MIT student uses AI to design buildings with less concrete

Concrete is responsible for 8 percent of the world's carbon emissions.
Loukia Papadopoulos
Representational image of concrete structures.jpg
Representational image of concrete structures.


In construction, concrete emissions refer to the greenhouse gas emissions associated with the production and use of concrete, one of the most widely used construction materials globally. Due to energy-intensive cement production processes and chemical reactions that take place during concrete curing, the concrete industry is a substantial source of carbon dioxide (CO2) emissions, responsible for an estimated 8 percent of the world's emissions.

Cement, which is a byproduct of heating limestone (calcium carbonate) and other minerals to high temperatures in a kiln, is the main component of concrete. In order to produce the necessary heat to decompose this limestone, fossil fuels are often burned and this produces CO2. 

Emissions are also generated when raw materials are transported to cement plants and when concrete is transported to construction sites. This includes emissions from trucks, ships, and other vehicles involved in the supply chain of concrete production.

Curbing emissions from concrete through topology optimization

There may be a way, however, to curb these concrete emissions thanks to the work of MIT student Jackson Jewett.

This is according to a press release by the institution published on Friday.

Jewett is currently in the third year of his PhD programme. His dissertation work builds on his master's thesis which focused on further developing algorithms that can design concrete structures that use less material, reducing carbon emissions from the construction sector. 

The process he is perfecting is known as "topology optimization," and it makes use of algorithms to create structures that meet a building’s performance requirements while consuming a minimal amount of resources. 

“In the last couple of months, I’ve been working on a reinforced concrete optimization algorithm that I hope will be the cornerstone of my thesis,” said Jewett.

The process, however, is long and arduous.

“It can take days or usually weeks to take a step toward making it work as an entire integrated system,” said Jewett. “The days when that breakthrough happens and I can see the algorithm converging on a solution that makes sense — those are really exciting moments.”

Materially efficient components

Jewett is on the hunt for materially efficient components that can be utilized to construct structures such as bridges and buildings. He does this through the use of computational power. During his work, he also takes into account additional restrictions, particularly making sure the manufacturing cost isn't too expensive. 

Before beginning his PhD studies, Jewett worked in the construction industry, he spent a year and a half as a structural engineer in New York City, which gave him a knack for producing work that can actually be put into practice. Jewett adds that the sooner he can complete his work, the better.

“The time horizon of when these things need to be implemented is relatively short if we want to make an impact before global temperatures have already risen too high. My PhD research will be developing a framework for how that could be done with concrete construction, but I’d like to keep thinking about other materials and construction methods even after this project is finished,” explained the student.

Add Interesting Engineering to your Google News feed.
Add Interesting Engineering to your Google News feed.
message circleSHOW COMMENT (1)chevron
Job Board