Wencong Cui

WebGIS development requires consistency, yet agentic AI often fails due to LLM context constraints, forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual‐helix governance framework reframing these as structural problems rather than capacity deficits. Using a 3‐track architecture (Knowledge, Behavior, Skills) and a persistent knowledge graph, it stabilizes execution by externalizing facts and enforcing protocols. Validation shows a governed agent successfully refactored a legacy WebGIS codebase (reducing cyclomatic complexity and improving maintainability), roughly halved trial‐to‐trial output variance relative to static prompting in a controlled experiment, and prevented common infodemic mapping errors in a 5‐condition COVID‐19 cartography ablation study. Operationalized via the open‐source AgentLoom toolkit, this externalized governance provides the stability necessary for production‐level geospatial engineering.

Severe depression is shaped by complex interactions between public health crises and socioeconomic conditions, yet the spatial and temporal dynamics of these factors remain underexplored. This study investigates the impact of COVID-19 case rates, vaccination rates, and socioeconomic factors on severe depression rates across 1470 counties in the contiguous USA in 2021 and 2022. We combined Ordinary Least Squares (OLS) regression with Multiscale Geographically Weighted Regression (MGWR) to capture both global associations and local geographic variability. Results show that higher COVID-19 case rates in 2021 were associated with increased rates of severe depression in 2022, while higher vaccination rates during the same period were associated with decreased rates of severe depression. However, these associations weakened when using 2022 data, suggesting a temporal lag in the impact on mental health. MGWR analyses revealed regional disparities: COVID-19 case rates had a stronger impact in the Midwest, while vaccination benefits were more pronounced on the West Coast. Additional factors, such as unemployment, limited sunlight exposure, and the availability of mental health resources, also influenced outcomes. These findings underscore the importance of temporally and geographically nuanced approaches to public mental health interventions and support the need for region-specific strategies to address mental health disparities in the wake of public health crises.

This paper examines the performance of ChatGPT, a large language model (LLM), in a geographic information systems (GIS) exam. As LLMs like ChatGPT become increasingly prevalent in various domains, including education, it is important to understand their capabilities and limitations in specialized subject areas such as GIS. Human learning of spatial concepts significantly differs from LLM training methodologies. Therefore, this study aims to assess ChatGPT's performance and ability to grasp geospatial concepts by challenging it with a real GIS exam. By analyzing ChatGPT's responses and evaluating its understanding of GIS principles, we gain insights into the potential applications and challenges of LLMs in spatially-oriented fields. We conduct our evaluation with two models, GPT-3.5 and GPT-4, to understand whether general improvements of an LLM translate to improvements in answering questions related to the spatial domain. We find that both GPT variants can pass a balanced, introductory GIS exam, scoring 63.3% (GPT-3.5) and 88.3% (GPT-4), which correspond to grades D and B+ respectively in standard US letter grading scale. In addition, we also identify specific questions and topics where the LLMs struggle to grasp spatial concepts, highlighting the challenges in teaching such topics to these models. Finally, we assess ChatGPT's performance in specific aspects of GIS, including spatial analysis, basic concepts of mapping, and data management. This granular analysis provides further insights into the strengths and weaknesses of ChatGPT's GIS literacy. This research contributes to the ongoing dialogue on the integration of AI models in education and can provide guidance for educators, researchers, and practitioners seeking to leverage LLMs in GIS. By focusing on specific questions or concepts that pose difficulties for the LLM, this study addresses the nuances of teaching spatial concepts to AI models and offers potential avenues for improvement in spatial literacy within future iterations of LLMs.