{"id":2518,"date":"2025-07-24T11:23:56","date_gmt":"2025-07-24T10:23:56","guid":{"rendered":"https:\/\/www.digital-solutions.uk\/?p=2518"},"modified":"2025-07-24T11:25:22","modified_gmt":"2025-07-24T10:25:22","slug":"geoai-overcoming-the-hype-and-avoiding-hallucinations","status":"publish","type":"post","link":"https:\/\/www.digital-solutions.uk\/index.php\/geoai-overcoming-the-hype-and-avoiding-hallucinations\/","title":{"rendered":"GeoAI: Overcoming the Hype and Avoiding Hallucinations"},"content":{"rendered":"\n

As artificial intelligence (AI) continues to reshape how we interact with data, the geospatial world is no exception. At this year\u2019s GEO Business event, Professor Richard Kingston, Director of the NERC Digital Solutions Programme delivered a compelling talk titled \u201cGeoAI: Overcoming the Hype and Avoiding Hallucinations<\/a><\/em>\u201d addressing the rising enthusiasm around GeoAI while offering a crucial counterbalance looking at the risks of AI-driven misinformation or in AI terms, hallucination.<\/p>\n\n\n\n

The Hype versus Reality of GeoAI<\/h4>\n\n\n\n

Many organisations are racing to deploy GeoAI tools, enticed by their ability to uncover insights, generate maps, and respond to complex queries. But as pointed out in the talk, building something does not guarantee it will be used, or trusted. The notion of \u201cbuild it and they will come\u201d does not always lie true and it is essential that what you build is driven by user needs.<\/p>\n\n\n\n

Users don\u2019t just want access to data\u2014they want services. They want apps, dashboards, storytelling tools, and collaborative platforms. Most importantly, they want answers they can trust.<\/p>\n\n\n\n

When AI Hallucinates the Landscape<\/h4>\n\n\n\n

A striking example comes from a query to a Large Language Model (LLM). When asked about wildfire risk in the Thames Estuary, the LLM confidently produced a plausible but entirely inaccurate paragraph about peatland wildfire risk in a mostly urban, low-lying tidal wetland. This \u2018hallucinated\u2019 output stated:<\/p>\n\n\n\n

\u201cRecent climate models suggest that rising summer temperatures and declining soil moisture in the Thames Estuary could increase the risk of peatland wildfires by 2080. These events pose a serious threat to the region\u2019s carbon sinks and biodiversity corridors, particularly in areas of unmanaged wetland.\u201d<\/em><\/p>\n\n\n\n

What this illustrates is a textbook GeoAI hallucination: the model stitched together convincing sounding terms including \u201cpeatland,\u201d \u201cwildfire,\u201d \u201cclimate change\u201d despite no scientific or spatial basis for the claim as the Thames Estuary is mostly urban, salt marsh, and mudflats where wildfires in low-lying tidal wetlands are extremely rare.<\/p>\n\n\n\n

Grounding AI with Retrieval-Augmented Generation (RAG)<\/h4>\n\n\n\n

To counter these hallucinations in the DSH we have deploying what is called a RAG approach (Retrieval-Augmented Generation). This approach ensures the LLM does not invent answers from scratch, instead, it retrieves factual, relevant knowledge from trusted datasets before generating responses. In the case of DSH we have built a database of all the NERC metadata which the AI tool uses to respond to queries by the user. Constraining your search to your own data is the most important take-away here. When we ask the same question using Claude-AI and our RAG approach connected to the NERC meta-data database the LLM correctly retrieves information about salt marsh erosion under sea level rise, grounded in the following data:<\/p>\n\n\n\n