A lab advancing how we access, understand, and act on data about our world.
A public, live-updating catalog of cloud-optimized weather datasets.
Operational skill scores for forecast models, scored against observations.
Forecast files don't arrive all at once — they trickle in over minutes or hours, on a cadence set by whoever produces the model. To stop guessing, we built wxopticon: a tool that watches upstream weather sources and answers two operational questions — when to expect a given dataset, and whether a run is on time relative to how that feed actually behaves.
Arrival monitoring for the weather sources we depend on: when to expect each model run, whether today's run is on time, and a signed webhook the moment data crosses a readiness boundary — live at status.dynamical.org.
Global METAR surface observations, 1940–present, as cloud-native GeoParquet — ground truth for scoring forecasts against what actually happened.