Grow Solutions plans to develop AI-based crop imagery to measure crop health and enhance AeroPod hardware and firmware package
Grow Solutions (GRSO) has announced plans to develop artificial intelligence (AI) that can automatically measure crop health, detect growth patterns and adjust the environmental settings in its AeroPod-based vertical farms.
The company believes that the enhancements will enable its network of smart farms to accelerate crop quality, gain higher yield while reducing the costs with the need for minimal staff with specialised crop knowledge.
GRSO said that it is working to internalise critical grow data and generate its intellectual property (IP) that builds on its first-generation AeroPod developed by Farm Boys Design.
The AI being developed is expected to enhance AeroPod’s hardware and firmware package to continuously monitor the growing environment while 16 variables are maintained in their pre-set ranges including air and water temperatures, macro- and micro-nutrient levels, humidity levels and lighting.
The upgraded package will enhance GRSO’s support for over 65 crops
The package upgraded with AI will integrate crop imagery into the AeroPod sensor platform to continue advancing yield and quality of each of the over 65 supported crops.
The imagery can quantify yield, measure crop quality through colour and leaf texture and diagnose different stresses experienced by the plants without human intervention.
Grow Solutions CEO and president Chad Fischl said: “Remote crop sensing will take GRSO’s smart farms to the next level. Machine learning will give every farmer across our network the benefits of a highly-skilled crop advisor without the time and labour costs.”
GRSO is aligning with partners to enhance its AeroPod’s data-driven smart capabilities.
The company has partnered with ag-tech company Prairie Robotics which previously developed self-driving farm equipment and sold the technology to DOT Technology, which was recently acquired by Raven Autonomy.
It has also partnered with the University of Regina’s Electronic Systems Engineering professor Abdul Bais who will supervise an intern to develop machine learning models to maximise crop yield and quality using AeroPod crop imagery.