Superfund Map Concept
Introduction
America has over a thousand sites that are so contaminated with toxic matter they have been taken over by the federal government for cleanup, under the CERCLA designation started in 1980, also known as “Superfund sites.” New Jersey, California, and Pennsylvania have the highest concentrations of contaminated sites—all states where my family and I live. These are former and current ports, mines, landfills, factories, sewage treatment plants, power plants, etc. Since in most cases private entities caused the damage, the federal government attempts to get those entities to pay for cleanup costs, but public money is used as a backstop. Because of this, there is extensive documentation on why sites deserve the Superfund designation, inspections, and cleanups, all available to the public, but it is housed in websites designed for those with a Ph.D. and EPA employees, using a long list of jargon and acronyms, coupled with inscrutable visual design, running on high-bandwidth, low-accessibility websites. The information is available, but not realistically accessible, to the public. Moreover, many sites have hundreds of pages of documentation that take hours to comb through even for readers who can understand them.
Meanwhile, our digital maps show places you can either spend money at or drive your car to; preferably both. Besides parks, there is very little information on industrial facilities, much less the hazards they have and continue to pose to public health and the environment. While we understand them as fairly complete indexes of our surroundings, they are indexes of our current commercial surroundings, omitting the infrastructure that will outlast us and the sites that make our lives possible. Previously, I made a small design project (Remapping Our Landscapes) of how sites like mines and power plants could be represented on apps like Apple Maps.
In this project, I shift the focus to the most dangerous, extreme sites, those listed in Superfund’s National Priorities List, and leverage advancements in large language models to not only render statistics, but communicate the gist of the history and status of these sites to the public. I aim to create a tool for connecting with the land around us not as consumers, but as organisms living in an ecosystem we experience, and one which makes it easy to be curious and learn about our surroundings. The web tool shows a satellite map of our areas, highlighting the Superfund sites. On opening one, visitors can read a brief synopsis of the site’s history and present, and ask questions about it. The LLM powering these answers is trained on the documentation published for each Superfund site, stored as vector embeddings, using Retrieval Augmented Generation to provide answers based on per-site documentation and mitigate hallucinations. The interface includes a novel interaction where selecting text in LLM answers allows for branching off new lines of inquiry, allowing visitors to ask wide-ranging questions about the world using this map as a grounding space, physically and digitally.
References
Brown, Toby. 2025. “Beem Demo.” Twitter. https://x.com/gopalkraman/status/1883248138745741750.
While JavaScript has been able to detect text selection for a long time, Brown’s demo at South Park Commons in January is the first time I’ve seen text selection used for initiating follow-up queries to an LLM; apps like Perplexity have long employed lists of suggestions at the end similar to Google, and many AI chat UIs have suggested pills near a query box at the bottom of the screen. The selection allows you to choose any part of the response as a jumping-off point, and could lend itself to asking multiple new questions per answer, instead of having one linear conversation as demonstrated here.
Calma, Justine, and Amelia H. Krales. 2025. “The women who made America's microchips and the children who paid for it.” The Verge. https://www.theverge.com/features/611297/manufacturing-workers-semiconductor-computer-chip-birth-defect.
This article from The Verge re-ignited my interest in Superfund recently. It follows the generation of women that worked in the chip fabrication labs of Silicon Valley in the 1980s, the hazardous materials they worked with, and the generation of children they had with frighteningly high levels of birth defects and developmental disabilities. The article brought to my attention one specific result of Superfund cleanups, land use restrictions, which are oftentimes not followed by future tenants of properties, e.g. building schools or churches over contaminated soil.
Campbell, Lachlan. 2023. “Remapping Our Landscapes.” @lachlanjc/edu. https://edu.lachlanjc.com/2023-05-15_dis_remapping_our_landscapes.
This was my first design project about land and maps, and serves as an intellectual precursor to this project. It began with the simple insight that our digital maps feature landmarks you can 1) drive to or 2) spend money at. Besides our parks, that’s basically all! Industrial hazards, infrastructure, and everything that powers our world—and will outlast us—is not marked, including Superfund sites. This project is about building a map of the inverse, where you can’t click on anywhere that you can spend money at, and focusing exclusively on the land and the hazards.
Crawford, Kate. 2023. “Earth.” In Datapolis: Exploring the Footprint of Data on Our Planet and Beyond, edited by Paul Cournet and Negar S. Bensi. N.p.: Nai010 Publishers.
This essay traces the connection between the tech industry/San Francisco/Silicon Valley and Earth’s land. The section that stuck with me was reminding us how wealth first came to San Francisco through the Gold Rush—a dangerous, polluting, extractive process based on hype and individualism that made certain men wealthy. Connecting with Calma’s article in The Verge, I realized that Silicon Valley has operated on cycles of these factors, from the individualist extraction/pollution of the Gold Rush in the 19th century, to the material manufacturing of chip labs in the 20th, to the digital extraction and environmental consequences of AI development in the 21st. This understanding of technology as rooted in environmental extraction/destruction, and grounding of the “cloud” in the land, is a key factor in my work. This project attempts to justify the destruction of using LLMs to flip the motives for their overuse on their head, plus using technical innovations like caching responses and on-device processing to reduce the pollution that goes into making the project itself.
Jiao, Eddie. 2025. “Common Knowledge Demo.” Twitter. https://x.com/gopalkraman/status/1883248154491166912.
Jiao’s demo, the same night as Toby Brown’s at South Park Commons, shows research prototypes of LLM/infinite canvas experiences designed for documents/reading. While early in their nature and not productized, Jiao’s work is relevant in using LLMs in this more “academic” context of work, instead of directly for profit, as most AI-focused work is these days. His prototypes of branching results and follow-up questions are also inspiring to the interaction design of this project.
Post-Tribune. 2020. “Federal agency shuts down website with interactive map showing pollution sources and Superfund sites.” Chicago Tribune. https://www.chicagotribune.com/2020/01/06/federal-agency-shuts-down-website-with-interactive-map-showing-pollution-sources-and-superfund-sites/.
While the Trump 2.0 administration is doing a rapid takedown of content they largely left online on federal websites in the 1.0 administration, there were internet casualties then as well. This includes TOXMAP, a project to make the Superfund information more easily navigable, which went offline before my research took me to this topic. I hope to make up for this loss with something far more accessible, and that is more of a freeform learning tool than these government database-maps ever are. The current standard tool from the EPA is an ArcGIS map, and states like California have their own specialized tools, but all suffer from high bandwidth requirements, difficult to read typography and visual design, and oftentimes poor accessibility.
Santarsiero, Rachel. 2025. “Disappearing Data: Trump Administration Removing Climate Information from Government Websites | National Security Archive.” National Security Archive. https://nsarchive.gwu.edu/briefing-book/climate-change-transparency-project-foia/2025-02-06/disappearing-data-trump.
The current political climate outlined in this article demonstrates the urgency of the project, as data—data I have argued is already too inaccessible, if available to the American public—is rapidly disappearing from EPA and other environment-related agencies’ websites. While to my knowledge the data this project relies on continues to be available, the National Security Archive’s work in preservation, combined with that of Archive.org and other nonprofit initiatives, could become necessary for documentation related to environmental justice that needs to be part of this project’s LLM training.
Wattenberger, Amelia. 2024. “Fish Eyes.” Amelia Wattenberger. https://wattenberger.com/thoughts/fish-eye.
Wattenberger, an interface researcher/prototyper, writes about LLMs as providing a service to text similar to zooming a map, where different landmarks become revealed or hidden as you zoom—LLMs can keep track of what’s important in text and change the length/level of detail at any level of granularity. This is essentially the concept of ingesting so many source documents and composing high-level summaries of site histories, with the ability to drill into more detail by asking questions: zooming out the map. One of the later visualizations in this piece explores an alternative mechanism to serve the hyperlink, exploding out a handful of cards that reorganize when highlighted words are clicked. While that interaction doesn’t make its way into this project, the concept of highlighting words there’s more information about does.