on 13 Dec 2019 8:39 PM

Vaerens is one of the 6 (six) companies that participated in the AGINFRAplus Data Science Challenge ( It is a company based in the Netherlands that has just started its business activity.

Traditional symbolic programming alone has its limits in its ability to handle a high degree of complexity that comes with growing crops in a controlled environment. Artificial intelligence offers the opportunity to create new solutions for crop cultivation where we use algorithms to analyse and manage the complexity of biological systems.

Vaerens as a startup is specialised to approach horticulture from a perspective of artificial intelligence and cloud computing. Their team is on a mission to build a company that creates new sustainable agriculture technologies on the intersection of data science, computer science, and biology. Key characteristics for their designs are scalability and commercial viability.

They’ve been communicated with horticulturalists, growers, lighting manufacturers, and plant researchers. One of the most common questions faced in controlled environment farming is "what is the best lighting strategy for my crop?". The answer is always the same: it depends.

One has to take into account a variety of factors, including which crop/cultivar one is working with and what type of trait one is trying to affect.

Their approach to offer continuous answers to this question is to build a collection of data-driven algorithms that are capable of predicting how plants will respond to a combination of growth variables and lighting conditions. Using these predictions they compose tailored plant lighting strategies for their clients.

In order for them to be able to do this predictive analysis they focus on doing cost-effective plant data farming. Having the right quality and quantity data is a requirement for getting accurate results. In order to achieve both the right quality and quantity of data required for accurate predictions, they combine publicly available academic data with proprietary tailored data collected through plant data farming.

This is how the plant data farming process works:
I. In collaboration with growers and horticulturists, Vaerens grows crops under strictly controlled circumstances.
II. Imaging and sensory data is harvested from the crops; deep learning analysis is applied.
III. Iterations of farming cycles are optimised by an artificial intelligence-driven tuning strategy.
IV. The harvested data is used to train algorithmic models to make predictions about optimised growth conditions.

Vaerens, in order to power its innovation, is using publicly available data and executes some computationally demanding software algorithms. Moreover, they are using public or commercial cloud services to store and manage their data.

You can visit Vaerens website here

As was the case with all six companies that participated in the competition, it was decided that Vaerensreceives the AGINFRAplus Artificial Intelligence Champion distinction.

This means that this company will be announced as the one of the AGINFRAplus Champions and will be promoted through AGINFRAplus extensive international network through a variety of channels and media. A digital badge will also be provided to Vaerens, which they may use to list this distinction at their web site, pitch deck or other promotional material.



The selected AGINFRA+ Use Cases will illustrate the benefits of applying the Science as a Service approach to pressing research questions from the corresponding research communities.


This community focuses on use cases aim to support the workflow of researchers, intermediaries and business analysts working on crop modelling, crop phenology estimation and yield forecasting, as well as related activities in the area of policy and decision support in food security, farm management advice and related activities.



This community focuses on use cases to support scientists in the multidisciplinary field of risk assessment and emerging risk identification as there is currently a strong need to create new technology-supported solutions that facilitate the knowledge integration processes relevant for these tasks.



This community focuses on use cases related to the high-throughput phenotyping large amount of data which need to be analyzed immediately for decision making. This aims to support phenomics researchers to select plant species and varieties which are the most adapted to specific environments and to global changes.


subscribe to our newsletter

stay updated!