Predicting Grocery Store Visits During the Early Outbreak of COVID-19 with Machine Learning.

While non-essential travel was canceled during the coronavirus infectious disease (COVID-19) pandemic, grocery shopping was essential. The objectives of this study were to: 1) examine how grocery store visits changed during the early outbreak of COVID-19, and 2) estimate a model to predict the change of grocery store visits in the future, within the same phase of the pandemic. The study period (February 15-May 31, 2020) covered the outbreak and phase-one re-opening. Six counties/states in the United States were examined. Grocery store visits (in-store or curbside pickup) increased over 20% when the national emergency was declared on March 13 and then decreased below the baseline within a week. Grocery store visits on weekends were affected more significantly than those on workdays before late April. Grocery store visits in some states (including California, Louisiana, New York, and Texas) started returning to normal by the end of May, but that was not the case for some of the counties (including those with the cities of Los Angeles and New Orleans). With data from Google Mobility Reports, this study used a long short-term memory network to predict the change of grocery store visits from the baseline in the future. The networks trained with the national data or the county data performed well in predicting the general trend of each county. The results from this study could help understand mobility patterns of grocery store visits during the pandemic and predict the process of returning to normal.

How do Parents Manage Symptomatic Children? Social-Distancing Insights for COVID-19 and Seasonal Influenza.

Strategies for controlling pandemics include social distancing. Using data from a 2016 nation-wide survey pertaining to influenza, (generalized) ordered logit models are developed to identify the factors associated with the relative frequency (never/sometimes/always) a household (a) isolates a sick child from others in the household, (b) keeps the sick child out of school/daycare, (c) stops the child's social activities, (d) has a parent stay home to care for the child, and (e) has another adult care for the child. Marital status is non-significant for isolation practices but is significant in caregiving. Married individuals are 25% more likely to report a parent always staying home with a sick child. Males are more likely to report never isolating a sick child (6%, 3%, and 2% for actions a, b, and c, respectively) and 3% more likely to never have a parent stay home. Individuals knowledgeable about the disease are 10% more likely to always keep a sick child home from school/daycare. Parents are 27% more likely to always stay home with an infant. Individuals who had never worn masks (before the survey) are less likely to isolate a child within the household, but do not act significantly differently with respect to school/daycare.

Building an Interdisciplinary Team for Disaster Response Research: A Data-Driven Approach.

Building an interdisciplinary team is critical to disaster response research as it often deals with acute onset events, short decision horizons, constrained resources, and uncertainties related to rapidly unfolding response environments.  This article examines three teaming mechanisms for interdisciplinary disaster response research, including ad hoc and/or grant proposal driven teams, research center or institute based teams, and teams oriented by matching expertise toward long-term collaborations. Using hurricanes as the response context, it further examines several types of critical data that require interdisciplinary collaboration on collection, integration, and analysis. Last, suggesting a data-driven approach to engaging multiple disciplines, the article advocates building interdisciplinary teams for disaster response research with a long-term goal and an integrated research protocol.

The Frontiers of Uncertainty Estimation in Interdisciplinary Disaster Research and Practice.

Conceptualizing, assessing, and managing disaster risks involve collecting and synthesizing pluralistic information-from natural, built, and human systems-to characterize disaster impacts and guide policy on effective resilience investments. Disaster research and practice, therefore, are highly complex and inherently interdisciplinary endeavors. Characterizing the uncertainties involved in interdisciplinary disaster research is imperative, since misrepresenting uncertainty can lead to myopic decisions and suboptimal societal outcomes. Efficacious disaster mitigation should, therefore, explicitly address the uncertainties associated with all stages of hazard modeling, preparation, and response. However, uncertainty assessment and communication in the context of interdisciplinary disaster research remain understudied. In this "Perspective" article, we argue that in harnessing interdisciplinary methods and diverse data types in disaster research, careful deliberations on assessing Type III and Type IV errors are imperative. Additionally, we discuss the pathologies in frequentist approaches, calling for an increasing role for Bayesian methods in uncertainty estimations. Moreover, we discuss the potential tradeoffs associated with information and uncertainty, calling for deliberate consideration of the role of diversity of information prior to setting the scope in interdisciplinary modeling. Future research guided by further reflections on the ideas raised in this article could help push the frontiers of uncertainty estimation in interdisciplinary hazard research and practice.

Critical Time, Space, and Decision-Making Agent Considerations in Human-Centered Interdisciplinary Hurricane-Related Research.

In hazard and disaster contexts, human-centered approaches are promising for interdisciplinary research since humans and communities feature prominently in many definitions of disaster and the built environment is designed and constructed by humans to serve their needs. With a human-centered approach, the decision-making agent becomes a critical consideration. This article discusses and illustrates the need for alignment of decision-making agents, time, and space for interdisciplinary research on hurricanes, particularly evacuation and the immediate aftermath. We specifically consider the fields of sociobehavioral science, transportation engineering, power systems engineering, and decision support systems in this context. These disciplines have historically adopted different decision-making agents, ranging from individuals to households to utilities and government agencies. The fields largely converged to the local level for studies' spatial scales, with some extensions based on the physical construction and operation of some systems. Greater discrepancy across the fields is found in the frequency of data collection, which ranges from one time (e.g., surveys) to continuous monitoring systems (e.g., sensors). Resolving these differences is important for the success of interdisciplinary teams in protective-action-related disaster research.

Influenza risk perception and travel-related health protection behavior in the US: Insights for the aftermath of the COVID-19 outbreak.

Influenza is a contagious virus affecting both one's health and economic productivity. This study evaluates uses a survey of 2168 individuals across the U.S. Ordered logit regressions are used to model risk perception and generalized ordered logit regressions are used to model risk mitigation travel-related decisions. Models are estimated for three influenza outbreak scenarios, specifically an individual's travel-related: 1) risk perceptions, 2) risk mitigation decisions when infected and the individual wants to prevent spreading it, and may want treatment, and 3) risk mitigation decisions when not infected and the individual wants to reduce exposure. Risk perception results show that a recent personal experience with influenza-like symptoms and being female significantly increased risk perception at mandatory and medical trip locations. Risk mitigation model results show that males are less likely to alter their travel patterns in response to the possible spreading of the virus or increasing exposure. Knowing the difference between influenza and the stomach flu is more influential in reducing travel than a recent influenza experience in one's household. Individuals proactive with their health (i.e., receive the vaccine, have health insurance) are also proactive in seeking medical attention and reducing influenza spread. Lastly, aligned with the Protection Motivation Theory, individuals reduce travel to locations in which they perceived medium or high risk. However, increased risk perceived at one's work location did not significantly reduce travel. The findings provide insight into the risk perception and mitigation behavior of the American public during the COVID-19 pandemic and after restrictions are lifted.

Impact of demographic disparities in social distancing and vaccination on influenza epidemics in urban and rural regions of the United States.

BACKGROUND: Self-protective behaviors of social distancing and vaccination uptake vary by demographics and affect the transmission dynamics of influenza in the United States. By incorporating the socio-behavioral differences in social distancing and vaccination uptake into mathematical models of influenza transmission dynamics, we can improve our estimates of epidemic outcomes. In this study we analyze the impact of demographic disparities in social distancing and vaccination on influenza epidemics in urban and rural regions of the United States. METHODS: We conducted a survey of a nationally representative sample of US adults to collect data on their self-protective behaviors, including social distancing and vaccination to protect themselves from influenza infection. We incorporated this data in an agent-based model to simulate the transmission dynamics of influenza in the urban region of Miami Dade county in Florida and the rural region of Montgomery county in Virginia. RESULTS: We compare epidemic scenarios wherein the social distancing and vaccination behaviors are uniform versus non-uniform across different demographic subpopulations. We infer that a uniform compliance of social distancing and vaccination uptake among different demographic subpopulations underestimates the severity of the epidemic in comparison to differentiated compliance among different demographic subpopulations. This result holds for both urban and rural regions. CONCLUSIONS: By taking into account the behavioral differences in social distancing and vaccination uptake among different demographic subpopulations in analysis of influenza epidemics, we provide improved estimates of epidemic outcomes that can assist in improved public health interventions for prevention and control of influenza.

The dynamic nature of risk perceptions after a fatal transit accident.

In 2009, two trains of Washington, DC's Metrorail system collided, resulting in nine deaths and 50 serious injuries. Based on a multiwave survey of Metrorail users in the months after the crash, this article reports how the accident appears to have (1) changed over time the tradeoffs among safety, speed, frequency of service, cost, and reliability that the transit users stated they were willing to make in the postaccident period and (2) altered transit users' concerns about safety as a function of time and distance from the accident site. We employ conditional logit models to examine tradeoffs among stated preferences for system performance measures after the accident, as well as the influence that respondent characteristics of transit use, location, income, age, and gender have on these preference tradeoffs. As expected, respondents appear averse to longer headways between trains, longer travel durations, higher travel costs, a higher number of late trains, and a higher number of fatalities. The models also show evidence of higher aversion to fatalities from transit system operation among females compared to males. In addition, respondents less experienced with Metrorail travel and those with lower household incomes show higher aversion to fatalities, and this aversion increases as a subject's psychological distance from the accident site decreases. Contrary to expectations shaped by previous studies, aversion to fatalities appears to have increased between the early months after the accident and the end of the survey period, and the expected relationship between age and aversion to fatalities is not statistically significant.

Uniting multi-adult households during emergency evacuation planning.

When a no-notice emergency prompts an evacuation, family members in different locations throughout a city may unite so that they can evacuate as a group. This paper draws on data from more than 300 interviews conducted in the metropolitan area of Chicago, Illinois, United States. The study uses discrete choice models to analyse the expectations of respondents regarding whether their likely plans for evacuation involve gathering spouses, parents, adult-age children, and/or non-family members. In addition, it addresses the matter of whether respondents plan to reunite with family members at home. Individuals' access to a personal car is the dominating factor in predicting whether respondents plan to gather a spouse. Being the parent of a child under the age of 18 years increases the tendency to report planning to reunite with family members at home. Both commute mode and car availability are not significantly associated with plans to reunite at home.