Help and Support



What is Cloudrun?

Cloudrun is a platform for running custom, on demand, high-resolution weather forecasts. We help businesses, researchers, and other power users of weather data create more valuable weather forecasts at fraction of the cost.

Why run custom weather forecasts?

Publicly available weather models are generalized to large areas such as the entire globe or the continental United States. To cover large areas, public models use coarser resolution, often making them less accurate.

With Cloudrun, you choose the exact forecast region that you need. Cloudrun then automatically determines the model resolution for that region, and runs a custom and optimized forecast. These custom forecasts produce features at finer detail and typically better represent the actual weather. The resolution is scaled with the region size such that a day of forecast completes in approximately one hour of real time.

Who is Cloudrun for?

If you need custom and high-resolution weather forecasts for which you own the data and nobody else can access it, then Cloudrun is for you. The unique feature of Cloudrun is to allow anybody to develop their own numerical weather prediction system, without meteorological expertise or access to expensive supercomputers.

Our target industries include:

  • General weather prediction
  • Renewable energies (solar and wind)
  • Insurance and reinsurance
  • Prediction of electric power usage and power grid loads
  • Mountaineering, sailboat racing, camping, and other outdoor activities
  • Fisheries and agriculture
  • Sports and entertainment events
  • Ski and beach resorts


Do I need meteorology or weather modeling expertise?

No meteorological expertise is necessary to use Cloudrun. To get started, just select the area that you want to use and the start and end time for your forecast, and the forecast will start running immediately.

When will my forecast be ready?

Forecasts typically take about 1 to 1 ½ hours per forecast day to complete. For example, a 5-day forecast will typically take between 5 and 6 hours of real time to complete. You can view the remaining time on the Forecast Dashboard.

What information do I get from my forecasts?

The output data of each forecast provide full 2-dimensional fields of:

  • Temperature
  • Humidity
  • Precipitation (rain, snow, hail)
  • Wind speed and direction
  • Incoming solar radiation
  • Cloud cover
  • And many more!

For efficiency and to be able to provide free cloud storage of your forecast output files, we restrict the output to surface fields only. If you have need for full 3-dimensional (whole atmospheric column) output of any of the model fields, please reach out to us at

Do I own the weather data that I create through Cloudrun?

Yes! All model data are yours to keep. You can use it for your own product, service, consulting, or even re-sell it as is.

What if I want a specific resolution rather than Cloudrun determining my resolution automatically?

Please reach out at and we'll happily create a custom forecast for you.

Can I schedule recurring Forecasts?

Not yet through, but we’re working on it! In the meantime, please contact us and we’ll gladly set up scheduled recurring forecasts for you.


What kind of weather model do you use?

Cloudrun forecasts is currently based on the Weather Research and Forecasting (WRF) model.

WRF is an advanced numerical weather prediction and modeling software suite. It features a non-hydrostatic dynamical solver and a wide array of boundary layer, cloud microphysics, and cumulus parameterization schemes. WRF can run in both global and regional configurations, as well as with storm-following nests for high resolution tropical cyclone predictions.

WRF has been developed by the National Center for Atmospheric Research (NCAR), with significant contributions from the atmospheric research community. It is a registered trademark of the University Corporation for Atmospheric Research.

We also maintain a mirror of the complete WRF source code on GitHub. Check it out!

What WRF version do you support?

Through our new forecast wizard, we run WRF version 4.0.1. We plan to keep updating our model as new versions are released by the WRF development team at NCAR.

In our "expert" mode, where you run the model by uploading your own input files, you can choose between WRF versions 3.8.1, 3.9, and 3.9.1.

Do you plan to support other models?

Yes, we plan to offer ocean circulation and surface wave models, in the future, for ocean current and surf prediction applications. If you are interested in these or other capabilities, plese let us know.

What physics and dynamics options can I use?

If you create your simulation using the Forecast Wizard, you can't directly control physics and dynamics settings, and the Wizard configures your forecast with the settings that are most appropriate for the region and resolution of your forecast. We're constantly working on evaluating and improving the model configuration in the Forecast Wizard mode.

If you set up your simulation by uploading input files, you can use any physics and dynamics options that you would otherwise use when running WRF yourself on your own machine. Our system will do its best to catch any errors or incompatibilities that you may have in your namelist.input file.

Can I run fixed or moving nests?

Yes, you can run either fixed or moving nests if you set up your simulation by uploading input files. The Forecast Wizard currently supports only simulations without nests.

Can I upload my own, custom version of WRF?

Currently, you can only run the official, unmodified WRF releases. If there's enough demand, we'd love to give users the ability to run customized variants of WRF. Please let us know at if this capability is important to you.

Back to top


Do you have a public API for users and developers?

Yes! We have an API for our users to create and access weather forecasts directly. If you'd like to try it, please email us at

What programming languages does your API support?

Our API accepts HTTP requests from any client (for example curl) and we have a Python interface as well. Send as a request if you'd like your favorite language to be supported.

Back to top


Do you use parallel computing for your runs?

Yes, all model runs are done in parallel. If you use the Upload Inputs mode, you will have the choice of 3 to 5 different parallel settings. If you use the Forecast Wizard, we use the optimal parallel configuration that yields shortest compute time.

How does your hardware compare with industry-standard supercomputers?

Our processors are latest generation and typically a few years ahead of industry-standard supercomputers. This is because classic HPC systems are very large and can update hardware only every 3-5 years. For example, DOE's recent system Cori uses Haswell processors from 2014. NASA's largest and fastest supercomputer Pleiades is mostly based on Ivy Bridge processors from 2013, with some Haswell and Broadwell processors. While Cloudrun does not aim to be a replacement for those systems, we do provide much faster and cheaper solution with state-of-the-art hardware and flexibility of the cloud.

Back to top


Do you offer customer support?

We currently offer free email support to all Cloudrun users. You can also reach us by phone at +1 (760) 853-1067, however we do not yet offer dedicated phone support and may not answer every call.

Do you offer scientific support and consulting?

If you need dedicated scientific support and consulting for your weather, wave, or ocean modeling needs, or you want to set up and run WRF on your own system, please reach out at

Back to top

The Cloudrun Team

Who is Cloudrun?

Cloudrun was founded by Milan Curcic and Josh Noe. Milan is a meteorologist and oceanographer with expertise in High Performance Computing (HPC) and Earth system model development. Josh is a computer scientist with expertise in designing and building complex full-stack systems and user interfaces.

How to best reach us?

If you need help with using Cloudrun or experience an issue with the platform, the best way to reach us is by email at, or by phone at +1 (760) 853-1067. Keep in mind that we currently don't offer dedicated phone support. If we don't pick up, please leave a message and we will get back to you as soon as we can.