No abstract

The built environment affects mental health outcomes, but this relationship is less studied and understood. This article proposes a novel multi-level scenario-based predictive analytics framework (MSPAF) to explore the complex relationships between community mental health outcomes and the built environment conditions. The MSPAF combines rigorously validated interpretable machine learning algorithms and scenario-based sensitivity analysis to test various hypotheses on how the built environment impacts community mental health outcomes across the largest metropolitan areas in the US. Among other findings, our results suggest that declining socio-economic conditions of the built environment (e.g., poverty, low income, unemployment, decreased access to public health insurance) are significantly associated with increased reported mental health disorders. Similarly, physical conditions of the built environment (e.g., increased housing vacancies and increased travel costs) are significantly associated with increased reported mental health disorders. However, this positive relationship between the physical conditions of the built environment and mental health outcomes does not hold across all the metropolitan areas, suggesting a mixed effect of the built environment’s physical conditions on community mental health. We conclude by highlighting future opportunities of incorporating other variables and datasets into the MSPAF framework to test additional hypotheses on how the built environment impacts community mental health.

No abstract

No abstract

Wildfire spread is a stochastic phenomenon driven by a multitude of geophysical and anthropogenic factors. In this study, we propose a spatiotemporal data-driven risk assessment framework to understand the effect of various geophysical/anthropogenic factors on wildfire size, leveraging a systematic machine learning approach. We apply this framework in the state of California—the most vulnerable US state to wildfires. Using county-level annual wildfire data from 2001-2015, and various geophysical (e.g., landcover, wind, surface temperature) and anthropogenic features (e.g., population density, housing type), we trained, tested, and validated a suite of ensemble tree-based learning algorithms to identify and evaluate the key factors associated with wildfire size. The extreme gradient boosting (XGBoost) algorithm outperformed all the other models in terms of generalization performance, categorization of important features, and risk performance. We found that standard deviations of meteorological variables with long-tailed distributions play a key role in predicting wildfire size. Specifically, the top ten factors associated with high risk of larger wildfires include larger standard deviations of surface temperature and vapor pressure deficit, higher wind gust, more grassy and barren land covers, lower night-time boundary layer height and higher population density. Our proposed risk assessment framework will help federal/state decision-makers to adequately plan for wildfire risk mitigation and resource allocation strategies.