Windborne Systems, a startup founded by Stanford students in 2019, has released its sixth version of the WeatherMesh AI weather forecasting model. The model offers more frequent and accurate predictions than traditional and AI systems used by the European Centre for Medium-Range Weather Forecasting (ECMWF), which is considered the leading provider of weather forecasts. According to the company, WeatherMesh 6 is as accurate five days out as traditional forecasts are the day before, particularly for surface temperature measurements. The model generates forecasts every hour, compared to traditional models that update every six hours. Its resolution is now 3 km in Europe and the continental US, where data quality is highest. Windborne’s CEO, John Dean, noted that the company’s unique combination of model-building and data collection has led to these improvements. The company currently has about 400 balloons in flight, gathering sensor data from 15 global sites. Windborne’s head of AI, Joan Creus-Costa, explained that direct ingestion of data from their balloons and other sources is the key reason for the model’s improvement. The company also added transponders to its balloons to report their location through the ADS-B system, reducing the risk of collisions with aircraft. *Source: [techcrunch](https://techcrunch.com/2026/06/01/this-ai-weather-startup-is-out-forecasting-government-agencies/)*