Smart technology for a specialist in interior planting

Data-driven plant management and smart plant sensors.

Our client brings interior planting to a higher level with smart technology. Together with NiftyBits, they developed a data-driven solution with sensors and a cloud platform. This results in more efficient plant management, healthier plants, and less unnecessary maintenance.

Contact Us

Facts & Results

  • Strategic Pilot: successful rollout of a demonstration dashboard for the maintenance of office plants at ASML.
  • ASML Innovation Booster: Selected for the acceleration program of the tech giant.
  • 'Digital Twin' of every plant: On-site visits are only needed when a plant’s digital twin shows that action is required.

Technology

IoT Sensors

Predictive Maintenance

Smart Gardening

SaaS Portal

Proof of Concept

Validation of smart systems for healthy office plants

Our client transforms traditional plant maintenance into a high-tech service. The problem associated with traditional plant management is often twofold: plants die due to dehydration or overwatering, while at the same time there are unnecessary service trips made. The challenge was to develop a system that not only keeps the plants alive, but also fully digitalizes the management process.

Measuring is knowing: The sensor grid

NiftyBits has converted this vision into a Proof of Concept that can be applied to both existing plants as well as new green projects. The universal plug-and-play sensors are placed in the plant pots to measure the actual water usage. This data is synchronized in real-time with a custom-made cloud solution. Through an intuitive dashboard, the user gets instant insights into the status of each plant, its exact location within the building and its maintenance history. To ensure optimal plant health, the software is equipped with an intelligent alarm system that sends a notification as soon as a plant reaches the ‘danger zone’.

Predictive Maintenance & AI

The core of the innovation in this pilot is the intelligence behind the data: the ‘machine learning’. The system is trained to recognize usage patterns of specific plant pots based on plant location within the building, the season, and weather conditions. This makes it possible to accurately predict when a plant pot needs to be refilled, before levels become critical. During this test phase, we are optimizing this algorithm to generate maintenance routes based on actual needs. Routes for the plant care workers are automatically generated, reducing CO2 emissions and lowering costs of operation.

Plant Monitor DashboardPlant Monitor sketchWithered plant
NiftyBits About Us Portfolio Expertise Contact
NL EN