Jua enters the market with a $2.5M pre-seed investment

Incorporated in Canton Schwyz, Jua is launching a platform that will enable the meteorological industry to produce customised high-resolution weather models which outperform all existing approaches. Along with the product launch, the startup has secured $2.5 million in its pre-seed round led by Promus Ventures.

Besides Promus Ventures, Jua also attracted prominent investors Siraj Khaliq (Co-Founder of the Climate Corporation & former Partner at Atomico), Mehdi Ghissassi (Head of Product at Alphabet-acquired Deepmind), and Session.vc (founded by seasoned entrepreneurs and investors of companies like On Running, Bexio or Nutmeg). Promus Ventures Partner Pierre Festal is also joining the Jua board. The funding will flow into further platform developments.

Founded in 2022 by serial entrepreneurs Andreas Brenner (CEO) and Marvin Gabler (CTO), Jua today employs ten team members at its hubs in Zurich, Berlin and Cape Town. The team has invested more than three years of research and development into creating its proprietary data platform and, among others, training the world’s first global high-resolution weather prediction model. There is currently no global observation or comprehensive model of the Earth’s atmosphere that would allow meteorologists to truly understand the interplay between weather patterns and natural disasters accurately.

Jua’s platform contains one of the largest weather and geospatial data sets. It includes a training infrastructure that enables even non-technical users to customise their models with proprietary data. Running on a 48-hour timescale, Jua’s weather prediction model can predict more than fifteen weather-based parameters, including precipitation, air pressure, wind speed and wind direction. Some regions are covered in up to 250 metres squared resolution, and the model is updated every fifteen minutes, enabling significant improvements in forecasting extreme events.

The new weather model also provides up to 25-times higher spatial resolution and ten-times higher temporal resolution than conventional alternatives. This massive resolution increase is achieved via an end-to-end deep learning approach and tens of millions of sensors compared to the hundreds of thousands of sensors used by current standard models. The model is energy efficient, requiring over a thousand times less computing power than any other numerical weather model.

Jua’s platform is currently being offered to a select number of customers worldwide; however, the startup plans to launch it to a broader audience in early 2023.

Andreas Brenner, Co-founder and CEO of Jua, comments: “We are going to change perceptions of weather prediction forever. Regarding geospatial resolution, temporal resolution and update frequency, our first model already outperforms all existing numerical models by several orders of magnitude. We now enable everyone from small startups to large companies to get access to much better weather data than they have ever seen before.”

(Press release/RAN)