AI experiments to help Japan’s fruit growers

Researchers in Japan have been running experiments using robotics and artificial intelligence (AI) to minimize fruit farmers’ reliance on labor shortages and having no successors. Trials are underway in Chiba Prefecture , a major Japanese pear-producing area near Tokyo, as well as in Yamanashi Prefecture , the country’s main grape-producing region, in central Japan.

In the spring of this year, a consortium made up of the Chiba prefectural government, agricultural cooperatives and other companies launched a two-year pilot project on pear-growing properties in the cities of Ichikawa and Narita . According to Tokyo-based NTT Data Institute of Management Consulting Inc. (which is overseeing the experiments), a robotic loading vehicle automatically follows workers as they harvest pears, transporting the fruit to a designated location.

An integrated camera takes pictures of the previously picked pears and the surrounding foliage, the AI ​​analyzes the data and provides information on the best time to harvest the fruit based on its growth.

“The time will come when AI-controlled technology is capable of performing complicated manual tasks such as pollination and fruit bagging,” said an expert in the field.

The consortium has also developed an app that is being tested to see how it can help prevent leaf blight caused by a fungus, which attacks the leaves, fruit and stems of pears. Sensors installed in pear fields collect meteorological data, such as temperatures and rainfall, and recommend the right amount of pesticides to protect against disease.

The robots are reducing “our physical load,” said Toshiharu Itabashi , eighth-generation owner of Yamani Kaju Noen , the farm where the experiment is taking place. “Since we are concerned about fruit diseases every year, AI projections are very helpful.”

An unprecedented increase in weather events in recent years mainly due to global warming has made things extremely difficult for even experienced growers to predict crop growth, Itabashi, 63, said.

“By leveraging this cutting-edge technology, I hope to protect this farm so it can continue to operate for generations to come.”

According to the Chiba prefectural government, although the domestic demand for pears remains stable, the market is expected to expand with more exports to Southeast Asia and other regions. “We hope that the popularization of (AI-based) agriculture will contribute to the maintenance of production,” an official said.

In 2019, a research team from Yamanashi University’s engineering faculty, led by Professor Mao Xiaoyang, developed a device that can perform so-called berry thinning in which bunches of grapes are removed to make room for them to grow. the ones that remain larger.

When a farmer, wearing goggles with a small camera attached, approaches a bunch of grapes, the AI ​​calculates the number of berries in each bunch and highlights which ones need to be removed.

An app had already been developed that estimated the number of berries when the grapes were placed in a special container, but the new device, called ” SmartGlass “, is even easier to use because it allows a person to use both hands for thinning. grapes. , as requested by producers, Mao said.

Adding improvements such as clearer visibility and improved goggle accuracy, the team aims to deliver a commercially viable device soon.

Fruit production is considered more challenging for inexperienced farmers compared to vegetable cultivation.

Vegetables take several months to grow before harvest, but trees can take years to grow from saplings to an age when they are producing fruit, says Shinnosuke Kusaba of the Tea and Fruit Tree Science Institute. National Food and Agricultural Research Organization in Tsukuba. Ibaraki prefecture.

He is cautiously optimistic about the use of AI farming technology.

“The use of (AI-based) agriculture will encourage new entries. But cost cuts and improvement in usability are still needed for practical application,” Kusaba said.