The Problem -  Understanding your plants moisture requirements and optimising irrigations through the crop lifecycle is hard. Moisture sensors provide VWC percentage data (Volumetric Water Content) . But its hard to use this arbitrary number to perfect your irrigation scheme.

The hypothesis - Many growers have invested in soil moisture sensors but the data provided by the system is not easy to understand or useable to make effective change to irrigation timing and volumes. Growers need a simpler representation of the information with an empirical target to aim for when optimising irrigations at any crop stage.

The Solution - We are excited to introduce an AI-driven algorithm that automatically calibrates and normalises data to the maximum water-holding capacity of your plants. This means you can easily see when you have over-irrigated or when you are approaching your optimum dry-back points. To explain this further see the output example here.

The Experiment - We believe the AI enriched moisture data from #moiSteer is a game changer in the battle to optimise irrigations. But we want to know what you think. We want to test our hypothesis before further enhancing the system to fully unlock the power of the algorithm. This would include live integrations with existing sensors and/or deploying our own moisture sensor network. Ultimately converging on fully automated precision irrigation.