Business-driven digital twins in horticulture

Horticulture is becoming increasingly data-driven and makes increasing use of innovative digital technologies, such as cloud computing, the Internet of Things, machine learning and robotics, writes Cor Verdouw of Mprise Agriware.

That was very clear at the Greentech in Amsterdam. For example, all but one of the nominated innovations were digital data solutions. Berry, a strawberry harvesting robot, won the concept prize. Other nominees were a sensor network of digital insect traps (Trap-Eye), an autonomous growing system for indoor farming (Gronos) and a software tool to calculate CO2 food prints (HortiFoodPrint calculator). Many digital solutions were also promoted on the stands. A small selection: greenhouse drones (PATS, Corvus), tomato harvesting robots (the winner of the Robot Challenge GRoW, and EGA Matic), sensors for measuring plant stress (Vivent) and leaf temperature (Sigrow), detection systems for digital phenotyping (Hiphen), yield predictions based on computer vision (YieldComputer, ecoation), autonomous cultivation systems (Blue Radix, ioCrops, Koidra) and much more.

Growing remotely with Digital Twins
These technological developments are radically changing horticultural production. Instead of experienced growers monitoring the condition of the crop themselves (‘walking around management’), cultivation decisions can be based on real-time data and intelligent algorithms.

Growers can monitor and control their business operations remotely, made possible by so-called Digital Twins. Such a virtual twin is a digital copy of, for example, a greenhouse that is linked to the real greenhouse and is continuously updated.

A Digital Twin can be enriched with smart algorithms and machines or robots can be connected. For example, growers are warned via the Digital Twin if there are (expected) problems and they can check the situation in the greenhouse from their desk or smartphone by digitally looking at the plants or machines involved. They can also use the Digital Twin to digitally simulate the effects of interventions in advance, then take the best action remotely and check afterwards whether the problem has actually been solved.

What are Digital Twins?
The term Digital Twin was introduced by NASA in 2012 to “mirror” the exact state of a real space vehicle during a mission. So essentially a Digital Twin is a virtual, digital representation of a physical object attached to it in (near) real time. This view can be simple, for example an overview of a greenhouse with live data. It can also be a realistic environment, where you can, for example, virtually walk through the greenhouse and inspect 3D plants. But all Digital Twins have these five characteristics:

  • Timeliness: a Digital Twin represents its physical twin in (near) real-time, changes in the physical object are identified and synchronized (immediately), and vice versa;
  • Fidelity: The reliability and security of a Digital Twin should be unquestionable so that you can blindly rely on Digital Twins for decision making;
  • Integration: a Digital Twin integrates different types of data from the physical object and ensures an unambiguous representation;
    Intelligence: Digital Twins not only reflect object data, but also use algorithms to describe, analyze and predict the behavior of the physical counterpart;
  • Complexity: Digital Twins can mirror different physical objects at different levels of granularity, ranging in horticulture from the genetics of individual plants to a company or value chain.

Digital Twins in horticulture are currently focusing on cultivation
Although the term Digital Twin seems to be a new buzzword, I see it as a further development of smart, data-driven horticulture. In practice, Digital Twins already exist, although they are often not called that yet. A literature study by one of my students at Wageningen University shows that most are still relatively ‘basic’ Digital Twins that focus on remote monitoring and control. However, there will be more ‘advanced’ Digital Twins, such as for (near) real-time predictions.

Another conclusion of the research is that Digital Twins in horticulture now mainly focus on cultivation management in the greenhouse in the field of climate, energy and lighting. There is still little research into Digital Twins for individual plants, although that level of detail is important for breeding, for example. Completely absent from the review were Digital Twins for the business processes and the performance of horticultural companies as a whole.

Integrated Digital Twins for business and cultivation
However, Digital Twins are not an end in themselves, but a means to improve business results. For the future, therefore, I envision a layered Digital Twin that combines the company, the cultivation and even the individual plants. The starting point would be a management cockpit with the actual and expected business performance, such as lead times, product quality, waste, cost price and delivery reliability.

These indicators combine different data from different sources, including ERP systems, automation in the greenhouse or in the field and external data. Smart algorithms will enable the simulation of expected performance, for example through demand forecasting based on artificial intelligence. One can zoom in on the details for specific business processes, locations, varieties, production batches, etc.

For the cultivation process, you zoom in on, for example, the Digital Twin of a greenhouse, whose expected yield is lower than planned. In this digital greenhouse, the grower checks the climate and other cultivation conditions of the parties concerned. They can also view the physiological characteristics of the plant (e.g. stress) and even the genetic profile in the Digital Twin of a reference plant in these lots.

The various Digital Twins support this analysis with smart decision support tools. These tools advise a grower about the measures to be taken, for example the use of 8,000 extra predatory mites against spider mites in compartments A and B of greenhouse Z. After approval by the grower, the Digital Twin instructs a drone to target the exact number of predatory mites in the right place. places.

Incidentally, the Greenhouse Digital Twin will autonomously control most crops on the basis of predetermined standards. This allows growers to focus on exceptions and the business side of cultivation.

No ‘layered’ Digital Twins without integrated business software
The virtualization of horticulture with Digital Twins now seems to be gaining momentum and will have a major impact on productivity, efficiency, quality and sustainability. In my opinion, the successful Autonomous Greenhouse Challenge is very exemplary. The participating teams control the cultivation in their compartment completely remotely on the basis of sensor data and smart algorithms.

This year’s winner’s net profit (lettuce) was almost 30% higher than the peer group of experienced growers. In fact, last year (cherry tomatoes) all teams performed significantly better and the winner’s net profit was more than twice as high!

Digital Twins can also capture the knowledge of experienced horticultural experts and thus contribute to tackling the scarcity of green personnel. In addition, Digital Twins are a promising tool for setting up, scaling up and managing international production sites.

I expect that Digital Twins will become increasingly embedded in business operations in the near future. As a result, they are more likely to consist of multiple interconnected levels from company to factory. However, this is only possible if the underlying data is correct.

For a ‘layered’ Digital Twin from farmer to plant, this means not only cultivation and planting data, but also company data and external data. A well-integrated farm management system that works seamlessly with automation in the greenhouse and in the field is therefore a crucial precondition.

Leave a Comment

%d bloggers like this: