BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.osgeo.org//foss4g-europe-2026//talk//QZN7Q3
BEGIN:VTIMEZONE
TZID:EET
BEGIN:STANDARD
DTSTART:20001029T050000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:EET
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:EEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-europe-2026-QZN7Q3@talks.osgeo.org
DTSTART;TZID=EET:20260630T150000
DTEND;TZID=EET:20260630T153000
DESCRIPTION:The Province of South Holland manages one of the most densely p
 acked\, data-rich regions in Europe. Housing pressure\, nitrogen depositio
 n\, flooding risk\, ageing infrastructure\, biodiversity loss — the ques
 tions are urgent\, and the data to answer them mostly already exists. It's
  public\, it's free\, and almost none of it talks to anything else.\nWe bu
 ilt something to fix that.\nOver the past two years\, we've assembled a sp
 atial data warehouse for Zuid-Holland: an H3 geo-datacube at resolution 9\
 , combining six years of Dutch open datasets — demographics and housing 
 (CBS)\, land use and nature (LGN)\, water quality (IHW/KRW)\, air quality 
 (RIVM)\, ground height (AHN)\, noise exposure\, and accessibility distance
 s. Every dataset on the same hexagonal grid. Every hexagon its own small s
 tory about a patch of land.\nThen we gave it a voice.\nA natural-language 
 assistant — built entirely on open source tools — lets policy advisors
 \, planners\, and analysts ask questions in plain Dutch and get a map back
  in seconds. No SQL. No data wrangling. No waiting for a colleague who kno
 ws which table holds what. "Where did nature expand while population shran
 k between 2018 and 2023?" becomes a map. "Which areas combine flooding ris
 k with high housing pressure and poor accessibility?" becomes a map. Decis
 ions that used to take a week of preparation start with a conversation.\nT
 he stack is fully open: LangGraph for the AI workflow\, DuckDB for query e
 xecution\, FastAPI for the backend\, Deck.gl and MapLibre GL JS for render
 ing. The warehouse itself is built on Delta Lake — a living system\, not
  a static file — designed to grow as new provincial datasets are onboard
 ed.\nThis talk covers the architecture\, the hard-won lessons (LLM halluci
 nations hitting production queries is a fun problem to debug)\, and a live
  demo against the actual provincial data warehouse. We'll show what the he
 xagons reveal about Zuid-Holland that spreadsheets never could — and wha
 t it looks like when a province can finally ask itself the right questions
 .\nAll code is open source. The pattern is replicable. The data is already
  yours.\nStack: H3 · DuckDB · LangGraph · FastAPI · Deck.gl · PDOK ·
  Delta Lake
DTSTAMP:20260605T082527Z
LOCATION:A02
SUMMARY:Asking a Province a Question: LLMs\, H3\, and Open Dutch Geodata - 
 Thijs Oosterhuis
URL:https://talks.osgeo.org/foss4g-europe-2026/talk/QZN7Q3/
END:VEVENT
END:VCALENDAR