It’s a mammoth task given the size of Britain’s 20,000 mile rail network.

AI is proving to be instrumental for UK’s Network Rail to achieve biodiversity net gain on its land by 2035. The UK Centre for Ecology & Hydrology (UKCEH) and technology firm Keen AI have been working with Network Rail to develop AI-powered solutions that can identify potential problems such as invasive species and native trees struck by disease. (UKCEH)

Trial runs of a system that uses AI to analyze images of lineside vegetation taken by on-train cameras have shown that it can successfully identify different species of trees and plants. The method is fast, cheap, safe and can be deployed at scale doing away with the requirement to appoint a large number of expert surveyors and ensuring their safety.

The AI system would be able to cover Network Rail’s 20,000 mile network using moving trains and its reports would enable railway workers to take proactive steps for vegetation management.The AI software can identify ash trees as well as Himalayan Balsam, the poisonous plant Ragwort, and even the notorious Japanese knotweed.

The trials were successful even when the cameras were mounted on high speed trains.

Dr Tom August, a computational ecologist at UKCEH, stated: “Our equipment was able to take thousands of clear images from a train travelling at up to 80mph, and our AI software can identify ash and other species to a high level of accuracy.”

Amjad Karim, chief executive of Keen AI, said “Network Rail spends £200 million each year on vegetation management; in order to keep the network operational. The aim of our work is to give staff at Network Rail the tools they need to safely and accurately identify where action may be required.”

Related Story: The U.K. Arms Itself With AI to Combat Invasive Plant Species