YKYushim Kim

Yushim Kim

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yushim Kim has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Administrative Decision-Making with Generative AI: The Challenge of Epistemic Boundedness

    by Yushim Kim, Jieun Kim, Taeuk Kim, Hee-Chan Cho

    This essay reframes administrative decision-making in the generative AI era by identifying how epistemic constraints rather than traditional information constraints shape administrative rationality. We introduce the concept of epistemic boundedness: the inability to verify the veracity and foundations of available information. Large language models (LLMs) exemplify this challenge through their opaque reasoning processes and tendency to produce plausible but inaccurate outputs. We propose sociotechnical strategies to mitigate these constraints, including retrieval-augmented generation (RAG) and institutionalized verification procedures for AI-generated content. By implementing these complementary strategies, government agencies can take advantage of LLMs’ capabilities while preserving the integrity and accountability of administrative decision-making processes.


  • Urban Neighborhoods with Greater Access but Less Use of Nearby Parks: Case of Los Angeles, California

    by Youngjae Won, Ji Eun Kim, Yushim Kim, Elizabeth A. Corley

    We examine the relationship between urban residents’ access and use of nearby green spaces, recognizing that this link can vary across neighborhoods. Our study integrates park data from the Trust for Public Land and population mobility data from SafeGraph for the Los Angeles urban area. Using geographically weighted regression (GWR) and multiscale GWR (MGWR), we identify neighborhoods with high park accessibility but significantly lower usage. A post hoc analysis of MGWR results shows that neighborhoods with good park proximity but low usage tend to have fewer White residents and lower educational attainment than those with higher usage. Similarly, neighborhoods with ample park acreage but underutilization are characterized by younger populations, fewer households with children, fewer female residents, and lower educational attainment compared to neighborhoods with higher park usage. These findings suggest that physical access alone may not ensure park usage, particularly among marginalized communities. We discuss implications for urban planners and decision-makers.


  • Connecting park access and use data for equitable environmental planning

    by Yushim Kim, Jieun Kim, Youngjae Won, Jake Nelson, Michelle Stuhlmacher

    To ensure equity in the provisioning of urban green spaces, both how green spaces are distributed (i.e., access) as well as whether residents are utilizing them (i.e., use) needs to be considered simultaneously. Yet, few green space equity studies have considered both access and use together, and the fragmented literature provides only a partial view of each. This disconnection partly lies in challenges in integrating disparate “access” and “use” datasets. Using the Phoenix-Mesa urbanized area in Arizona as a case study, we present the conceptual and data challenges we have encountered when linking park access using the Trust for Public Land dataset with park usage measured from large scale human mobility datasets (SafeGraph, now Advan). We then show how the choices of data integration can affect findings of green space equity in the study area. In this paper, we enumerate the data and analytical issues encountered, illustrate research opportunities that the data integration provides for green space equity analyses, and discuss the implications of our findings for equitable environmental planning and policy.


  • Institutional shifts and landscape change: the impact of the Período Especial on Cuba’s land system architecture

    by Michelle Stuhlmacher, B.L. Turner, Amy E. Frazier, Yushim Kim, Jessica Leffel

    Formal institutions, especially policies, play a key role in land system change. Compared to other drivers of change, however, the impact of policies on landscapes is under-addressed in land system science, in part due to difficulties isolating their effect on longitudinal land change. We address this gap by examining land system architecture changes in Cuba brought about by the 1991 collapse of the Soviet Union and the resulting economic crisis: El Período Especial (‘Special Period’). Employing a satellite imagery time-series alongside a review of policy documents, we identify statistically significant land system changes linked to the era’s institutional shifts. We find that concentrated policy efforts to transform agriculture and protect forests corresponded to considerable changes for agriculture but minimal changes to forests. Some changes resulting from the institutional shifts of the Período Especial became visible in the landscape as soon as a few years, while others took decades to manifest.