Innovation Spring 2026

“

The robot’s ability to move around, collect data, and independently process the information is the main innovation distinguishing Kim’s work. It’s grounded in a significant industry need: high-precision EP sensors can cost tens of thousands of dollars, making it cost prohibitive to buy these sensors for each row or plant. Nourish Labs, a precision fertilizer and irrigation company, is now working with Kim to deploy and commercialize advanced sensing technology across farms. “Technological development from engineers is important, but their adoption is more valuable than anything else,” Kim said. “Building the space between engineers and growers is important.” Most recently, Kim’s research group has been developing a more precise sensor that minimizes plant stress by probing crops with microneedles. “We’ve been talking to our customers, and growers are excited about the potential that this type of technology could have,” said Nourish Labs co-founder and CEO Blake Ponuick. “For the industry, in my view, this type of development could be a game changer.” Ponuick’s co-founder Justin Valmont, who entered the industry as a hydroponic cultivator himself, sees the development of precise fertilization and irrigation informed by real-time data as a solution to a challenge he has long faced as a grower. “Being a cultivator myself, I know that a single crop loss could be catastrophic for the business,” he said. “Better sensing technology is a form of crop insurance with some very high potential.” Ultimately, Nourish Labs is looking to develop systems that predict water needs before stress becomes visible on leaves, enabling more precise and efficient irrigation. “Every single day, these plants are growing one to two percent,” said Valmont. “If we can get data directly from the plant – almost like an x-ray, or an ultrasound – and proactively react to what it's telling us, we're able to feed the plants with an optimized fertilizer recipe.” AI to the rescue Sensing alone does not improve agricultural outcomes. “AI is the backbone that connects sensing to action,” said Kim. At the beginning of the process, data points are transformed into representations suitable for learning. Systems must then identify individual biological entities, separate them from dense clusters, and explain how they change over time. CNNs form the backbone of most modern agricultural vision systems because they learn spatial features directly from data.

Before water stress, nutrient stress, or pathogen attacks become visible on the leaf through RGB cameras, there may already be electrophysiological signals. Filling that gap with early detection is the key thing we want to do.

Dr. Woo Soo Kim , P.Eng. Mechatronic Systems Engineering, SFU

”

SUPPLYING PRODUCTS COMMUNITIES ARE BUILT ON

Call us to discuss your project requirements with our experienced sales, technical marketing , engineering and production teams.

Innovation Spring 2026

19