Experimental AI loans are helping fruit growers


A farmer examines grapes with “SmartGlass” glasses. (Courtesy photo of Professor Mao Xiaoyang / Kyodo of Yamanashi University)

CHIBA, Japan (Kyodo) – Researchers in Japan have conducted experiments with robots and artificial intelligence to reduce fruit growers’ dependence on scarce labor while helping those who are getting older and have no successor.

Trials are ongoing in Chiba Prefecture, a key Japanese pear production area near Tokyo, and Yamanashi Prefecture, the country’s main wine-growing region in central Japan.

In the spring of this year, a consortium made up of Chiba Prefecture, agricultural cooperatives and other companies started a two-year trial project on pear-growing areas in the cities of Ichikawa and Narita.

According to the Tokyo-based consulting firm NTT Data Institute of Management Consulting Inc., which is overseeing the experiments, a robotic truck automatically follows workers as they pick pears and transports the fruit to a designated location.

An integrated camera takes photos of the pears that have been picked and the surrounding foliage, AI analyzes the data and provides information on the best time to harvest the fruit based on the growth.

“The age will come when AI-driven technology will be able to perform intricate manual tasks like pollinating and bagging fruits,” said an expert in the field.

The consortium has also developed an app that is being tested to see how it can help prevent late blight that affects the leaves, fruits and stems of pears, caused by a fungus. Sensors installed in pear fields collect meteorological data such as temperatures and precipitation and recommend the appropriate amount of pesticides to ward off the disease.

The robots “reduce our physical strain,” said Toshiharu Itabashi, the eighth generation owner of Yamani Kaju Noen, the farm on which the experiment is being carried out. “Since we are plagued by fruit diseases every year, the AI ​​projections are very helpful.”

An increase in unprecedented weather events in recent years, largely due to global warming, has made it extremely difficult for even skilled farmers to predict plant growth, said Itabashi, 63.

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

While domestic demand for pears remains stable, according to the Chiba Prefectural Government, the market is expected to expand with more exports to Southeast Asia and other regions. “We hope that popularizing (AI-based) agriculture will help keep production going,” said an official.

In 2019, a research team from the Faculty of Engineering at Yamanashi University, led by Professor Mao Xiaoyang, developed a device that can perform a process called berry thinning, which involves removing grape clusters to make room for the remaining grapes to grow larger.

When a farmer approaches a grape with goggles and a small camera, the AI ​​estimates the number of berries in each grape and highlights those that should be removed.

An app has already been developed that estimates the number of berries when the grapes are placed in a special container, but the new device called “SmartGlass” is even more user-friendly as it allows one person to use both hands to thin out the grapes as requested by the breeders, said Mao.

By adding refinements like clearer visibility and improved accuracy of the glasses, the team would like to offer a commercially viable device soon.

For inexperienced farmers, growing fruit is considered to be more difficult than growing vegetables.

Vegetables take several months to grow before harvest, but trees can take years to grow from seedlings to an age when they will produce fruit, says Shinnosuke Kusaba of the National Agriculture and Food Research’s Institute of Fruit Tree and Tea Science Organization in Tsukuba. Ibaraki prefecture.

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

“The use of (AI-based) agriculture will encourage new market entries. However, for practical use, cost reductions and an improvement in user-friendliness are required, ”says Kusaba.


Comments are closed.