Traditionally, policymakers and urban planners haven’t had access to city data that can reveal complex patterns and relationships between factors that influence urban development. In some cases, data is too laborious or costly to measure at frequent time intervals, and in others, unexpected or unforeseen circumstances such as a pandemic like COVID-19 are responsible for invalidating earlier forecasts.
But this is changing rapidly, with emerging technologies unlocking new possibilities for urban planning. Advances in emerging technologies like Artificial Intelligence and Machine Learning can help us understand our cities better and derive useful insights from real-time data collected through automated models that provide a much closer view of the situation on-ground compared to traditional approaches.
These insights can properly assess public interests and help policymakers in making decisions that are more sustainable.
In this article, we will explore some sophisticated ways in which Artificial Intelligence can enhance Urban Planning.
Narrow roads in cities can be a tremendous inconvenience. The combination of small country roads and heavy trucks, sometimes driven by workers unfamiliar with the region, has resulted in countless instances of large vehicles running off the road, rolling over on narrow turns, or being involved in accidents. Problems like traffic and congestion are also common, especially in urban centers.
The obvious solution to solve this is to upgrade the existing road infrastructure or build new highways but accurately predicting their need and maintenance schedule can be difficult. This can be fixed with the help of AI-based traffic and mobility systems. These systems collect and analyze traffic data, generate solutions, and apply them to traffic infrastructure. AI-based traffic systems work by collecting data from connected traffic systems, which provides input about live traffic or years of historical traffic behavior.
These systems can also take into account data about a host of other potential problems that can impact roads and traffic in the future. In order to understand this data, such systems use machine learning models to process, analyze, and learn about traffic infrastructure. The AI then uses those insights to suggest solutions that can enable authorities to build better and safer infrastructure.
A deep learning algorithm can also help in successfully predicting maintenance requirements of road infrastructure and thus prevent expensive and unplanned failures.
Cambridge-based AI company, Intellegens, announced details of a proof of concept project with global construction and infrastructure group Skanska, which could save Hampshire County Council in excess of £100,000 per annum on road drainage and gully maintenance work. In a trial, drainage data of Hampshire County was passed through a deep learning solution which turned it into a series of models that could enable stakeholders to predict where drainage issues were most likely to occur.
Another example is the automatic recognition of road damage by ARCADIS in which images are taken with a camera of a certain road section using annual images from CycloMedia or with a GoPro. These images are then read into a custom-developed software module, which is can determine the exact location of the defect, the type of defect, the extent of the defect, and even recommended a maintenance measure. Using historical data, this model can also calculate the deterioration of roads, allowing road authorities to draw up a predictive maintenance plan.
Having accurate population forecasts helps the government with long-term infrastructure planning, particularly where land resources are scarce and the infrastructure is expensive and may take many years to build.
Forecasts try to estimate the rate of population growth, but anticipating the numbers and characteristics of the future population is very difficult as it can be influenced by unforeseen circumstances like a pandemic, war, and other mass catastrophes. Death rates can even decrease with advances in medicine and healthcare. Even the United Nations has issued multiple projections of the future world population and revises it every two years. The revisions from the projections released just two years earlier look small but become significant when accumulated over several decades.
Mathematical models can be inadequate in including all the datasets that can influence population growth and making accurate predictions. On the other hand, the cost of collecting the data required for the task is huge. To tackle these problems, machine learning algorithms can be brought to the rescue.
Artificial Intelligence and Machine Learning have gained considerable prominence over the last decade fuelled by a number of high-profile applications. It is used for forecasting too and can be very much efficient in forecasting population with automated collection and analysis of a broad and diverse set of data. These algorithms are used to quickly analyze huge and diverse datasets that can influence the growth of the population and increase the accuracy of forecasts by reducing human errors.
- Water resource management
The vast networks of buried water, wastewater, and stormwater infrastructure are the veins and arteries feeding our people, our cities, and protecting our environment. Without sustainable and viable water, waste, and stormwater solutions, our quality of life is in peril. Society’s water, wastewater, and stormwater systems have always played significant roles in eliminating disease, safeguarding the environment, and protecting communities.
There is a significant strain on water utilities’ ability to continue delivering critical services to customers while operating with limited resources. But using AI in water resource management can make way for need-based water supply and water-saving systems.
Utilities can deploy smart meters, sensors, and other IoT hardware that will inevitably result in the collection of huge amounts of data about water consumption of a region and can also detect leakages to recommend quick action. Automated analysis of this data using Machine Learning and AI will enable building an efficient water system, optimizing current water resources, infrastructure planning for water structures, and give necessary flexibility to handle unforeseen circumstances.
- Problems with sewage systems
Sewers are the most important part of sewerage systems. They are laid below the ground and are difficult to repair, often taking up significant time and resources. Smart hardware like small, rugged, low power sensors that are able to communicate with specially-designed machine learning and AI solutions can help authorities to minimize expensive repairs by automatically detecting abnormalities in real-time and recommending timely actions.
Such smart systems getting data from smart sensors installed underground can also significantly reduce the total costs to inspect and assess underground infrastructure. With the help of these systems, utilities can monitor real-time performance and AI models can predict when and where problems may arise.
External data such as weather and tides or migration trends can also be incorporated in the solutions to increases accuracy over the long-term and to actively operate and maintain these sewage systems. These smart systems can also aid in future planning for sewage systems when the data sets become large enough to apply advanced artificial intelligence tools.
AI can also be used to help residents and organizations track their waste in real-time and send notifications to users to correctly sort their waste whenever irregularities are detected.
- Smarter and safer driving
The safety of passengers, pedestrians, and drivers has always been the top concern for the transportation industry and AI can bring us closer to ensuring that. Taking advantage of AI models not only decreases accidents or mishaps caused by human errors but can also monitor safety regulation compliance and help drivers in vehicle maintenance by sending them timely alerts.
Using data analytics in logistics, on the other hand, provides a data-driven view on routes and driving behavior, which upgrades the transportation planning process, increase efficiency, and makes the process safer.
Traffic prediction models can allow users to do smarter route planning using historical as well as real-time traffic data, road and weather conditions, and even information about sporting events or construction in the area.
What lies ahead?
Artificial Intelligence is quickly revolutionizing every field from food to aviation. Several of the applications of AI in Urban Planning suggested above are even being utilized in the real-world albeit at a small scale. Some applications can be scaled up quickly to be utilized in many parts of the world.
But the barriers, especially for developing countries, to applying these technologies can still seem daunting. Investments needed to facilitate the collection of data to train AI models can be huge and the upgradation of existing infrastructure can be discouraging.
Under these circumstances, several successful examples of smart cities leading the way could be the boom AI needs to transform urban planning and our lives along with it.
VisionRI’s Centre of Excellence on Emerging Development Perspectives (COE-EDP) aims to keep track of the transition trajectory of global development and works towards conceptualization, development, and mainstreaming of innovative developmental approaches, frameworks, and practices.
Credit: Google News