Road snow removal in areas that receive heavy snowfall in winter is a labor-intensive and time-sensitive task. Typically in such areas, local patrols conducted during the day assess snow accumulation and the amount of forecasted snowfall, using their knowledge and experience to guide nightly snow removal operations. However, as populations in rural areas decline and grow older, the scarcity of experienced snow removal operators has become a pressing concern. What's more, for many regions the situation is made worse by more extreme weather conditions in recent years.

As noted by the National Geographic^*, scientists predict that climate change could actually make blizzards more intense. A warmer atmosphere may mean that less snow overall is falling, but a warmer atmosphere also holds more moisture. This eventually falls as snow in winter and results in more frequent and intense storms.

At a time when heavy snowfall can make roads impassable and shut down the daily lives of millions, NTT, NTT East and NEC Corporation are working together to deliver a technological solution that has the potential to transform the winter months of snowbound areas.

The three research partners have successfully demonstrated a new use of telecommunication optical networks for making crucial and timely decisions on snow removal in heavy snowfall areas. Their pioneering technology uses vibration sensing, a method that promises to revolutionize how communities cope with severe winter conditions.

Vibration sensing involves a machine learning model that estimates road surface conditions based on vibration characteristics transmitted through underground communication optical fibers. These fibers, already in place for telecommunications purposes, double as sensors for detecting traffic vibrations, offering a maintenance-free and weather-resistant monitoring system. In theory, the vibration sensing approach allows for remote, real-time decision-making across multiple snow removal zones, without the need for additional sensor devices. No more time is wasted in having to travel to zones of bad weather and make decisions on the scene; NTT and NEC technology can make it possible for operators to know the condition of their roads immediately and make prompt decisions on which areas to prioritize.

That's the theory. An experiment conducted in Aomori City in northern Japan from November 2022 to March 2023 proved the technology could become a reality. It involved connecting a sensing instrument to the upper end of a telecommunication optical fiber underground. Over several months, the research team collected traffic vibration data, including vehicle speed information and vibration frequency response characteristics. This data was then used to build a snow removal necessity decision model, enabling accurate, real-time snow removal decisions.

One of the most significant benefits of the technology is that it gives a better solution than the traditional, rule-of-thumb methods. The model uses vehicle speed as an indicator of traffic flow smoothness and vibration frequency response characteristics correlated with road surface conditions. This allows for more precise and efficient snow removal, ensuring smoother traffic and safer roads.

The roles of the companies in designing fiber vibration sensing were distinct yet collaborative. NTT analyzed the sensing data and proposed the snow removal decision method using machine learning. NTT East focused on observing road surface conditions and providing necessary equipment for the experiment. Meanwhile, NEC implemented the optical fiber sensing measurement and developed the vehicle speed calculation algorithm.

It goes without saying that other regions of the world experience heavy snowfall, not just Japan, and the implications of fiber vibration sensing technology extend far beyond Aomori City. The partner companies plan to continue experiments in various regions of Japan in the immediate future, each with unique characteristics, to demonstrate the versatility of the snow removal necessity decision model. Their ultimate goal is to digitalize real-time snow removal decisions, thereby maintaining a sustainable snow removal system in heavy snow areas. It's a potential solution that would apply equally well to many countries around the world.

The innovative use of telecommunication optical networks for vibration sensing in snow removal represents a leap forward in tackling problems faced by heavy snowfall areas. By harnessing existing communication infrastructure and using cutting-edge machine learning models, NTT, NTT East and NEC are not just solving a regional problem; they are paving the way for smarter, more resilient urban environments.

^* https://education.nationalgeographic.org/resource/maybe-its-cold-outside/

NTT—Innovating the Future of Urban Environments

Daniel O'Connor

Daniel O'Connor joined the NTT Group in 1999 when he began work as the Public Relations Manager of NTT Europe. While in London, he liaised with the local press, created the company's intranet site, wrote technical copy for industry magazines and managed exhibition stands from initial design to finished displays.

Later seconded to the headquarters of NTT Communications in Tokyo, he contributed to the company's first-ever winning of global telecoms awards and the digitalisation of internal company information exchange.

Since 2015 Daniel has created content for the Group's Global Leadership Institute, the One NTT Network and is currently working with NTT R&D teams to grow public understanding of the cutting-edge research undertaken by the NTT Group.