Strawberries can be easy to grow – especially, it seems, if you're an algorithm.
When farmers in China competed to grow the fruit with technology including machine learning and artificial intelligence, the machines won, by some margin.
Data scientists produced 196% more strawberries by weight on average compared with traditional farmers.
The technologists also outperformed farmers in terms of return on investment by an average of 75.5%
The inaugural Smart Agriculture Competition was co-organized by Pinduoduo, China's largest agri-focused technology platform, and the China Agricultural University, with the Food and Agriculture Organization of the United Nations as a technical adviser.
Teams of data scientists competed over four months to grow strawberries remotely using Internet of Things technology coupled with artificial intelligence (AI) and machine learning-driven algorithms.
In the competition, the technology teams had the advantage of being able to control temperature and humidity through greenhouse automation, the organizers said. Using technology such as intelligent sensors, they were also more precise at controlling the use of water and nutrients. The traditional farmers had to achieve the same tasks by hand and experience.
One of the teams, Zhi Duo Mei, set up a company to provide its technology to farming cooperatives after it generated a lot of interest during the competition.
The contest helped the traditional farmers and the data scientists better understand each other's work and how they could collaborate to everyone's advantage, the leader of the Zhi Duo Mei team, Cheng Biao, said.
Pinduoduo
Growing potential
Numerous studies show the potential for Fourth Industrial Revolution technologies like AI to boost economic growth and productivity.
By 2035, labour productivity in developed countries could rise by 40% due to the influence of AI, according to analysis from Accenture and Frontier Economics.
Sweden, the US and Japan are expected to see the highest productivity increases.
In its Future of Jobs Report 2020, the World Economic Forum estimates that by 2025, 85 million jobs may be displaced by a shift in the division of labour between humans and machines, while 97 million new roles may emerge that are more adapted to the new division of labour between humans, machines and algorithms.
Emerging technologies including AI and drones will also play a vital role in helping the world recover from COVID-19, according to a separate Forum report compiled with professional services firm Deloitte.
The Global Technology Governance Report 2021 considers some of the most important applications for these technologies – and the governance challenges that should be addressed for these technologies to reach their full potential.
Reprinted with permission of the World Economic Forum. Read the original article.
A new study looked at how California black worms work together to form "worm blobs" in order to model their behavior in moving swarms of simple robots. The "blob" formation, which can range in size from 10 to 50,000 worms, serves to protect the creatures from drying out and withstanding threats like strong heat.
The researchers from Georgia Institute of Technology focused on how thousands of the worms (Lumbriculus variegatus), about a centimeter in length each, can intertwine into an "active matter," which behaves as one. This self-organized shape-shifting blob allows the worms to achieve much more complex outcomes together than they would without getting hitched up.
The work promises to help engineers working on swarm robots to understand and adapt the mechanics of how such blobs behave.
Saad Bhamla, an assistant professor at Georgia Tech's School of Chemical and Biomolecular Engineering, highlighted that being in a group is beneficial to the worms' survival:
"We were curious about why these worms would form these living blobs," said Bhamla. "We have now shown through mathematical models and biological experiments that forming the blobs confers a kind of collective decision-making that enables worms in a larger blob to survive longer against desiccation."
The scientists also showed that the worms in a blob can move together, exhibiting unique collective behavior. The capabilities of the blob are much more than anything the individuals can do on their own. Studying these blobs helps researchers who are looking to transfer the key traits of living systems to ones designed by humans. Swarm robots, in particular, are built around the idea that individual robots must collaborate to be able to engage in complex actions.
Collective worm and robot "blobs" protect individuals, swarm together
The worms were studied closely by the research associate Yasemin Ozkan-Aydi, whose experiments included testing the blob's responsiveness to temperature and light changes and creating a "worm gymnasium", which allowed her to gauge the strength of the worms. To create a worm blob, she took the worms out of water. When they couldn't find the water, they came together in a ball-like blob. The worms would trade off on who would be on the outside of the blob, where most evaporation took place. This allowed the collective to suffer less of an effect from the lack of liquid. The researchers concluded that being in a blob helped the worms survive 10 times longer when being out of water, compared to individual worms.
Georgia Tech research associate Yasemin Ozkan-Aydin holds a smarticle blob as Georgia Tech Assistant Professor Saad Bhamla holds a worm blob.
Credit: Christopher Moore, Georgia Tech
Professor Daniel Goldman, in whose lab these experiments were carried out, pointed to the unexpected smartness of what the worms did.
"They would certainly want to reduce desiccation, but the way in which they would do this is not obvious and points to a kind of collective intelligence in the system," explained Goldman. "They are not just surface-minimizing machines. They are looking to exploit good conditions and resources."
This intelligence of the worms was also on display in heat experiments, where the cooperation between the worms in the blob allowed them to slink away from hot spots, dramatically improving their survival chances. Moving as a blob, 95% of the worms made it to the cold side.
Ozkan-Aydin incorporated the observations of worm behavior into small robotic blobs made of "smart active particles" or "smarticles." She pinned six 3D-printed robots which featured two arms and two light sensors in a mesh, essentially entangling them similarly to the worms. She then programmed and tested different movements the robots could perform, finding that the robot swarms "generate emergent behavior that is similar to what we saw in the worms."
You can check out the new study "Collective dynamics in entangled worm and robot blobs" published in PNAS, the Proceedings of the National Academy of Sciences.
