Mapping Responsible AI Workflows for Geospatial Data Science: Developing the I-GUIDE Data Ethics Toolkit

Peter T. Darch, Kyra M. Abrams, Ivan Y. M. Kong

AI workflows in geospatial data science promise substantial societal benefits yet pose persistent challenges of ethical risk, transparency, and reproducibility. Current guidance, ranging from high‑level principles to isolated documentation templates, remains difficult to translate into day‑to‑day research practice, especially for teams operating under tight deadlines. This paper reports the design and early implementation of the I‑GUIDE Data Ethics Toolkit (DET), a suite of lightweight, interoperable tools for users of the NSF-funded Institute for Geospatial Understanding through an Integrative Discovery Environment (I‑GUIDE) platform. Building on a longitudinal, mixed‑methods case study of I‑GUIDE platform users, including surveys, semi‑structured interviews, and sustained participant observation of platform users, we derived six design priorities: usability, anticipatory planning, distributed responsibility, comprehensive coverage, and policy compliance. We then integrated and tailored elements of existing AI and research data lifecycles into an eight‑stage I‑GUIDE Research Lifecycle that anchors the DET. The DET comprises four new tools: (1) Data Cards and (2) Model Cards that capture provenance, bias, and usage constraints; (3) a Research Product Management Plan for project‑level data and model governance; and (4) MEG‑AID, a checklist that assigns, tracks, and audits ethical and reproducibility tasks across the lifecycle. Future work will embed DET into the I-GUIDE cyberinfrastructure to enable features such as automated metadata extraction, bias diagnostics, and coupling of the toolkit with platform‑integrated training modules, thereby lowering administrative burden while making responsible practice a default feature of geospatial AI research.