AI-Controlled Crop Harvester Could Have Big Implications for Energy Sustainability
Physicists at the Technical University of Denmark have developed the world’s smallest fruit harvester controlled by artificial intelligence (AI), which enables a harvester measuring just a few microns.
Kaare Hartvig Jensen, Associate Professor at DTU Physics, set out to reduce the need for harvesting, transporting, and processing crops for the production of biofuels, pharmaceuticals, and other products. The substances that are extracted are called plant metabolites, and the new method eliminates the need for chemical and mechanical processes.
The research was published in Plant Physiology.
Plant metabolites have a wide range of crucial chemicals, and those like the malaria drug artemisinin have therapeutic properties. Others like natural rubber or biofuel from tree sap have mechanical properties.
Most plant metabolites are isolated in individual cells, and the method of extracting the metabolites is important given that the procedure impacts product purity and yield. The extraction process involves grinding, centrifugation, and chemical treatment using solvents, which results in pollution that leads to the high financial and environmental processing costs.
“All the substances are produced and stored inside individual cells in the plant. That’s where you have to go in if you want the pure material. When you harvest the whole plant or separate the fruit from the branches, you also harvest a whole lot of tissue that doesn’t contain the substance you’re interested in,” says Kaare Hartvig Jensen.
“So there are two perspectives to it. If you want to extract the pure substances, you need to do it cell by cell. And when you can do that, as we’ve shown, you don’t have to harvest the plant. Then you can put the little robot on and it can work without damaging the plant,” Kaare continues.
As of right now, the harvester is being used with plants and leaves, but the team sees it working on a larger scale in the future. If everything works as planned, the new approach could create a new source of biomass and establish a new area of sustainable energy production.
A potential application in the future could be to use the technology to tap energy from trees.
“In the forests of northern Canada and Russia, there are spruce forests with around 740 billion trees that are completely untouched. That’s about 25% of the total number of trees on the planet. By developing this technology, we can tap trees for sugar and make biofuel without chopping down or damaging the trees,” explains Kaare.
The harvester looks for cells in fruit and leaves that are 100 microns in diameter, and the top of the needle is about 10 microns in diameter.
Magnus Valdemar Paludan is a PhD student at DTU Physics who created the system of image analysis, image recognition, and robot control.
“It’s all done with a microscope camera. To begin with, I manually marked pixels on the microscopy images showing the cells that the robot will harvest. That information can be used to train a computer to find similar cells in new images,” Magnus says.
AI and Machine Learning
The new technology relies on machine learning and the GoogLeNet pre-existing neural network. The network is able to recognize microscopic structures and perform advanced image analysis.
“We used a technique called transfer learning, where you use the existing neural network’s ability to recognize different objects in an image. By showing the computer a number of new images with the manually marked cells, we succeeded in adjusting the network’s parameters so it recognizes the microscopic metabolite-rich cells,” says Magnus.
“The harvester can then go in and take a picture of the leaf with the microscope camera, run it through the software, and recognize the cells it needs to harvest. Next, it can extract the chemicals automatically using a microrobot, while the rest of the plant remains undisturbed,” explains Magnus.
- Eugene Chan, MD, Chairman & Co-Founder & of Abpro – Interview Series
- Iktos Secures €15.5 Million in Funding to Accelerate AI Drug Discovery
- AI in Phishing: Do Attackers or Defenders Benefit More?
- Building a Recommendation System Using Machine Learning
- AI in Medicine Must Prioritize the Other ‘A’: Augmentation