Why farm indoors?

With more of the world’s population moving to cities, indoor farms that grow crops near urban areas in a way that is efficient with space and other resources may be an important way forward. Dramatic improvements in crop yield and operational efficiency can be made by using data (collected for instance by sensors or cameras) to build an increasingly smart plant factory. This plant factory allows us to control the environment for crops to grow more, better-tasting crops in a way that is reproducible. By iteratively automating processes in the farm and increasingly relying on data products, we ensure that this can be done in a way that not only scales to the levels of production needed, but also allows us to use the farm as a testbed for innovation.

Data-driven automation

In this talk, I will outline some relevant processes in running an automated indoor plant factory and the process we use to automate these as we scale. In particular, I will focus on how the Data & AI team works with other teams such as the Agricultural Science, Operations, Supply Chain and Robotics teams.

As an example, I will discuss a recent project, in which the decisions around the environment to grow crop in, where in the vertical farm to place crop, and how to schedule work in the farm were automated. This project touches agriculture, since there may be different ways different crops react to an environment, but also operations and supply chain, since scheduling farm work impacts our ability to work efficiently and manage our product stock. This automation project requires high-quality data, such as yield predictions from computer vision, sensor data that can tell us which positions are suitable for certain crop to grow in, operations data, such as the expected time it takes to complete a task, and other data related to automation.