Amid rising climate-related challenges facing global agriculture, OneSoil partnered with Rainbow Weather to help farmers better predict and manage rainfall-related risks. The collaboration came as extreme precipitation events had increased significantly since the early 2000s, disrupting planting schedules, reducing crop yields, and costing the European agricultural sector an estimated €28 billion annually.

Farmers could already track wind speed and temperature via the 'Virtual Weather Station' OneSoil's existing app. What the collaboration brings is a 'Hyperlocal Precipitation Forecast' feature to the platform. This new layer shows clouds motion and, therefore, predicts rainfall probability and intensity down to a specific four-hour window for exact coordinates, whether it's a particular section of a sunflower field in France or a cornfield in South Africa.

This precision and speed are possible thanks to machine learning models trained to analyze large volumes of radar, satellite, and atmospheric data to detect patterns in how precipitation develops and moves, Alexander Matveenko, co-founder and CEO at Rainbow Weather, explains.

For modern farmers, this ultra-short-term data is financially crucial, CEO at OneSoil Stepan Zulynskyi notes, "Knowing what will happen in the next few hours is more valuable than a general daily forecast." He further explains that operations like fertilizing and chemical spraying are highly sensitive to rain. If an unexpected downpour hits immediately after a tractor completes a pass, thousands of dollars in inputs can wash away, forcing farmers to re-apply chemicals, waste labor, and damage soil health. According to the team, the new feature has already been used by more than 15 000 farmers monthly.

Alexander Matveenko adds that more accurate forecasts can bring new value to farmers given that, over the last few years, weather has become one of the biggest sources of risk in agriculture: "In these conditions, farmers are looking for tools that could help them access granular data on upcoming precipitation, as well as historical data on how much rainfall has already occurred, so they can better plan fieldwork. Rainbow Weather is exactly what they need."

About Rainbow Weather

Rainbow Weather is a next-gen climate tech startup for ultra-accurate short-term forecasts founded in 2021 by Yuriy Melnichek, who previously built AIMatter (acquired by Google), a neural network-based AI platform, as well as the video creation and editing app Vochi (acquired by Pinterest), and fashion marketplace Wanna (acquired by Farfetch), and Alexander Matveenko, a founder of artificial intelligence mapping startup MapData that he sold to Mapbox in 2017. The company has raised a €4.87M ($5.5M) seed funding round, with main investors including Yuri Gurski, founder and president of Flo Health, the first purely digital consumer women's health app to achieve unicorn status. Rainbow Weather's forecasting is available globally, with more than 1 million installs and over 120,000 active users. The company also works with 400 B2B clients sharing its forecasting via API.

In addition, the team runs weatherindex.ai, an open-source tool that evaluates the accuracy of short-term precipitation predictions from providers like AccuWeather, Vaisala, and The Weather Company in real time. It pulls live data from public APIs and compares forecasts with verified airport weather reports using standard metrics such as accuracy and F-score (a measure of predictive performance).