Premonition Net, A Multi-Timeline Transformer Network Architecture Towards Strawberry Tabletop Yield Forecasting
This addresses yield forecasting for agriculture to improve food security, lower prices, and reduce waste, but it appears incremental as it builds on existing transformer methods with a new architecture.
The paper tackled strawberry yield forecasting by proposing Premonition Net, a multi-timeline transformer network, achieving a testing set RMSE loss of ~0.08 for forecasts 3 weeks ahead.
Yield forecasting is a critical first step necessary for yield optimisation, with important consequences for the broader food supply chain, procurement, price-negotiation, logistics, and supply. However yield forecasting is notoriously difficult, and oft-inaccurate. Premonition Net is a multi-timeline, time sequence ingesting approach towards processing the past, the present, and premonitions of the future. We show how this structure combined with transformers attains critical yield forecasting proficiency towards improving food security, lowering prices, and reducing waste. We find data availability to be a continued difficulty however using our premonition network and our own collected data we attain yield forecasts 3 weeks ahead with a a testing set RMSE loss of ~0.08 across our latest season.