Urban farming, automated. Monitor, control, and optimise growing conditions from your phone.

Easygrow is an AgriTech platform for growing crops in urban areas using a hydroponics system, also known as vertical farming. Hydroponics is a method of growing plants without soil using dissolved nutrients in water, forming part of the technology-driven 'farm to table movement'.

In the Easygrow container, vegetables are grown vertically with sensors managing an efficient nutrient and watering system. Light can also be manipulated for optimal, weather-independent growth, enabling urban farmers to produce lettuce in various types, sizes, and flavors (such as wasabi or vanilla-flavored lettuce) in just two weeks.

Elements developed the mobile app and website and integrated the IoT technology to operate the system and monitor and adjust growth progress.

Data-driven urban farming with Machine Learning & IoT

The platform revolves entirely around data, keeping detailed records of pH and EC values per crop and per growth phase. Hardware sensors collect this data, which is analyzed and processed by Machine Learning technology to continuously improve growth recipes.

Mobile control and crop management

With the mobile app, growers have complete control over the hydroponics system and crops. Users receive notifications and can monitor, control, and adjust their vegetable and herb cultivation directly from their phone.

Full hardware and software integration

Elements fully integrated the physical hardware with the software platform, installing and configuring all hardware sensors and providing necessary operational support.

Why Flutter for an IoT app?

Flutter gave us a single codebase for iOS and Android, which matters for a B2B product where the device split across users is unpredictable. More importantly, Flutter's performance characteristics are well-suited to a dashboard app that updates continuously with live sensor data, without the jitter that can appear in hybrid frameworks under heavy real-time data load.

Elements installed and configured all the physical hardware sensors, establishing a direct connection between physical units and the software ecosystem. By capturing live pH and EC values from hardware sensors, the team implemented Machine Learning workflows to analyze crop data, continually refining the growth formulas while supporting the ongoing operation of the platform.