An official website of the United States government
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
Predicting Hurricane Evacuation Decisions with Interpretable Machine Learning Methods
Abstract Facing the escalating effects of climate change, it is critical to improve the prediction and understanding of the hurricane evacuation decisions made by households in order to enhance emergency management. Current studies in this area often have relied on psychology-driven linear models, which frequently exhibited limitations in practice. The present study proposed a novel interpretable machine learning approach to predict household-level evacuation decisions by leveraging easily accessible demographic and resource-related predictors, compared to existing models that mainly rely on psychological factors. An enhanced logistic regression model (that is, an interpretable machine learning approach) was developed for accurate predictions by automatically accounting for nonlinearities and interactions (that is, univariate and bivariate threshold effects). Specifically, nonlinearity and interaction detection were enabled by low-depth decision trees, which offer transparent model structure and robustness. A survey dataset collected in the aftermath of Hurricanes Katrina and Rita, two of the most intense tropical storms of the last two decades, was employed to test the new methodology. The findings show that, when predicting the households’ evacuation decisions, the enhanced logistic regression model outperformed previous linear models in terms of both model fit and predictive capability. This outcome suggests that our proposed methodology could provide a new tool and framework for emergency management authorities to improve the prediction of evacuation traffic demands in a timely and accurate manner.
more »
« less
- PAR ID:
- 10585686
- Publisher / Repository:
- Springer
- Date Published:
- Journal Name:
- International Journal of Disaster Risk Science
- Volume:
- 15
- Issue:
- 1
- ISSN:
- 2095-0055
- Page Range / eLocation ID:
- 134 to 148
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Against the backdrop of the ever-evolving IT industry, this comparative study explores the differences among various project management methods, highlighting key distinctions between Agile and traditional approaches by evaluating the benefits of Agile and the drawbacks of not adopting agile methods. Agile practices have gained recognition for their adaptability and efficiency, in addressing dynamic industry demands. Our multifaceted approach, which examines the pros and cons of Agile methodologies across various industries employs different machine learning algorithms—logistic regression, linear regression, and decision tree regressor. The study quantitatively measures Agile’s impact compared to other methodologies using prediction probabilities, classifications, confusion metrics, R-squared, and Mean Squared Error (MSE) for performance analysis. Results highlight that linear regression outperforms other models with 71% accuracy and 82% precision. These findings offer valuable insights into understanding Agile’s impact on IT industries, encouraging further exploration and refinements to make informed decisions on project management strategies and fostering future research to enhance IT project success rates.more » « less
-
The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on two definitions of interpretability that have been introduced in the machine learning literature: simulatability (a user's ability to run a model on a given input) and "what if" local explainability (a user's ability to correctly determine a model's prediction under local changes to the input, given knowledge of the model's original prediction). Through a user study with 1,000 participants, we test whether humans perform well on tasks that mimic the definitions of simulatability and "what if" local explainability on models that are typically considered locally interpretable. To track the relative interpretability of models, we employ a simple metric, the runtime operation count on the simulatability task. We find evidence that as the number of operations increases, participant accuracy on the local interpretability tasks decreases. In addition, this evidence is consistent with the common intuition that decision trees and logistic regression models are interpretable and are more interpretable than neural networks.more » « less
-
To mitigate the devastating impacts of hurricanes on people’s lives, communities, and societal infrastructures, disaster management would benefit considerably from a detailed understanding of evacuation, including the socio-demographics of the populations that evacuate, or remain, down to disaggregated geographic levels such as local neighborhoods. A detailed household evacuation prediction model for local neighborhoods requires both a robust household evacuation decision model and individual household data for small geographic units. This paper utilizes a recently pub- lished statistical meta-analysis for the first requirement and then conducts a rigorous population synthesis procedure for the second. Our model produces predicted non-evacuation rates for all US Census block groups for the Tampa-St. Petersburg-Clearwater Metropolitan Statistical Area for a Hurricane Irma-like storm along with their socio-demographic and hurricane impact risk profiles. Our model predictions indicate that non- evacuation rates are likely to vary considerably, even across neighboring block groups, driven by the variability in evacuation risk profiles. Our results also demonstrate how different predictors may come to the fore in influencing non-evacuation in different block groups, and that predictors which may have an outsize impact on individual household evacuation decisions, such as Race, are not necessarily associated with the greatest differentials in non-evacuation rates when we aggregate households to block group level and above. Our research is intended to provide a framework for the design of hurricane evacuation prediction tools that could be used in disaster management.more » « less
-
Abstract Timely, accurate, and reliable information is essential for decision-makers, emergency managers, and infrastructure operators during flood events. This study demonstrates that a proposed machine learning model,MaxFloodCast, trained on physics-based hydrodynamic simulations in Harris County, offers efficient and interpretable flood inundation depth predictions. Achieving an average$$R^2$$ of 0.949 and a Root Mean Square Error of 0.61 ft (0.19 m) on unseen data, it proves reliable in forecasting peak flood inundation depths. Validated against Hurricane Harvey and Tropical Storm Imelda,MaxFloodCastshows the potential in supporting near-time floodplain management and emergency operations. The model’s interpretability aids decision-makers in offering critical information to inform flood mitigation strategies, to prioritize areas with critical facilities and to examine how rainfall in other watersheds influences flood exposure in one area. TheMaxFloodCastmodel enables accurate and interpretable inundation depth predictions while significantly reducing computational time, thereby supporting emergency response efforts and flood risk management more effectively.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/s13753-024-00541-1
