Better manage your greenhouses through monitoring to deliver yield optimization.

The solution

Farmers need to monitor all of the environmental characteristics of their greenhouses that have an effect on crop yield and timing, and to optimize those factors in order to maximize yield, so it’s critical for the solution to ensure that the right technologies and processes are put in place to capture accurate information in real-time.

Defining what data to collect is critical
In order to create the solution so that the information can be acted upon to deliver the required yield optimization, we started by identifying the key data required. In this solution, this included:

1.  Room temperature
2.  Humidity
3.  CO₂ levels
4.  Soil temperature and moisture
5.  Lights status (on/off)
6.  Nutrient injection volume and timing
7.  Water flow rates

Initial goals of the solution
The first goal of the AI + IoT solution was to connect with the proprietary greenhouse SCADA so that data would be collected consistently and reliably, ensuring data quality and integrity. This would then provide the following outcomes:

1.  The ability to monitor real-time data received from the SCADA via a web-based and mobile system
2.  Ensure device management of the SCADA was set in place
3.  Define business logic to the application in-order to meet the greenhouse growers business objectives
4.  Provide alarm and alert notifications via email or SMS messages when there was communication downtime
5.  Start collecting enough historical data to enable the ability to test different logic to predict yield
6.  Providing real-time SMS notification when environmental thresholds aren’t not met and there is risk for for reduced yield
7.  Test the application, making sure all of the above goals are met, based on the below solution architecture

Before setting the solution live, we tested four critical aspects of the solution:

Security
The Rayven AI + IoT platform is built with security as a top priority and our proprietary security architecture ensures that data is secure at all points of the environment.

The solution includes data encryption in transit from device-to-cloud, as well as device authentication; security (Bearer) tokens; SSL, AES and RSA encryption; as well as additional device security checks done via automated polling.

Connectivity
In order to retrieve the data, we integrated MODBUS to the greenhouse advanced control hardware management system, enabling us to retrieve over 100 data points every 30 seconds from the control hardware management system. In addition we connected to additional sensors in the greenhouse which weren’t controlled via the control hardware management system, like door sensors. All of this information is then sent directly to the Rayven cloud IoT platform

Data integrity
Once data started flowing from the control hardware management system and the sensors, the first task was to translate some of the MODBUS tag codes into a readable format, which meant creating custom logic translators to the code. Then, we also created sophisticated case logic in the Rayven codeless work flow to visualize the large variety of translated data and validate it against what was being seen on the local greenhouse system in real-time.

Industrial data science
The objective of exploratory data analysis was to observe trends in the data and provide insights into what environmental factors may effect optimized yield:

1.  Create an algorithm that defines optimal growth patterns
2.  Create alerts when specific environmental settings are effecting yield
3.  Compare greenhouse rooms to identify parameters that may effect yield
4.  Forecast yield based on current environmental settings

What’s next?

We are continuing to collect and visualize the insights that are coming through and continuing improve our forecasting results. We will soon be expanding the solution to our greenhouses and sites to further compound the yield optimization benefits across the organization.