Artificial intelligence, machine learning, digital twins, etc. are making their way into the construction industry. For what benefits and application? Find out through the example of ORIS Materials Intelligence.

Artificial Intelligence used for complex analysis during infrastructure planning

Artificial intelligence (AI) is a sub-discipline of computer science that aims at making machines intelligent. Intelligence includes the ability to process sensory impressions, information, language or problems and thus to interact with the environment. Such technology is used to simulate different structures, for example in road construction. Using only the human brain, the scenarii are limited in time and in number. Using AI results in multiple variants and scenarios analysed in a short period of time, using various criteria such as material consumption, greenhouse gas emissions and the expected costs. This contributes to delivering a thorough, comprehensive assessment, making a decisive contribution to implementing infrastructure projects as sustainably as possible. Using AI might lead to identify out-of -the-box scenario that would have not been identified otherwise.

The next stage in development is the so-called generative AI, which means that the machine can also produce content independently. Take the example of Chat GPT which creates articles based on a couple of keywords. Other fields of application could include an input of requirements for an infrastructure and AI would generate directly a design proposal instead of evaluating and comparing different options as it is the case now.

Faster mapping of material suppliers through machine learning

ORIS' core service is the mapping of all construction sites (quarries, cement, RMX, asphalt, etc.). To date, 32,000 sites were identified and referenced on the platform, using machine learning, a sub-discipline of artificial intelligence

How is Machine Learning used? If you look at gravel works from a bird's eye view, for example, you can recognise recurring specific characteristics on satellite images with the human eye. For example, there are frequently recurring features such as access roads, conveyor systems, quarry ponds and sandy subsoil. The identification of such characteristics is first defined on examples, so that they can then be applied through machine learning. Through human correction or specification, the identification gets better and better, the machine starts to learn. Based on this information, more and more sites can be automatically identified and existing data can be validated - speeding up the process of identification and mapping of construction materials sites.

Accurate calculations of the CO₂ footprint thanks to advanced algorithms

An accurate and thorough evaluation of the CO₂ footprint of aggregates is a complex endeavour. Essentially, the calculation of the CO₂ footprint is about systematically collecting, processing and finally calculating data. It needs to consider all the phases of a product's life cycle, such as the extraction of raw materials, the manufacture of the product, its transport to the construction site, its use and finally its recovery or landfill. By using software with intelligent algorithms, this process can be automated, time- and cost-efficient and quality-assured. After inputting data, ORIS' CO₂ calculator will deliver its users within 72 hours a certificate with the carbon footprint of an aggregate product.

More sustainable designs with the simulation of different scenarios through digital twins

Digital twins are virtual models designed to accurately reflect a physical object. The object being studied replicate vital areas of functionality to produce data about different aspects of the physical object’s performance. Once informed with such data, the virtual model can be used to run simulations, study performance issues and generate possible improvements, all with the goal of generating valuable insights. 

In infrastructure planning and designing, the use of digital twins proves its effectiveness to process external data - such as climate change impact models, in order to factor in the effects of climate change in the region.

Looking at construction materials through AI, Machine Learning and digital twins is the core innovation brought by ORIS to the construction industry. The use of raw materials more sustainably, the limitation of greenhouse gas emissions, the use of less water, the design of long-lasting infrastructure assets ... are just a few benefits from using advanced digitalisation.