Key Takeaways:
- Source.ag has announced a next-generation AI-powered Harvest Forecast model for tomato growers, currently in phased rollout.
- Mean forecast accuracy at the three-week horizon has improved by 33% compared to the previous model generation.
- The share of cultivations with forecasts more than 20% off target has declined by 25%, while severe forecast outliers have been reduced by 50%.
- Several data processes that previously required manual input from growers have been automated, reducing operational burden.
- Full deployment to all tomato customers is expected in the coming months, with a broader AI transformation of the platform planned.
Source.ag Advances AI Forecasting Platform for Greenhouse Tomato Growers
Source.ag, a data and AI platform for professional greenhouse horticulture, has announced a significant upgrade to its AI-powered Harvest Forecast model for tomatoes. The next-generation model is currently live with an initial group of growers, with a broader rollout planned in the coming weeks.
Measurable Gains in Forecast Performance
The updated model delivers notable improvements across key accuracy metrics. At the three-week forecast horizon, mean accuracy has increased by 33% compared to the previous generation. The proportion of cultivations where forecasts deviated by more than 20% from actual results has declined by 25%. Severe outliers — cases where the model produced significant misses — have been reduced by 50%.
“The most tangible change for growers is how much less the model asks of them,” said Sebastiaan Vermeulen, Data Scientist at Source.ag. “We've automated several of the data processes that used to require regular manual input, which removes real friction from the grower's week. At the same time, we made a number of changes to how the collected data is used in the new model, leading to substantial improvements in the prediction accuracy. We've now made it easier than ever before to hit harvest commitments, realise a better price, and reduce waste.”
3 Comments