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.

Estimating long-term and short-term impact of COVID-19 activity restriction on regional highway traffic demand: A case study in Zhejiang Province, China.

Since the outbreak of COVID-19 in China in late 2019, government administrators have implemented traffic restriction policies to prevent the spread of COVID-19. However, highway traffic volumes obtained from ETC data in some provinces did not return to the levels of previous years after the end of the traffic restriction policy, suggesting that traffic restriction policy may have long-term effects. This paper proposed a method that analyzes traffic restriction policies' long-term and short-term impact on highway traffic volume under COVID-19. This method first analyzes the long-term and short-term impacts of traffic restriction policies on the highway traffic volume using the Prophet model combined with the concept of traffic volume loss. It further investigates the relationship between COVID-19 cases and the long-term and short-term impacts of the traffic restriction policy using Granger causality and the impulse response function of the Bayesian vector autoregressive (BVAR) model. The results showed that during the COVID-19 pandemic, highway traffic in Zhejiang Province decreased by about 95.5%, and the short-term impact of COVID-19 cases was most pronounced on the second day. However, the long-term effects were relatively small when the traffic restriction policy ended and was verified by data from other provinces. These results will provide decision support for traffic management and provide recommendations for future traffic impact assessments in the event of similar epidemics.

COVID-19, traffic demand, and activity restriction in China: A national assessment.

The global COVID pandemic of 2020, affected travel patterns across the world. The level of impact was influenced not only by the virus itself, but also by the nature, extent, and duration of governmental restriction on commerce and personal activity to limit its spread. This paper focuses on the interaction between COVID-19 transmission and traffic volume and further explores the impact of traffic control policies on the interaction. Roadway traffic volume was used to quantify and assess the Chinese response to the pandemic; specifically, the relationship between government restrictions, travel activity, and COVID-19 progression across 29 provinces. Space and time distributions of traffic volume across China during the first half of 2020, were used to quantity the response and recovery of travel during the critical initial onset period of the virus. Most revealing of these trends were the impact of the Chinese restriction policies on both travel and the virus as well as the relationship of traffic trends during the closure period with the speed and extent of the recovery "bounce" across individual provinces based on location, economic activity, and restriction policy. These suggest that the most significant and rapid declines in traffic volume during the restriction period resulted in the most pronounced returns to normal (or more) demand levels. Based on these trends a Susceptible Infection Recovery model was created to simulate a range of outbreak and restriction policies to examine the relationship between COVID-19 spread and traffic volume in China.

Toward a crowdsourcing solution to identify high-risk highway segments through mining driving jerks.

Traffic crashes have become a leading cause of preventable deaths globally. Identifying high-risk segments not only benefits safety specialists to better understand crash patterns but also reminds road users to be aware of driving risks. This study reports on a new crowdsourcing solution to identify high-risk highway segments by analyzing driving jerks. Driving jerks represent the abrupt changes of acceleration, which have been shown to be closely related to traffic risks. In this study, we first calculate driving jerks from each participant's naturalistic driving data and identify "unsafe" drivers based on their jerk-ratio. Then, we innovatively propose an improved line-constrained clustering method to identify each participant's jerk clusters on each road. These individual-specific jerk clusters are overlapped with road networks to identify potential risky segments. By synthesizing these potential risky segments reported by different participants, we obtain the final detection results for high-risk highway segments. In this study, we compare the jerk-cluster-determined risky segments with crash-rate-determined risky segments to evaluate the proposed solution's effectiveness. The study results demonstrate that our crowdsourcing solution can effectively identify high-risk road segments with an estimated 75 % accuracy. More importantly, by analyzing this valued surrogate measure, safety specialists can identify hazardous road segments before crashes occur.

Assessment of evacuation training needs: Targeting instruction to meet the requirements of local communities and agencies.

As the need to prepare for, respond to, and recover from major disruptive events continues to become more critical, the use of evacuation as a protective action strategy when confronted with life-threatening disasters is a key component of community resilience planning. While the basic concepts of evacuations are straightforward and consistent across locations and hazard types, the details of planning and managing an evacuation are more varied and complex. To improve evacuation preparedness, the training of emergency managers, police, and transportation agencies becomes key. This study assesses the need for evacuation training among key governmental agencies. A national survey of evacuation planning training needs among emergency managers and those involved in transportation management and operations was undertaken in 2016. This paper summarizes key findings of this survey, which included 727 respondents across 136 cities and 48 states and 2 territories, to reveal the results of this training-needs self-assessment. Based on this analysis, training needs and other recommendations for the development and delivery of curriculum on evacuation planning are presented.

A preliminary investigation of the relationships between historical crash and naturalistic driving.

This paper describes a project that was undertaken using naturalistic driving data collected via Global Positioning System (GPS) devices to demonstrate a proof-of-concept for proactive safety assessments of crash-prone locations. The main hypothesis for the study is that the segments where drivers have to apply hard braking (higher jerks) more frequently might be the "unsafe" segments with more crashes over a long-term. The linear referencing methodology in ArcMap was used to link the GPS data with roadway characteristic data of US Highway 101 northbound (NB) and southbound (SB) in San Luis Obispo, California. The process used to merge GPS data with quarter-mile freeway segments for traditional crash frequency analysis is also discussed in the paper. A negative binomial regression analyses showed that proportion of high magnitude jerks while decelerating on freeway segments (from the driving data) was significantly related with the long-term crash frequency of those segments. A random parameter negative binomial model with uniformly distributed parameter for ADT and a fixed parameter for jerk provided a statistically significant estimate for quarter-mile segments. The results also indicated that roadway curvature and the presence of auxiliary lane are not significantly related with crash frequency for the highway segments under consideration. The results from this exploration are promising since the data used to derive the explanatory variable(s) can be collected using most off-the-shelf GPS devices, including many smartphones.

Selection and allocation of manual traffic control points and personnel during emergencies.

Manual traffic control is an intersection control strategy in which law enforcement officers allocate intersection right-of-way to turning movements. Many emergency traffic management plans call for manual traffic control in response to oversaturated roadway conditions. This is because it is thought to more effectively move traffic during temporary surges in demand. The goal of this research was to evaluate the current state-of-the-practice used by the Army Corps of Engineers (ACE) in selecting intersections for manual traffic control and allocating police personnel to them during emergencies. This research uses the emergency traffic management plans developed by the ACE for nine counties in the Maryland Eastern Shore region. This area encompassing 14,318 intersections of which 74 were selected for manual traffic control during emergencies. This work sought to quantify the correlations that exist between intersection attributes and the ACE' decision to allocate officers to control them. The research findings suggest that US routes, State routes, and emergency evacuation routes are statistically significant in determining the need for police control at intersections. Also significant are intersection on contraflow corridors and intersections near grade separated interchanges. The model also determined that intersections isolated from evacuation routes and county exits were more likely to be selected for manual control, indicating that rural areas may rely on manual traffic control in the absence of multilane highway and freeways. This research also found that intersections involving evacuation routes, contraflow corridors, and grade separated interchanges may warrant additional police personnel (two or more officers) for manual traffic control.

Experimental modeling of the effect of hurricane wind forces on driving behavior and vehicle performance.

While traffic planning is important for developing a hurricane evacuation plan, vehicle performance on the roads during extreme weather conditions is critical to the success of the planning process. This novel study investigates the effect of gusty hurricane wind forces on the driving behavior and vehicle performance. The study explores how the parameters of a driving simulator could be modified to reproduce wind loadings experienced by three vehicle types (passenger car, ambulance, and bus) during gusty hurricane winds, through manipulation of appropriate software. Thirty participants were then tested on the modified driving simulator under five wind conditions (ranging from normal to hurricane category 4). The driving performance measures used were heading error and lateral displacement. The results showed that higher wind forces resulted in more varied and greater heading error and lateral displacement. The ambulance had the greatest heading errors and lateral displacements, which were attributed to its large lateral surface area and light weight. Two mathematical models were developed to estimate the heading error and lateral displacements for each of the vehicle types for a given change in lateral wind force. Through a questionnaire, participants felt the different characteristics while driving each vehicle type. The findings of this study demonstrate the valuable use of a driving simulator to model the behavior of different vehicle types and to develop mathematical models to estimate and quantify driving behavior and vehicle performance under hurricane wind conditions.