How Predictive AI Improves Supply Chain Logistics

From airports and shipping ports to highways, pipelines and wind farms, artificial intelligence is reshaping how the world builds and manages its infrastructure

AI has enormous potential in infrastructure. Upwards of US$153 trillion will be spent on infrastructure in the next ten years globally, and such projects need innovative thinking from asset managers, engineers and computer scientists.

The secondary positive effects of infrastructure spending include corresponding consumer spending that boosts investment in other sectors. AI can improve efficiencies, capture big data, streamline design and build processes, and improve safety.

While many countries have infrastructure investment projects planned, many will need to be re-engineered for big data capture and AI integration. That opportunity, connecting big data and AI in infrastructure design, build and asset management, is a critical piece where China and Japan have already made inroads.

In infrastructure, predictive AI can detect when the probability of major disruptions will increase significantly, whether triggered by natural or man-made causes. This anticipatory capability is particularly vital: it can help predict where problems will arise and adapt infrastructure operations to forestall disruption before it happens.

Airports: Smarter Skies

Predictive AI will be significant for airport and flight management. Flight delays have a negative impact on airlines, airports and passengers, so the ability to predict events and manage impacts is critical to aviation decision-making. Airports using air traffic systems with AI and machine learning for airspace efficiency could save the US economy US$50 billion per year in saved costs from airport delays alone.

Flight disruptions are estimated to cost airlines US$25 billion per year. Using AI, machine learning and cognitive computing to predict types of flight disruptions and make operational changes to accommodate them would put a significant dent in those costs. Predictive AI is expected to be adopted by most airlines and airports within the next five years.

Predictive AI is already improving airport management by leveraging big data analytics and machine learning to predict airport operational conditions five times sooner than previously possible. For example, if an airport always changes its runway configuration when wind blows from the opposite direction, and weather forecasts show that wind will change direction at 2 pm, the model can predict a runway configuration change after 2 pm. Since runway configuration changes affect approach patterns and taxi times, airlines that know operational conditions ahead of time can optimize planning for flights, routes and fuel consumption.

AI is also used to improve public safety in airports. Video analytics software can detect hazards and alert administrators about suspicious objects or intrusions into restricted areas. Advances in video analytics now make it possible to reconstruct 2D video images into 4D understanding by adding depth and time, improving accuracy and reducing false positives. Facial recognition, long used at airports in China, is being embraced in the West for security and immigration. Queue detection functionality in video analytics can also help eliminate long lines at security and passport control, alerting administrators in real time when crowds form so they can deploy staff to open more lanes.

The Kaggle data science community is hosting an online competition to build machine learning tools that help airport security agents improve the accuracy and efficiency of threat recognition algorithms. Competitors develop ways to accurately predict the location of threat objects on a person’s body. The TSA is providing a dataset of images so that algorithms can be trained on images of people carrying weapons.

Gatwick Airport in London is tracking different areas of airport activity to predict passenger volumes and improve service delivery. A Switzerland-based company is developing disruption warning and prediction capabilities using industry-specific and public data feeds, including Twitter, to monitor imminent disruptions and allow for cost reduction in aviation management.

PASSUR Aerospace, a US company, uses predictive AI to improve the performance of airline and airport logistics using multiple data sources from disparate systems, together with machine learning, to create an integrated solution for airport operations.

Researchers from the State University of New York and Binghamton University developed an AI program to predict how long passengers will be stuck waiting for flights, using weather and air traffic data to help airlines inform passengers more quickly and accurately about travel conditions.

The TSA is testing AI technology to increase the speed and accuracy of airport security screening using a new type of full-body scanning that can process multiple passengers at a time, incorporating facial recognition to identify people in a database and detect facial expressions and postures that may pose a security risk, although the latter raises legal and ethical concerns in AI law.

San Francisco International Airport is undergoing a US$2.4 billion renovation that includes a new AI software tool automating cost-benefit analysis for buildings and sites. For example, the AI predicted that building a green roof over Terminal 1 would yield a US$5 million saving over a 50-year timespan, making a compelling case for its inclusion in the redesign.

JetBlue is launching a trial of biometric-enabled self-boarding at Logan International Airport, using facial recognition to optimize the boarding process. Airports in Dubai are also beginning to use automation software to improve airport planning, particularly coordinating resources such as check-in gates and aircraft stands. AI can perform calculations for 40 flights per second and integrate information from multiple sources to improve the automation process.

Shipping Ports: Smarter Cargo

The operational, communicative and collaborative abilities of ports can be vastly improved using AI, particularly with respect to cargo owners, agents, shipping companies and port units. AI in port settings can closely track cargo, equipment, personnel and logistics flows to intelligently detect risks, maintain operations and ensure the safety and security of local cities. In the future, advances in AI will allow ports to connect seamlessly with their machine control functions to allocate and distribute resources as efficiently as possible under different operational conditions.

The US Coast Guard uses predictive AI for port security to schedule patrols that deter and disrupt potential threats, including terrorist threats. For example, the system uses data on passenger load numbers and traffic changes to create schedules that make it challenging for bad actors to predict opportune times to attack infrastructure.

In Japan, Mitsui OSK Lines and Yokohama National University are using predictive AI to analyze ocean transportation data with a view to predicting shipping market conditions and bunker prices more accurately for a competitive edge in transport and logistics.

ClearMetal, a US company, uses predictive AI and machine learning to manage shipping logistics as freight moves from port to port. It aggregates data about carrier operations, weather forecasts, labour issues and economic changes to create a predictive model for 75 points of uncertainty, which updates in real time. For example, ClearMetal can tell a company that 35 containers will be ready to ship from Vancouver to China in two weeks, when they are expected to arrive, where in the port they should be delivered, and what traffic and weather conditions look like at the destination port. If weather cancels a shipment, the program adjusts projections so the company can reallocate resources or recalculate a shipping route.

Highways: AI in the Fast Lane

Cities around the world are beginning to use AI to optimize transportation delivery and highway management, such as using sensors and cameras to optimize traffic light timing for optimal traffic flow. AI in smart traffic light systems can save the US economy US$121 billion per year and eliminate 56 billion pounds of CO2 annually.

AI can be used for vehicular traffic management on highways to improve safety by increasing situational awareness and providing drivers with real-time route information. With the adoption of intelligent highway technology, AI can increase highway capacity by up to 273%. In the UK, traffic lights are being fitted with technology for safety and roadway load management. The AI-powered traffic lights monitor speed and congestion, prioritize cyclists, buses and ambulances with green lights, and use heatmaps to analyze how pedestrians and motorists are using the road.

In China, Alibaba’s Aliyun is being used to predict real-time traffic in collaboration with the Hangzhou government to alleviate road congestion. By employing Aliyun, the Hangzhou government has seen an 11% increase in traffic efficiency on its roads. China has also partnered with Vancouver-based quantum computing company D-Wave to bring smarter AI traffic management systems to China’s largest cities.

In India, the Tata Group is creating a series of roads to develop an autonomous traffic system that accounts for pedestrians who walk through traffic at will, lanes that merge without warning, poor signage and stray cattle. Indian roads present a deep learning challenge because they involve modern highways and dirt tracks, erratic street signage and the risk of stray elephants, camels and three-wheeled rickshaws sharing the road with cars.

In the US, the Regional Transportation Commission of Southern Nevada launched a pilot program to help prevent crashes and reduce traffic backups in Las Vegas, cross-referencing historical data with real-time data including traffic light timing, major traffic events, weather conditions, vehicle locations and speeds. The pilot is premised on the idea that resources can be better deployed to problem areas to reduce traffic fatalities and congestion, saving millions of dollars in law enforcement, emergency services and municipal insurance expenses.

German automaker Volkswagen is researching ways to combine deep learning and quantum computing to optimize traffic flow in densely populated cities, analyzing stop lights, traffic flow, pedestrians and road construction to predict which routes are better for drivers by studying past traffic patterns in urban environments.

Oil and Gas: Watching the Pipeline

AI is playing a growing role in oil and gas infrastructure, particularly with respect to monitoring pipeline integrity and predicting volume demands. Pipeline integrity is a significant critical infrastructure component in oil-producing countries. Pipeline robotics are already in development, accessing pipeline integrity to ensure spills do not occur, which is particularly vital with environmentally sensitive loads.

The Southwest Research Institute in the US is developing a machine learning system to improve pipeline safety that captures and processes image data from thermal and infrared cameras to detect leaks early, allowing for more effective and responsive environmental management and saving significant costs.

Wind Farms: Remote Intelligence

AI is helping to monitor and improve the efficiency of wind farms and wind turbines in remote locations. Wind turbines off Denmark near the North Sea are so geographically isolated that they cannot be serviced for many months of the year. Companies operate remote diagnostic centres using AI to monitor turbines, analyze data to detect irregularities potentially indicative of impending failures, and make remote operational decisions.

In the US, the National Center of Atmospheric Research is using AI to help understand how much wind power will be produced the next day so that energy utilities and grid operators can use wind turbines at peak efficiency. The AI-based software considers wind speed together with data from weather satellites, stations and other wind farms to determine how much wind power is available at any given time.

The University of Manchester has a project to deploy AI and robotics for the remote operation and maintenance of offshore wind farms. Over 80% of the cost of offshore wind farm operation and maintenance arises from remote site access difficulties. The project looks at the use of AI and robotics to reduce maintenance costs by creating predictive and diagnostic techniques to detect problems early and implement cost-effective solutions. Robots and advanced sensors will be used to reduce the need for human intervention in hazardous and remote environments.

The idea of using robots to attend to remote wind farms is not new. In 2013, Helical Robotics launched robotic platforms to improve safety and reduce liability and personnel costs for wind turbine maintenance. Its lightweight magnetic climbing robot weighs less than 40 lbs but can lift 20 lbs, is deployable in less than one minute, and can scale wind towers for blade inspection. It can also examine turbine blades from the ground about 100 meters away using a high-powered telescope.

Hydroelectricity: Powering Up with Predictive AI

AI is perfectly designed for hydroelectricity. Each component of a hydroelectric dam, from intake to turbine, alternators, transformers, dam status and drain system, lends itself naturally to improvements from predictive AI. Predicting consumption of the resulting electricity is also AI-relevant, which could allow for more tailored capacity and performance of hydropower.

Dams produce 17% of the world’s electricity, and digitizing big data from hydroelectric dams is crucial to adopting AI and meeting demands with efficiency. The mathematical models currently operating power production are 30 years old, and new methods are needed to optimize energy globally. Applications of machine learning to automate dams and predictive AI for resource management would improve hydropower efficiency and save costs.

At the University of Guelph, engineers are using machine learning to help turn small dams into cost-effective renewable energy resources for rural users, based on the Archimedes screw developed in 250 BC. With the Archimedes screw, water flowing over a dam enters a channel containing a screw, which turns from the weight of the falling water, converting mechanical energy into electricity. The researchers are using neural networks and machine learning to determine how to optimize the screw’s customization to enable users in rural parts of Ontario to generate power for several hundred households.

Bibliography

Ackerman, Evan. “Study: Intelligent Cars Could Boost Highway Capacity by 273%.” IEEE Spectrum, September 4, 2012.

Akers, Mick. “RTC, Tech Firm Team Up on Pilot Program to Better Anticipate Accidents, Traffic Jams.” Las Vegas Sun, July 12, 2017.

Airport Business. “Travelers Can Make Themselves at Home in Smarter, Safer Airports.” June 27, 2017.

BTN News. “Aviation Now Using Artificial Intelligence to Predict Flight Disruptions and More.” January 26, 2017.

Castellanos, Sara. “Volkswagen to Use Deep Learning to Optimize Traffic Flow.” Wall Street Journal, June 28, 2017.

Cisco / Gorges, Mary. “Oceans of Data from World’s Offshore Wind Farms.” Cisco, February 2017. https://www.cisco.com/.

Dia, Hussein. “An Agent-Based Approach to Modelling Driver Route Choice Behaviour Under the Influence of Real-Time Information.” Emerging Technologies, 2002.

Flinders, Karl. “Dubai Airports Automates Resource Planning.” Computer Weekly, June 8, 2017.

Genge, B. “Data Fusion-Based Anomaly Detection in Networked Critical Infrastructures.” Dependable Systems and Networks Workshop, 2013.

Hill, Joshua S. “Robotics to Help Maintain Offshore and Onshore Wind Turbines.” CleanTechnica, April 3, 2013.

Holley, David. “Pipe Leak Detection System Employs Machine Learning to Limit Errors.” Xconomy, April 7, 2017.

Mannes, John. “The Kaggle Data Science Community Is Competing to Improve Airport Security with AI.” TechCrunch, June 22, 2017.

Miller, Mark. “The Next Wave in Airport Efficiency: Predictive Analytics.” Aviation Pros, April 6, 2016.

Ogden, Jim. “Artificial Intelligence Could Speed Airport Security.” The Jetsetter’s Homestead, March 24, 2017.

Port Technology. “MOL to Tap Artificial Intelligence for Shipping.” September 1, 2016.

Prigg, Mark. “The AI That Could Tell You How Long Your Flight Is Delayed For.” Daily Mail Online, November 14, 2016.

Rai, Saritha. “Anarchy on India’s Roads Has Driverless Car in a Jam.” Bloomberg Technology, June 29, 2017.

Rigg, Jamie. “AI Will Take Control of Milton Keynes Traffic Lights Next Year.” Engadget, May 17, 2017.

Robotics & AI. “Artificial Intelligence, Robotics and Biometrics on JetBlue’s Technology Watch List.” Future Travel Experience, June 2017.

Slowikowski, Matt. “How Artificial Intelligence Could Help Transform the Oil Industry.” OilPrice.com, August 21, 2016.

Stanford University, Transportation Planning. “One Hundred Year Study on Artificial Intelligence: Transportation Planning.” 2015.

Sys-Con Media. “PASSUR and GE Partner to Advance Airline and Airport Operations.” June 20, 2017.

Sys-Con Media. “San Francisco International Airport Uses Insights from Autocase to Convert ‘Triple Bottom Line’ from Aspiration to Reality on $2.4B Renovation.” June 19, 2017.

Tadjeh, Yasmin. “Company Using Artificial Intelligence to Improve Security.” National Defense, June 1, 2016.

University of Manchester. “Artificial Intelligence and Robots to Make Offshore Windfarms Safer and Cheaper.” Phys.org, March 9, 2017.

Walsh, Sue. “ClearMetal Announces Predictive Analytics Platform for Shipping.” RT Insights, February 29, 2016.