Series · 4 parts · August 2026
Building a City Digital Twin
I set out to model a city, and started where most people start - with the whole thing. This series is what the literature, the real data, and my own experiments did to that ambition, and what is left standing that is actually worth building.
The arc, in one breath
Part 1 writes down the mental model I began with - a city as entities on geography, flows between them, and senses that watch both - then records the six corrections the literature and the data forced on it: senses that report at speeds seven orders of magnitude apart, sensors that are a shadow of the state rather than a mirror of it, people who re-optimise rather than drift like particles, single runs that hide their own uncertainty, governance that is the controller of the loop rather than another entity inside it, and an output that should compare futures instead of forecasting one. Every correction pushes the same direction - toward a smaller, scoped twin. Part 2 puts that argument on trial against the record: a decade of government everything-twins that each converged to a scoped survivable core - a geometry platform, a flood demonstrator, a framework document - the scoped products that shipped and stayed shipped, and a US$2 billion foundation-model company running the same experiment today, whose independent validators have already drawn the envelope around its scoped part. It closes on the capability nobody has built: a spatial twin coupled to a council’s money. Part 3 stops arguing and goes to stand inside one of the twins the record vindicated: the NSW Spatial Digital Twin. On census night it takes the portal up on its “add your own data” button and pushes a census-night headcount down onto individual land parcels, a grain the Bureau of Statistics never publishes at, which turns out to be a lesson in what a scoped twin will and will not tell you. Part 4 stops reading and starts building: a scoped twin made by hand, with OpenStreetMap roads cropped by osmium and run through SUMO, put to one concrete question - how long the Victoria Park precinct takes to clear when 63,000 people leave the Brisbane 2032 stadium at once, and where it chokes. Thirteen real runs are baked into an interactive map, with the assumptions and the sanity checks set out beside them.
Part 1 · The Model · August 2026
My mental model of a city: what held up, what didn't
A city is entities, flows and senses - a state-space model, as it turns out, and that skeleton survives. Six of the assumptions resting on it do not. The corrections, and the ideas from control engineering, econometrics and meteorology that forced them.
Read Part 1 →Part 2 · The Track Record · August 2026
“Let's simulate everything” experiments: what worked & what didn't
The everything-twins governments funded over the last decade, the scoped twins that outlived them, and a US$2 billion foundation-model company re-running the same experiment. What survives is scoped - and one scoped capability is still missing.
Read Part 2 →Part 3 · The Side Quest · August 2026
Exploring the official NSW Digital Twin portal
A census-night accident turned into a small experiment: layering 2021 census-night counts onto individual land parcels of the NSW Spatial Digital Twin. The census stops at the SA1, so reaching the parcel meant borrowing detail from the cadastre itself, in two browser consoles and no desktop tooling.
Read Part 3 →Part 4 · Hands On With SUMO · August 2026
Brisbane 2032 egress from Victoria Park: hands on experiments with SUMO
A scoped twin built by hand: OpenStreetMap roads cropped with osmium and run through SUMO, asking how long the Victoria Park precinct takes to clear after 63,000 people leave at once. Thirteen real runs baked into an interactive map, with the assumptions and the sanity checks laid out beside it.
Read Part 4 →