Inside the Emerging Role of XR in Cannabis Growing

Imagine entering a cannabis grow room and immediately seeing which plants are approaching water stress, where humidity is drifting outside the preferred range, and which section of the canopy deserves closer inspection. Instead of consulting several dashboards, the relevant information appears beside the plants themselves.

That is the practical promise of extended reality. A recent review published in Engineering¹ examines how virtual reality, augmented reality, and mixed reality are being tested across agriculture. The reviewed applications range from crop diagnosis and machinery guidance to livestock monitoring, aquaculture, remote operations, and worker training.

Cannabis occupies only a small part of the review, but one of its most relevant examples involves a virtual reality-based digital twin for medicinal cannabis production. More importantly, many of the wider findings apply unusually well to cannabis. Commercial cultivation already depends on controlled environments, closely monitored plants, valuable harvests, and large volumes of sensor data. XR could make that information easier to use while growers are standing inside the cultivation space.

Extended Reality Could Give Grow Rooms a Digital Layer

Extended reality, commonly shortened to XR, includes several related technologies. Augmented reality adds digital information to a view of the physical world. Virtual reality places the user inside a simulated environment. Mixed reality allows digital objects to remain anchored within and interact with physical surroundings.

These formats would not perform identical jobs inside a cannabis facility. AR could support daily crop work by displaying readings, warnings, or instructions near the affected plants. VR could recreate an entire cultivation room for planning and training. MR could eventually allow workers to interact with spatially anchored models of irrigation lines, airflow patterns, lighting zones, or plant canopies.

In each case, XR is primarily an interface. Cameras, sensors, and AI still collect and interpret the information. The role of XR is to present the result where it becomes useful.

Seeing Plant Data Where the Plant Is Growing

Cannabis facilities can produce an abundance of environmental data. Temperature, relative humidity, light intensity, carbon dioxide, substrate moisture, electrical conductivity, and irrigation activity may all be monitored. Depending on the system, growers might need to move between environmental controls, fertigation software, cultivation records, and visual inspections to understand what is happening.

An AR interface could organize this information spatially. A worker looking toward one bench might see its recent irrigation activity and root-zone readings. Another part of the room could be marked because humidity remained elevated after lights-out. A plant identified by computer vision as abnormal could receive a visible label directing the worker to inspect it.

This would extend developments already discussed in MyCannabis coverage of how AI is reshaping cannabis cultivation and processing. AI can detect patterns and generate predictions, but its recommendation still needs to reach the correct person at the correct point in the workflow. XR could connect those analytical systems with the physical crop.

The review describes this process as a progression from perception to analysis, visualization, and guidance. Sensors or cameras observe conditions. Software interprets the data. XR displays the finding, and the user determines the appropriate response.

This human role remains important. A coloured overlay should prompt inspection rather than replace it. Cannabis symptoms can have overlapping causes, and an algorithm could mistake irrigation stress for a nutrient problem or overlook a developing issue hidden beneath the canopy. Growers would still need to confirm what the system reports.

Computer Vision Could Make Crop Scouting More Focused

The agricultural systems reviewed by the researchers include tools for detecting crop maturity, classifying disease, counting pests, estimating yield, and directing workers toward particular fruit. Although most were developed for crops other than cannabis, they demonstrate how XR can combine computer vision with hands-on crop work.

One AR-guided grape-thinning system allowed untrained workers to achieve operational quality that was, on average, 8.18% higher than that of experienced farmers under the study conditions. Another system used AR glasses and deep learning to count rice planthoppers, reducing the required labor by half while improving survey efficiency and accuracy.

A cannabis adaptation might direct scouts toward leaves with unusual discolouration, sections of canopy showing inconsistent development, or areas where insect activity is suspected. It could also help standardize how employees inspect large facilities by ensuring that priority zones are not missed.

Harvest assessment presents another possibility. MyCannabis has previously examined how AI could help cannabis growers determine when to harvest. If imaging systems become capable of producing reliable plant-level recommendations, an AR display could show which plants or zones have reached a target condition rather than requiring a grower to compare separate images, laboratory results, and room maps.

This remains a future-facing application. The review repeatedly cautions that many agricultural XR systems have been tested on individual crops, in controlled conditions, or with limited participants. A model that performs well in one room or cultivar cannot be assumed to generalize across genetics, lighting systems, growth stages, or cultivation methods.

Digital Twins Could Let Cultivators Test Before They Change

A digital twin is a virtual representation of a real system that can be updated with information from its physical counterpart. In cultivation, that could mean modelling a room, its equipment, environmental conditions, and potentially its crop development.

The review specifically highlights a virtual reality-based digital twin involving pharmaceutical cannabis. That case study explored a virtual model designed to support the simulation and management of medicinal cannabis production.

For cultivators, the appeal is straightforward. Changes to airflow, lighting, irrigation, room layout, or operating procedures can carry financial risk when tested on a live crop. A sufficiently accurate digital twin could allow teams to examine possible changes virtually before implementing them.

Potential uses could include:

• Reviewing room layouts before moving equipment
• Visualizing airflow or environmental differences between zones
• Training employees on procedures before they enter production areas
• Rehearsing responses to equipment failures or abnormal conditions
• Comparing cultivation strategies without immediately risking plants

The word “accurate” is crucial. A visually convincing room is not necessarily a useful twin. The model must reflect the conditions that matter to the crop, and its predictions need to be tested against real production results. Otherwise, VR becomes a presentation tool rather than a dependable cultivation system.

Training May Be the Most Practical Early Use

Commercial cannabis operations often need employees to follow consistent procedures for sanitation, scouting, plant handling, equipment use, and room access. Traditional training can be difficult because cultivation spaces are active production environments. Bringing inexperienced workers into those rooms can interrupt work or create avoidable biosecurity and crop-handling risks.

VR could provide a controlled setting where employees practise procedures repeatedly before performing them around live plants. A trainee could learn the sequence for entering a clean production area, responding to an environmental alarm, or inspecting equipment without affecting an operating facility.

Unlike crop diagnosis, this application does not require an algorithm to recognize every possible plant condition in real time. The environment and lesson can be designed in advance. That makes training a more achievable near-term use than an AR system expected to diagnose multiple cultivars under changing conditions.

XR could also preserve operational knowledge. Experienced cultivators often rely on observations that are difficult to communicate through written procedures alone. Immersive training could record where to look, what sequence to follow, and how to move through a task. It would not capture every element of experience, but it could make more of that knowledge transferable.

Why Grow Rooms May Suit XR Better Than Open Fields

The review identifies direct sunlight, dust, rain, temperature variation, plant movement, weak connectivity, and irregular terrain as major obstacles to agricultural XR. Indoor cannabis cultivation removes some of those variables.

Grow rooms offer controlled lighting, defined work areas, nearby power, and more reliable networking. Plants are arranged systematically, and production systems already collect digital information. High crop value may also make it easier to justify specialized technology when it prevents losses or improves consistency.

However, indoor cultivation creates its own problems. High humidity can affect hardware, headsets may be uncomfortable during long shifts, and devices must fit sanitation protocols. Camera-equipped systems could record workers continuously, raising legitimate questions about surveillance and consent. Cultivation data may also reveal commercially sensitive information about genetics, yields, operating methods, or facility performance.

Before adopting XR, operators would need clear answers about who owns the data, where it is processed, how long it is retained, and whether technology providers can use it for other purposes.

XR Still Has to Earn Its Place in Cannabis Cultivation

The potential is substantial, but cannabis growers do not need another expensive platform that produces more information without improving the crop.

The strongest XR tools will likely begin with one well-defined problem. A facility might use VR to train workers, AR to guide maintenance, or a digital twin to test airflow changes. Success should be measured through practical outcomes such as reduced training time, fewer missed inspections, lower crop losses, faster maintenance, or more consistent execution.

Only after those narrow applications prove useful should operators attempt to create an all-encompassing virtual grow room.

For now, XR is best understood as an emerging way to bring digital cultivation systems closer to the plants and people they are meant to support. Cannabis offers favourable conditions for experimentation, but a convincing display is not enough. The technology will matter when it helps growers see a problem sooner, train a worker more safely, or make a better decision without adding unnecessary complexity.

References:

¹ Liu, T., Miao, Z., Yang, S. X., Zhou, J., Gong, L., Zhang, B., Liu, C., & Zhao, C. (2026). Extended reality as a new farming tool for enhancing smart agriculture and precision farming. Engineering. https://doi.org/10.1016/j.eng.2026.08.021