Ride requests appear unevenly across a city and change from one period to the next. A quiet zone can become busy while a neighboring zone empties, leaving drivers in the wrong places if dispatch relies only on the latest request count.
The film shows demand as a moving pattern over city cells. Its forecasting model combines each cell's recent activity with signals from nearby places and earlier times, then predicts where requests are likely to appear next. The comparison with observed demand reveals what is gained by treating location and time together. This matters operationally because vehicle repositioning, staffing, and expected passenger wait all depend on where demand will be, not merely on its citywide total. The displayed map is an explanation of the spatiotemporal idea; a useful forecast would still need to be tested on data beyond the examples used to train it.
Large language models can generate many plausible travel choices, but plausible is not the same as representative of real travelers. In the same choice situation, a human sample and an artificial sample may favor different options. If those differences are ignored, adding more synthetic responses can make a demand model more confident about the wrong behavior.
Watch film
Crashes are infrequent, yet road agencies must decide where to investigate or intervene before the next one occurs. That creates a prediction problem: can the conditions of a road segment help estimate its future crash count? Traffic volume, geometry, and other recorded features may interact in ways a simple straight-line rule misses.
Watch film
A road does not evolve in isolation. Speed on one link can be affected by traffic arriving from upstream, queues spilling back from downstream, and conditions on neighboring links. Forecasting several steps ahead therefore requires more than extending each road's own recent trend.
Watch film