Hurricanes are devastating natural disasters. In deciding how to respond to a hurricane, in particular whether and when to evacuate, a decision-maker must weigh often highly uncertain and contradic- tory information about the future path and intensity of the storm. To effectively plan to help people during a hurricane, it is crucial to be able to predict and understand this evacuation decision. To this end, we propose a computational model of human sequential decision-making in response to a hurricane based on a Partial Ob- servable Markov Decision Process (POMDP) that models concerns, uncertain beliefs about the hurricane, and future information. We evaluate the model in two ways. First, hurricane data from 2018 was used to evaluate the model’s predictive ability on real data. Second, a simulation study was conducted to qualitatively evaluate the sequential aspect of the model to illustrate the role that the acquisition of future, more accurate information can play on cur- rent decision-making. The evaluation with 2018 hurricane season data shows that our proposed features are significant predictors and the model can predict the data well, within and across distinct hurricane datasets. The simulation results show that, across dif- ferent setups, our model generates predictions on the sequential decisions making aspect that align with expectations qualitatively and suggests the importance of modeling information.
more »
« less
A Predictive Analytics Approach for Nursing Home Hurricane Evacuation
Whether to evacuate a nursing home (NH) or shelter in place in response to the approaching hurricane is one of the most complex and difficult decisions encountered by nursing home administrators. A variety of factors may affect the evacuation decision, including storm and environmental conditions, nursing home characteristics, and the dwelling residents’ health conditions. Successful prediction of evacuation decision is essential to proactively prepare and manage resources to meet the surge in nursing home evacuation demands. In current nursing home emergency preparedness literature, there is a lack of analytical models and studies for nursing home evacuation demand prediction. In this paper, we propose a predictive analytics framework by applying machine learning techniques, integrated with domain knowledge in NH evacuation research, to extract, identify and quantify the effects of relevant factors on NH evacuation from heterogeneous data sources. In particular, storm features are extracted from Geographic Information System (GIS) data to strengthen the prediction accuracy. To further illustrate the proposed work and demonstrate its practical validity, a real-world case study is given to investigate nursing home evacuation in response to recent Hurricane Irma in Florida. The prediction performance among different predictive models are also compared comprehensively.
more »
« less
- Award ID(s):
- 1825725
- NSF-PAR ID:
- 10129144
- Date Published:
- Journal Name:
- Proceedings of the 2019 IISE Annual Conference
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Hurricanes Isaac (2012), Harvey (2017), and Irma (2017) were storms with different geophysical characteristics and track forecast consistencies. Despite the differences, common themes emerged from the perception of track forecasts from evacuees for each storm. Surveys with a mixture of closed and open-ended responses were conducted during the evacuations of each storm while the storm characteristics and decision-making were fresh in the minds of evacuees. Track perception accuracy for each evacuee was quantified by taking the difference between three metrics: perceived track and official track (PT − OT), perceived track and forecast track (PT − FT), and home location and perceived track (HL − PT). Evacuees from Hurricanes Isaac and Harvey displayed a tendency to perceive hurricane tracks as being closer to their home locations than what was forecast to occur and what actually occurred. The large sample collected for Hurricane Irma provided a chance to statistically verify some of the hypotheses generated from Isaac and Harvey. Results from Hurricane Irma confirmed that evacuees expected a storm to be closer to their home locations after controlling for regional influences. Furthermore, participants with greater previous hurricane experience perceived a track as being closer to their home locations, and participants residing in zip codes corresponding with nonmandatory evacuation zones also perceived tracks as being closer to their home locations. These findings suggest that most evacuees from hurricanes in the United States appear to perceive storms as being closer to their home locations than they are and overestimate wind speeds at their homes, thus overestimating the true danger from landfalling hurricanes in many storms.
-
more » « less
Abstract Background Acute neurological complications are some of the leading causes of death and disability in the U.S. The medical professionals that treat patients in this setting are tasked with deciding where (e.g., home or facility), how, and when to discharge these patients. It is important to be able to predict potential patient discharge outcomes as early as possible during the patient’s hospital stay and to know what factors influence the development of discharge planning. This study carried out two parallel experiments: A multi-class outcome (patient discharge targets of ‘home’, ‘nursing facility’, ‘rehab’, ‘death’) and binary class outcome (‘home’ vs. ‘non-home’). The goal of this study is to develop early predictive models for each experiment exploring which patient characteristics and clinical variables significantly influence discharge planning of patients based on the data that are available only within 24 h of their hospital admission.
Method Our methodology centers around building and training five different machine learning models followed by testing and tuning those models to find the best-suited predictor for each experiment with a dataset of 5,245 adult patients with neurological conditions taken from the eICU-CRD database.
Results The results of this study show XGBoost to be the most effective model for predicting between four common discharge outcomes of ‘home’, ‘nursing facility’, ‘rehab’, and ‘death’, with 71% average c-statistic. The XGBoost model was also the best-performer in the binary outcome experiment with a c-statistic of 76%. This article also explores the accuracy, reliability, and interpretability of the best performing models in each experiment by identifying and analyzing the features that are most impactful to the predictions.
Conclusions The acceptable accuracy and interpretability of the predictive models based on early admission data suggests that the models can be used in a suggestive context to help guide healthcare providers in efforts of planning effective and equitable discharge recommendations.
-
Abstract An integrated storm surge modeling and traffic analysis were conducted in this study to assess the effectiveness of hurricane evacuations through a case study of Hurricane Irma. The Category 5 hurricane in 2017 caused a record evacuation with an estimated 6.8 million people relocating statewide in Florida. The Advanced Circulation (ADCIRC) model was applied to simulate storm tides during the hurricane event. Model validations indicated that simulated pressures, winds, and storm surge compared well with observations. Model simulated storm tides and winds were used to estimate the area affected by Hurricane Irma. Results showed that the storm surge and strong wind mainly affected coastal counties in south-west Florida. Only moderate storm tides (maximum about 2.5 m) and maximum wind speed about 115 mph were shown in both model simulations and Federal Emergency Management Agency (FEMA) post-hurricane assessment near the area of hurricane landfall. Storm surges did not rise to the 100-year flood elevation level. The maximum wind was much below the design wind speed of 150–170 mph (Category 5) as defined in Florida Building Code (FBC) for south Florida coastal areas. Compared with the total population of about 2.25 million in the six coastal counties affected by storm surge and Category 1–3 wind, the statewide evacuation of approximately 6.8 million people was found to be an over-evacuation due mainly to the uncertainty of hurricane path, which shifted from south-east to south-west Florida. The uncertainty of hurricane tracks made it difficult to predict the appropriate storm surge inundation zone for evacuation. Traffic data were used to analyze the evacuation traffic patterns. In south-east Florida, evacuation traffic started 4 days before the hurricane’s arrival. However, the hurricane path shifted and eventually landed in south-west Florida, which caused a high level of evacuation traffic in south-west Florida. Over-evacuation caused Evacuation Traffic Index ( ETI ) to increase to 200% above normal conditions in some sections of highways, which reduced the effectiveness of evacuation. Results from this study show that evacuation efficiency can be improved in the future by more accurate hurricane forecasting, better public awareness of real-time storm surge and wind as well as integrated storm surge and evacuation modeling for quick response to the uncertainty of hurricane forecasting.more » « less
-
more » « less
Hurricane-induced storm surge and flooding often lead to the closures of evacuation routes, which can be disruptive for the victims trying to leave the impacted region. This problem becomes even more challenging when we consider the impact of sea level rise that happens due to global warming and other climate-related factors. As such, hurricane-induced storm surge elevations would increase nonlinearly when sea level rise lifts, flooding access to highways and bridge entrances, thereby reducing accessibility for affected census block groups to evacuate to hurricane shelters during hurricane landfall. This happened with the Category 5 Hurricane Michael which swept the east coast of Northwest Florida with long-lasting damage and impact on local communities and infrastructure. In this paper, we propose an integrated methodology that utilizes both sea level rise (SLR) scenario-informed storm surge simulations and floating catchment area models built in Geographical Information Systems (GIS). First, we set up sea level rise scenarios of 0, 0.5, 1, and 1.5 m with a focus on Hurricane Michael’s impact that led to the development of storm surge models. Second, these storm surge simulation outputs are fed into ArcGIS and floating catchment area-based scenarios are created to study the accessibility of shelters. Findings indicate that rural areas lost accessibility faster than urban areas due to a variety of factors including shelter distributions, and roadway closures as spatial accessibility to shelters for offshore populations was rapidly diminishing. We also observed that as inundation level increases, urban census block groups that are closer to the shelters get extremely high accessibility scores through FCA calculations compared to the other block groups. Results of this study could guide and help revise existing strategies for designing emergency response plans and update resilience action policies.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
