Japanese engineers are developing an artificial intelligence (AI) based system to identify trees at risk of falling or dropping branches, as the threat to public safety from old trees on the roadside and in parks increases.
More and more local governments are considering using the technology amid a shortage of tree experts and arborists who usually check the condition of trees.
Currently, the system evaluates the tree zelkovadansakura, with plans to add kanginkgodan other species.
As reported by ANTARA from Kyodo, in the period between April 2021 to November 2024, a total of 1,732 tree-related accidents in parks and roads in Japan were recorded, with 110 of them resulting in injury or death, according to the Ministry of Land, Infrastructure, Transport and Tourism.
For example, in September 2024 a man was killed after a ginkgopatah tree branch fell on a pedestrian path in Hino, western Tokyo.
Information technology company, Optim Corp., headquartered in Tokyo along with Kyuden Droneservice Co. in Fukuoka is developing a drone-based AI system to detect dead trees.
Meanwhile, Sumitomo Mitsui Construction Co. is developing an AI-based tree risk assessment system that analyzes photos of dead or decaying tree parts via a smartphone or tablet.
Tree AI compares the photo with tens of thousands of stored images of trunks and branches, as well as tree doctor diagnoses, then assesses the risk of falling in four scale levels.
The results are available within minutes and stored in a complete database with the location of the tree.
"The risk of falling increases if the tree has internal cavities or mold in its trunk. It is difficult for ordinary people to assess this," said tree doctor Hidemi Kataoka, who was involved in the development of the program.
Local governments such as Kizugawa in Kyoto Prefecture, Miyakonojo in Miyazaki Prefecture, as well as the Tokyo Metropolitan Government have been testing the system.
Kizugawa, which manages about 20,000 trees, is unable to conduct routine inspections due to staff limitations.
"With AI, inspections can be more efficient and consistent," said Kizugawa officials.
Around 20 local governments are considering the implementation of the system. Sumitomo Mitsui also plans to launch a commercial service in fiscal year 2027.
"Many trees were planted during Japan's high economic growth to absorb vehicle emissions and now they are reaching the end of their life," said the company's Head of Green Infrastructure Division, Sho Tago, expressing his hope that the service can support efficient and appropriate tree management in the midst of staff limitations.
The English, Chinese, Japanese, Arabic, and French versions are automatically generated by the AI. So there may still be inaccuracies in translating, please always see Indonesian as our main language. (system supported by DigitalSiber.id)
