Elements of AI in collaborative projects
Saskatchewan — Ground Truth Agriculture Inc., a pioneering agritech company specializing in real-time grain quality data, has partnered with Saskatchewan Polytechnic's Digital Integration Center of Excellence (DICE) to integrate cutting-edge artificial intelligence. We have fine-tuned the system. The partnership aims to advance an innovative automated grain grading system to provide farmers and buyers with accurate and reliable grain quality information.
“Sask Polytech was the first person we reached out to for support with artificial intelligence and machine learning,” said Divyesh Patel, Chief Operating Officer, Ground Truth Agriculture. “The applied research work that Sask Polytech has completed over the past five to seven years is impressive. Working with the DICE team has been seamless, and we have access to the team's researchers and expertise to help accelerate our award-winning system. We were able to develop it.”
Traditionally, the grading process for determining grain quality relies on assumptions made from a small number of samples, leaving producers with an incomplete understanding of the entire crop. Ground Truth Agriculture has developed a machine learning platform that improves the speed and accuracy of grain quality assessment at harvest and at all points in the grain supply chain. This automated system benefits farmers by providing them with more accurate price information, while also giving buyers a comprehensive understanding of the quality of the grain they are purchasing.
The collaboration between Ground Truth Agriculture and DICE is already showing great results. “The first project we completed in collaboration with DICE was Canadian Western Red Spring wheat, where we used machine learning to identify 50 visual characteristics of this crop,” said Patel. “The DICE team helped build a model that detects visual features, freeing up Ground Truth Agriculture's employees to focus on other important tasks.” Western Red Spring Wheat Project in Canada The two DICE interns who worked were funded by Mitacs.
Building on this success, with support from the Natural Sciences and Engineering Research Council of Canada (NSERC) Applied Research and Development Grant and the Innovation Saskatchewan AgTech Growth Fund, recent graduates of the Sask Polytechnic Computer Science Technology (CST) are now , is working on developing similar technology. Red lentil detection model. By leveraging machine learning and machine vision technology, DICE researchers built a system to grade red lentils by visually identifying diseased or damaged kernels and impurities in a sample. We are supporting.
“DICE researchers complete a lot of the groundwork, which is very time-consuming,” Patel said. “It takes a lot of time and effort to figure out what works and what doesn’t. It’s a good experience for young machine learning engineers interested in the agtech industry. The DICE team They also helped us secure funding to continue this research, which has been very helpful.”
“Our partnership with Ground Truth Agriculture provides great internship opportunities for Sask Polytech students and recent graduates,” said DICE Research Manager Tanya Lung. “DICE interns are exposed to new technologies and gain insight to apply their skills in specialized industries such as agritech.” They delved into aspects such as grain grading, different grain types, and harvest timing. They also worked with the Ground Truth Agriculture team to leverage various computer vision tools and methodologies. ”
Prakher Singh, Ground Truth Agriculture researcher at DICE, said: We are grateful for the offer from DICE and Ground Truth Agriculture. I'm learning every day and collaborating with a very innovative team. ”
Ground Truth Agriculture envisions its system being used in laboratories, farms, elevators, testing labs, and even during international sales on ships and trains. The versatility and reliability of this agricultural technology system make it an invaluable tool for all stakeholders in the grain industry.
“Sask Polytech's intellectual property policies also make it an attractive partner,” Patel added. “The intellectual property of applied research projects is held by industry, which means that Ground Truth Agriculture has full control of the intellectual property of collaborative research projects. This is a great comfort. .”
Once the red lentil visualization work is complete, Ground Truth Agriculture and Sask Polytech look forward to collaborating on more models to visualize the next crop together.
DICE is Saskatchewan's first Technology Access Center (TAC), funded by NSERC and Innovation Saskatchewan. DICE conducts applied research in a variety of areas focused on data manipulation, analysis, storage, transmission, and display. Data is at the core of what we do at DICE. For more information, visit saskpolytech.ca/dice.
