International Journal of Geographical Information Science最新文献

Rural-urban classification schemes are frequently used in ecological studies of population health. However, the algorithms used to produce these classifications as well as their underlying assumptions may not match their intended use in health research. Here, we focus on the spatial distribution of features of the physical environment that are related to health - such as healthcare - to examine the extent to which eight classification schemes capture the heterogeneous context of rural places. We further explore how well rural-urban classifications distinguish between different types of rural places by comparing rural Tribal reservations with other rural areas in the American southwest. Because health services and infrastructure are often distributed through state and federal programs to underserved populations in rural areas, this approach speaks to the broader political implications in how rural communities are defined and represented. Results indicate that rural-urban classifications do not adequately reflect heterogeneous contexts within and across rural places. We advocate for more appropriate population health models that explain contextual differences in the relationship between health and place.

Understanding the relationship between risk factors, geospatial patterns, and disease outcomes is essential in health geography research. These relationships can inform the implementation of healthcare and public health strategies to improve health outcomes. To accurately uncover such complex relationships, it is necessary to have a predictive model capable of integrating both health variables and spatial information to forecast health outcomes, along with a tool to interpret and reveal the patterns identified by this model. We developed a Spatial Counterfactual Explainable Deep Learning model (SpaCE), comprising a spatially explicit health outcome predictor and a prototype-guided counterfactual explanation. The SpaCE model unifies geospatial and health variables to improve predictions and generates hypothetical examples with minimal changes but opposite outcomes. Using these counterfactuals, SpaCE assesses the impact of each variable in different spatial contexts. We evaluated the model for predicting cardiac arrest survival outcomes. With a 0.682 AUCROC score, the SpaCE exceeds baseline models by 10.2%. Further analysis also reveals that the geospatial context significantly affects how various risk factors affect the survival outcomes of patients. Overall, the SpaCE model significantly improves predictive accuracy and explainability. It provides targeted interventions at both individual and geographic levels, and the cardiac arrest case study shows its high adaptability to various disease scenarios.

Social issues, AI, and climate change are just a few of the disruptive focuses impacting science. The field of GIScience is well positioned to respond to accelerating disruptions due to the interdisciplinary nature of the field and the ability of GIScience approaches to be used in support of decision-making. This manuscript aims to start a conversation that will establish a research agenda for GIScience in an age of disruptions. We outline three guiding principles: (1) focusing on the relevance and real-world impact of research, (2) adopting systems-based thinking and contextual approaches and (3) emphasizing inclusive practices. We then outline prioritized research areas organized by what topics are important focal areas (Data and Infrastructure, Artificial Intelligence, and Causality and Generalizability), and what approaches to science we should be attentive to (Impactful Open Science, Collaborative and Convergent Science, and through Diverse Participation and Partnerships). We conclude with a call to increase impact by balancing slow science with practical and policy-oriented research. We also recognize that while broad adoption of spatial approaches is a signal of GIScience's success, we should continue to work together to advance core knowledge centered on spatial thinking and approaches.

The surge in the availability of spatial big data has sparked increased interest in researching human mobility patterns. Despite this, discovering human mobility patterns from such spatial big data and assessing the similarity between patterns remains a formidable challenge. This study introduces two novel methods: the Time-Informed pattern mining (TiPam) method for frequent pattern mining and a Time-Aware Longest Common Subsequence (T-LCS) algorithm for assessing similarity between time-conscious sequences. Leveraging these innovative algorithms, our research introduces an analytical framework for analyzing human mobility patterns at both individual and aggregated levels. As a case study, this proposed workflow is applied to examine the daily mobility patterns of voluntary mobile phone users in Kampala, Uganda. The 135 participants are found in four distinct groups labeled with distinct mobility properties for users in each group: "stay-at-home," "unoccupied," "education-oriented," and "work-oriented." The results effectively showcase the efficiency of the framework and the novel techniques employed. The framework's versatility extends to human mobility studies with other forms of data and across various research fields.