Anderson CloudNova builds high-throughput simulation and modelling infrastructure for climate research labs, observational astronomy, and the increasingly indistinguishable space between them.
Constellation is a single distributed runtime. The modules below are how you talk to it, but they all see the same data, the same provenance, the same compute budget.
GPU-accelerated simulation primitives for radiative transfer, fluid dynamics, and orbital mechanics, composable into experiment graphs.
Pipeline for raw observational data: ingest, align, calibrate, and version. Built around an immutable, content-addressed asset store.
Closed-loop experimentation. Define a hypothesis, let Nova plan runs against your budget, and review only the results worth your time.
We've grown by one product line per year. Each one had a research partner who paid us to figure it out with them, and then got first dibs on using it.
Two engineers and a postdoc, spun out of a JPL simulation team. First contract: a regional climate model.
First production simulation runtime. Adopted by three university labs in the same quarter.
Partnered with a southern-hemisphere observatory to ingest 8 PB of legacy data into the asset store.
Three modules unified into one runtime. Beta opens to non-academic partners.
If your problem fits inside a dashboard, you don't need us. If it spills over the edge, into petabytes, into multi-decade simulations, into wavelengths you can't see, write to orbit@cloudnova.systems.