not impede the development of an accurate model. As these issues are not discussed in previous studies, in this research, for the first time, a comprehensive analysis is done to provide answers to these challenges. Another issue that arises in all data-driven modeling is how to select an appropriate forecasting model. This paper addresses these issues by first testing nine machine learning models on data collected from three wastewater treatment plants located in Iran, Australia, and Spain. The most accurate forecaster, Bayesian network, was then used to address the articulated challenges. Key variables in forecasting effluent characteristics were flow rate, total suspended solids, electrical conductivity, phosphorus compounds, wastewater temperature, and air temperature. A minimum of 250 samples was needed during the model training to achieve a great reduction in the forecasting error. Moreover, a steep increase in the error was observed should the portion of missing values exceed 10%. The results assist plant managers in estimating the necessary data collection effort to obtain an accurate forecaster, contributing to the quality of the effluent.

From Policy to Prediction: Forecasting COVID-19 Dynamics Under Imperfect Vaccination.

Understanding the joint impact of vaccination and non-pharmaceutical interventions on COVID-19 development is important for making public health decisions that control the pandemic. Recently, we created a method in forecasting the daily number of confirmed cases of infectious diseases by combining a mechanistic ordinary differential equation (ODE) model for infectious classes and a generalized boosting machine learning model (GBM) for predicting how public health policies and mobility data affect the transmission rate in the ODE model (Wang et al. in Bull Math Biol 84:57, 2022). In this paper, we extend the method to the post-vaccination period, accordingly obtain a retrospective forecast of COVID-19 daily confirmed cases in the US, and identify the relative influence of the policies used as the predictor variables. In particular, our ODE model contains both partially and fully vaccinated compartments and accounts for the breakthrough cases, that is, vaccinated individuals can still get infected. Our results indicate that the inclusion of data on non-pharmaceutical interventions can significantly improve the accuracy of the predictions. With the use of policy data, the model predicts the number of daily infected cases up to 35 days in the future, with an average mean absolute percentage error of [Formula: see text], which is further improved to [Formula: see text] if combined with human mobility data. Moreover, the most influential predictor variables are the policies of restrictions on gatherings, testing and school closing. The modeling approach used in this work can help policymakers design control measures as variant strains threaten public health in the future.

A Hypothesis-Free Bridging of Disease Dynamics and Non-pharmaceutical Policies.

Accurate prediction of the number of daily or weekly confirmed cases of COVID-19 is critical to the control of the pandemic. Existing mechanistic models nicely capture the disease dynamics. However, to forecast the future, they require the transmission rate to be known, limiting their prediction power. Typically, a hypothesis is made on the form of the transmission rate with respect to time. Yet the real form is too complex to be mechanistically modeled due to the unknown dynamics of many influential factors. We tackle this problem by using a hypothesis-free machine-learning algorithm to estimate the transmission rate from data on non-pharmaceutical policies, and in turn forecast the confirmed cases using a mechanistic disease model. More specifically, we build a hybrid model consisting of a mechanistic ordinary differential equation (ODE) model and a gradient boosting model (GBM). To calibrate the parameters, we develop an "inverse method" that obtains the transmission rate inversely from the other variables in the ODE model and then feed it into the GBM to connect with the policy data. The resulting model forecasted the number of daily confirmed cases up to 35 days in the future in the USA with an averaged mean absolute percentage error of 27%. It can identify the most informative predictive variables, which can be helpful in designing improved forecasters as well as informing policymakers.

Networks of conforming or nonconforming individuals tend to reach satisfactory decisions.

Binary decisions of agents coupled in networks can often be classified into two types: "coordination," where an agent takes an action if enough neighbors are using that action, as in the spread of social norms, innovations, and viral epidemics, and "anticoordination," where too many neighbors taking a particular action causes an agent to take the opposite action, as in traffic congestion, crowd dispersion, and division of labor. Both of these cases can be modeled using linear-threshold-based dynamics, and a fundamental question is whether the individuals in such networks are likely to reach decisions with which they are satisfied. We show that, in the coordination case, and perhaps more surprisingly, also in the anticoordination case, the agents will indeed always tend to reach satisfactory decisions, that is, the network will almost surely reach an equilibrium state. This holds for every network topology and every distribution of thresholds, for both asynchronous and partially synchronous decision-making updates. These results reveal that irregular network topology, population heterogeneity, and partial synchrony are not sufficient to cause cycles or nonconvergence in linear-threshold dynamics; rather, other factors such as imitation or the coexistence of coordinating and anticoordinating agents must play a role.

The majority of Canadians likely behaved as myopic rationalists rather than success-based learners when deciding on their first dose of COVID-19 vaccine.

Introduction: Successful vaccine promotion communication strategies require knowing how eligible recipients will respond to the opportunity to get vaccinated. Two main classes of recipients are myopic rationalists, those who receive a dose of vaccine only if it maximizes their own instant benefit and if so, do it as soon as possible, and success-based learners, those who learn from others that they perceive to be most successful. Methods: A recent study models these two decision-making types, and estimates the population proportion of myopic rationalists in each U.S. state. In this report, we fit a similar model to data on COVID-19 vaccine uptake across the Canadian provinces and territories. Results: We estimated that 64% of Canadians behaved as myopic rationalists in taking the first dose of a COVID-19 vaccine, compared to an estimated 47% in the United States. Among the provinces, the lowest proportion of myopic rationalists was 0.51 in Saskatchewan, while the highest was 0.74 in Prince Edward Island. The correlation analysis suggested a positive correlation between the proportion of myopic rationalists and the average age across the Canadian provinces (Pearson-r = 0.71). Discussion: Canadian health management may benefit from these results in tailoring the vaccine promotion communication strategies.

From Policy to Prediction: Assessing Forecasting Accuracy in an Integrated Framework with Machine Learning and Disease Models.

To improve the forecasting accuracy of the spread of infectious diseases, a hybrid model was recently introduced where the commonly assumed constant disease transmission rate was actively estimated from enforced mitigating policy data by a machine learning (ML) model and then fed to an extended susceptible-infected-recovered model to forecast the number of infected cases. Testing only one ML model, that is, gradient boosting model (GBM), the work left open whether other ML models would perform better. Here, we compared GBMs, linear regressions, k-nearest neighbors, and Bayesian networks (BNs) in forecasting the number of COVID-19-infected cases in the United States and Canadian provinces based on policy indices of future 35 days. There was no significant difference in the mean absolute percentage errors of these ML models over the combined dataset [H(3)=3.10,p=0.38]. In two provinces, a significant difference was observed [H(3)=8.77,H(3)=8.07,p<0.05], yet posthoc tests revealed no significant difference in pairwise comparisons. Nevertheless, BNs significantly outperformed the other models in most of the training datasets. The results put forward that the ML models have equal forecasting power overall, and BNs are best for data-fitting applications.

An early warning indicator trained on stochastic disease-spreading models with different noises.

The timely detection of disease outbreaks through reliable early warning signals (EWSs) is indispensable for effective public health mitigation strategies. Nevertheless, the intricate dynamics of real-world disease spread, often influenced by diverse sources of noise and limited data in the early stages of outbreaks, pose a significant challenge in developing reliable EWSs, as the performance of existing indicators varies with extrinsic and intrinsic noises. Here, we address the challenge of modelling disease when the measurements are corrupted by additive white noise, multiplicative environmental noise and demographic noise into a standard epidemic mathematical model. To navigate the complexities introduced by these noise sources, we employ a deep learning algorithm that provides EWS in infectious disease outbreaks by training on noise-induced disease-spreading models. The indicator's effectiveness is demonstrated through its application to real-world COVID-19 cases in Edmonton and simulated time series derived from diverse disease spread models affected by noise. Notably, the indicator captures an impending transition in a time series of disease outbreaks and outperforms existing indicators. This study contributes to advancing early warning capabilities by addressing the intricate dynamics inherent in real-world disease spread, presenting a promising avenue for enhancing public health preparedness and response efforts.

Climate-dependent effectiveness of nonpharmaceutical interventions on COVID-19 mitigation.

Environmental factors have a significant impact on the transmission of infectious diseases. Existing results show that the novel coronavirus can persist outside the host. We propose a susceptible-exposed-presymptomatic-infectious-asymptomatic-recovered-susceptible (SEPIARS) model with a vaccination compartment and indirect incidence to explore the effect of environmental conditions, temperature and humidity, on the transmission of the SARS-CoV-2 virus. Using climate data and daily confirmed cases data in two Canadian cities with different atmospheric conditions, we evaluate the mortality rates of the SARS-CoV-2 virus and further estimate the transmission rates by the inverse method, respectively. The numerical results show that high temperature or humidity can be helpful in mitigating the spread of COVID-19 during the warm summer months. Our findings verify that nonpharmaceutical interventions are less effective if the virus can persist for a long time on surfaces. Based on climate data, we can forecast the transmission rate and the infection cases up to four weeks in the future by a generalized boosting machine learning model.

Predicting insect outbreaks using machine learning: A mountain pine beetle case study.

Planning forest management relies on predicting insect outbreaks such as mountain pine beetle, particularly in the intermediate-term future, e.g., 5-year. Machine-learning algorithms are potential solutions to this challenging problem due to their many successes across a variety of prediction tasks. However, there are many subtle challenges in applying them: identifying the best learning models and the best subset of available covariates (including time lags) and properly evaluating the models to avoid misleading performance-measures. We systematically address these issues in predicting the chance of a mountain pine beetle outbreak in the Cypress Hills area and seek models with the best performance at predicting future 1-, 3-, 5- and 7-year infestations. We train nine machine-learning models, including two generalized boosted regression trees (GBM) that predict future 1- and 3-year infestations with 92% and 88% AUC, and two novel mixed models that predict future 5- and 7-year infestations with 86% and 84% AUC, respectively. We also consider forming the train and test datasets by splitting the original dataset randomly rather than using the appropriate year-based approach and show that this may obtain models that score high on the test dataset but low in practice, resulting in inaccurate performance evaluations. For example, a k-nearest neighbor model with the actual performance of 68% AUC, scores the misleadingly high 78% on a test dataset obtained from a random split, but the more accurate 66% on a year-based split. We then investigate how the prediction accuracy varies with respect to the provided history length of the covariates and find that neural network and naive Bayes, predict more accurately as history-length increases, particularly for future 1- and 3-year predictions, and roughly the same holds with GBM. Our approach is applicable to other invasive species. The resulting predictors can be used in planning forest and pest management and planning sampling locations in field studies.

Dataset of COVID-19 outbreak and potential predictive features in the USA.

This dataset provides information related to the outbreak of COVID-19 disease in the United States, including data from each of 3142 US counties from the beginning of the outbreak (January 2020) until June 2021. This data is collected from many public online databases and includes the daily number of COVID-19 confirmed cases and deaths, as well as 46 features that may be relevant to the pandemic dynamics: demographic, geographic, climatic, traffic, public-health, social-distancing-policy adherence, and political characteristics of each county. We anticipate many researchers will use this dataset to train models that can predict the spread of COVID-19 and to identify the key driving factors.

Accurate long-range forecasting of COVID-19 mortality in the USA.

The need for improved models that can accurately predict COVID-19 dynamics is vital to managing the pandemic and its consequences. We use machine learning techniques to design an adaptive learner that, based on epidemiological data available at any given time, produces a model that accurately forecasts the number of reported COVID-19 deaths and cases in the United States, up to 10 weeks into the future with a mean absolute percentage error of 9%. In addition to being the most accurate long-range COVID predictor so far developed, it captures the observed periodicity in daily reported numbers. Its effectiveness is based on three design features: (1) producing different model parameters to predict the number of COVID deaths (and cases) from each time and for a given number of weeks into the future, (2) systematically searching over the available covariates and their historical values to find an effective combination, and (3) training the model using "last-fold partitioning", where each proposed model is validated on only the last instance of the training dataset, rather than being cross-validated. Assessments against many other published COVID predictors show that this predictor is 19-48% more accurate.

Homophily, heterophily and the diversity of messages among decision-making individuals.

To better understand the intriguing mechanisms behind cooperation among decision-making individuals, we study the simple yet appealing use of preplay communication or cheap talk in evolutionary games, when players are able to choose strategies based on whether an opponent sends the same message as they do. So when playing games, in addition to pure cooperation and defection, players have two new strategies in this setting: homophilic (respectively, heterophilic) cooperation which is to cooperate (respectively, defect) only with those who send the same message as they do. We reveal the intrinsic qualities of individuals playing the two strategies and show that under the replicator dynamics, homophilic cooperators engage in a battle of messages and will become dominated by whichever message is the most prevalent at the start, while populations of heterophilic cooperators exhibit a more harmonious behaviour, converging to a state of maximal diversity. Then we take Prisoner's Dilemma (PD) as the base of the cheap-talk game and show that the hostility of heterophilics to individuals with similar messages leaves no possibility for pure cooperators to survive in a population of the two, whereas the one-message dominance of homophilics allows for pure cooperators with the same tag as the dominant homophilics to coexist in the population, demonstrating that homophilics are more cooperative than heterophilics. Finally, we generalize an existing convergence result on population shares associated with weakly dominated strategies to a broadly applicable theorem and complete previous research on PD games with preplay communication by proving that the frequencies of all types of cooperators, i.e. pure, homophilic and heterophilic, converge to zero in the face of defectors. This implies homophily and heterophily cannot facilitate the long-term survival of cooperation in this setting, which urges studying cheap-talk games under other reproduction dynamics.

Evolutionary Dynamics of Homophily and Heterophily.

Most social interactions do not take place at random. In many situations, individuals choose their interaction partners on the basis of phenotypic cues. When this happens, individuals are often homophilic, that is, they tend to interact with individuals that are similar to them. Here we investigate the joint evolution of phenotypic cues and cue-dependent interaction strategies. By a combination of individual-based simulations and analytical arguments, we show that homophily evolves less easily than earlier studies suggest. The evolutionary interplay of cues and cue-based behaviour is intricate and has many interesting facets. For example, an interaction strategy like heterophily may stably persist in the population even if it is selected against in association with any particular cue. Homophily persisted for extensive periods of time just in those simulations where homophilic interactions provide a lower (rather than a higher) payoff than heterophilic interactions. Our results indicate that even the simplest cue-based social interactions can have rich dynamics and a surprising diversity of evolutionary outcomes.

How feeling betrayed affects cooperation.

For a population of interacting self-interested agents, we study how the average cooperation level is affected by some individuals' feelings of being betrayed and guilt. We quantify these feelings as adjusted payoffs in asymmetric games, where for different emotions, the payoff matrix takes the structure of that of either a prisoner's dilemma or a snowdrift game. Then we analyze the evolution of cooperation in a well-mixed population of agents, each of whom is associated with such a payoff matrix. At each time-step, an agent is randomly chosen from the population to update her strategy based on the myopic best-response update rule. According to the simulations, decreasing the feeling of being betrayed in a portion of agents does not necessarily increase the level of cooperation in the population. However, this resistance of the population against low-betrayal-level agents is effective only up to some extend that is explicitly determined by the payoff matrices and the number of agents associated with these matrices. Two other models are also considered where the betrayal factor of an agent fluctuates as a function of the number of cooperators and defectors that she encounters. Unstable behaviors are observed for the level of cooperation in these cases; however, we show that one can tune the parameters in the function to make the whole population become cooperative or defective.