Hanlin Zhou

Crime geographers are attentive to how the spatial characteristics of the environment affect criminal behaviors. Recently, scholars have found that aside from physical and social attributes, the perception of the environment, such as safety perception, is also associated with crime occurrence. However, perceived liveliness, a visual perceptual proxy for potential routine activity settings that are closely linked to routine activity theory and crime pattern theory, is rarely explored in prior research. This study examines the association between perceived liveliness and street thefts in the City of Cincinnati, the United States. The liveliness perception scores are derived from street view imagery using a support vector machine model trained on the MIT Place Pulse V2 crowdsourcing image survey. Negative binomial regression models are used to test the relationships between perceived liveliness and street theft, with social and physical environmental attributes controlled. Results show that perceived liveliness significantly improves model performance and is positively associated with street theft. This study provides the first evidence that perceived liveliness helps explain crimes. The positive relationship between perceived liveliness of the built environment and crime adds a new dimension to the routine activity theory and the crime pattern theory. It also offers a scalable and cost-effective measure that can assist urban planners and law enforcement in identifying potential theft hotspots using readily available street view imagery.

Daily nighttime light (NTL) images are widely used to map power outages and recovery, but clouds and quality screening leave gaps. We examined what NASA Black Marble data show about the February 2021 Winter Storm Uri outage in Harris County, Texas. When only high-quality retrievals were used, 16 February was the only usable night during the outage, and the next were 19 to 21 February. On 16 February, 5112 of 13,846 developed pixels (37%) were below half their pre-storm brightness, and 92% of those with an observed return were lit by 21 February. Return dates between these nights are unobservable. Recovery dates from a detector-based workflow depend on smoothing, persistence and aggregation choices; in a controlled experiment with known recovery dates and flag-0 observations only, an unsmoothed rule requiring three consecutive calendar nights has a median detection delay of 12 to 15 days. Compared with 20 ordinary clear nights, 16 February dimming was far more extensive and clustered. However, the estimated average total impact of the Social Vulnerability Index was 10.6 percentage points of reference radiance (95% interval −32.0 to 49.8), within the range estimated on ten ordinary pre-storm nights (−31.9 to 26.8). Single-night community comparisons need an ordinary-night baseline.

Winter Storm Uri (February 2021) caused the largest power grid failure in Texas history, with extensive outages in the state's most populous Harris County. This study integrates NASA Black Marble VNP46A2 nighttime light (NTL) observations with the CDC Social Vulnerability Index (SVI) to characterize post-storm recovery across 1,070 census tracts. Recovery was defined as the first day tract-level NTL reached at least 90% of its pre-storm baseline for three consecutive days. Contrary to the expectation that vulnerable communities recover more slowly, spatial regression revealed a weak, statistically significant negative association between SVI and recovery time (β = −0.556, p = 0.050), with spatial dependence also significant (ρ ≈ 0.47). Local Indicators of Spatial Autocorrelation identified significant clusters of slow recovery in lower-SVI suburban areas and fast recovery in higher-SVI urban neighborhoods. This association was sensitive to the recovery definition, reversing signs under longer persistence requirements. The spatial organization of urban infrastructure, rather than vulnerability alone, may plausibly explain these patterns, though not directly testable with available data. These findings caution against assuming a universal vulnerability–recovery relationship in infrastructure disasters and highlight the sensitivity of nighttime-light-based equity assessments to how recovery is operationally defined.

Traditional air pollution exposure assessment relies on sparse monitoring networks, leading to significant spatiotemporal gaps and exposure misclassification. Geospatial Artificial Intelligence addresses these limitations by integrating multisource data with advanced algorithms to generate high‐resolution, seamless pollution maps. This review particularly highlights GeoAI's role in enabling the paradigm shift from static to dynamic, person‐centric exposure assessment, providing the first comprehensive synthesis of technical challenges and emerging solutions critical for real‐world implementation. Core applications include high‐resolution pollution mapping, dynamic exposure estimation and health impact assessment, environmental justice analysis, and air quality forecasting and early warning systems. We discuss significant challenges in data management, modeling methodology, and implementation, alongside potential solutions including explainable AI and uncertainty quantification. Ultimately, GeoAI drives a fundamental transformation from static, place‐centric assessments to dynamic, person‐centric models, enabling more precise and equitable environmental health research and governance.