{"id":43008,"date":"2022-02-02T08:17:34","date_gmt":"2022-02-02T07:17:34","guid":{"rendered":"https:\/\/www.ferrovial.com\/blog\/?p=43008"},"modified":"2025-12-12T00:30:51","modified_gmt":"2025-12-11T23:30:51","slug":"can-artificial-intelligence-design-new-materials","status":"publish","type":"post","link":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/","title":{"rendered":"Can artificial intelligence design new materials?"},"content":{"rendered":"

Could artificial intelligence<\/strong> help us design new materials? In mid-2018, a promising article was published in the journal Science Advances<\/a>. A team of researchers had discovered metallic glasses in an \u201caccelerated manner.\u201d To do so, they had used machine learning.<\/p>\n

One of the biggest challenges of materials engineering<\/strong> is finding the right substance for a certain purpose based on certain properties the material must have. For example, what material could replace concrete? How can we design more sustainable asphalt<\/a>?<\/p>\n

As the authors noted in the abstract, \u201csearching the vast combinatorial space [of material combinations] is frustratingly slow and expensive,\u201d and a new way of finding suitable materials is needed. That new way is artificial intelligence.<\/p>\n

How can artificial intelligence find new materials?<\/h2>\n

Every existing material can be virtualized as a data set. Alloy steel, for instance, is made from specific proportions of iron and carbon (along with other elements) that undergo a specific process and take on a certain structure. That is, there\u2019s a \u2018chemical composition\u2019<\/strong> that goes with a certain internal organization and manufacturing process.<\/p>\n

This data set gives rise to a different set of properties that can be called \u2018material properties.\u2019<\/strong> These include viscosity, melting point, compressive strength, fluidity, conductivity, etc. Material properties are a function of composition, or in other words, each composition will give rise to a set of properties.<\/p>\n

properties = f(composition)<\/p>\n\n\n\n\n\n\n\n\n\n
Steel<\/td>\n% carbon<\/td>\nTensile strength (kgf\/mm2<\/sup>)<\/td>\n<\/tr>\n
Extra-mild<\/td>\n0.1 to 0.2<\/td>\n35<\/td>\n<\/tr>\n
Mild<\/td>\n0.2 to 0.3<\/td>\n45<\/td>\n<\/tr>\n
Semi-mild<\/td>\n0.3 to 0.4<\/td>\n55<\/td>\n<\/tr>\n
Medium-hard<\/td>\n0.4 to 0.5<\/td>\n65<\/td>\n<\/tr>\n
Hard<\/td>\n0.5 to 0.6<\/td>\n75<\/td>\n<\/tr>\n
Extra-hard<\/td>\n0.6 to 0.7<\/td>\n85<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Material characterization<\/strong>, which is the study of their properties, has been generating tables like the one shown above for centuries. It shows the tensile strength of the steel based on the percentage of carbon over iron. Each percentage of carbon translates into a different resistance.<\/p>\n

However, these tables are quite limited. Does a semi-mild steel with 0.31% carbon have the same strength as one with 0.39% carbon? Obviously not. It\u2019s not a discrete function but a continuous one. The problem is that obtaining each discrete piece of information is expensive because the material has to be manufactured and tested. That\u2019s why tables are tables and not formulas.<\/p>\n

For several centuries, statistics have been filling in the unknown gaps by using interpolation techniques – for example, 0.2% steel must be between 35 and 45 kg\/mm2<\/sup>, so about 40 kg\/mm2<\/sup> is an allowable figure. But as new materials emerge and we reach their limits, testing becomes more and more expensive.<\/p>\n

That\u2019s where artificial intelligence comes in<\/strong>. It can \u2018fill in\u2019 gaps in tables with materials that have never been produced, predicting properties based on what is known about other materials and even developing new tables on its own.<\/p>\n

The AI that took two hours to build the periodic table<\/h2>\n

The periodic table<\/strong> is one of humankind\u2019s greatest achievements when it comes to contextualizing matter. In 1869, Russian chemist Dmitri Mendeleev presented this table to the Russian Chemical Society, and it has evolved over the years as new elements were discovered.<\/p>\n

\"Dmitri
\nDmitri Mendeleev\u2019s Periodic Table (1871)<\/em><\/p>\n

He accomplished something incredible with this table. Not only did he manage to order known matter, but he could also make predictions about elements that weren\u2019t yet known<\/strong> based on the unoccupied chemical properties in the table. The first attempts at a periodic table date back to 1780, and it has taken us almost 250 years to shape and polish it.<\/p>\n

That\u2019s why it is so fascinating to watch artificial intelligence like Atom2Vec sort out a list of chemical compounds and draw a periodic table with the basic properties<\/a> of each element on its own in two hours. Furthermore, it did this in a vector space (which humans can\u2019t read without tools) rather than the table we\u2019re used to seeing.<\/p>\n

What has been achieved so far with \u2018AI materials?\u2019<\/h2>\n

We began the article by mentioning a publication about new types of metallic glass<\/strong> that were discovered using machine learning. To understand its potential, just consider that, for the 6,000 new combinations tested to form different metallic glasses over the last 50 years, some 20,000 permutations were tested during the first year of machine learning.<\/p>\n

The possibilities that artificial intelligence offers are immense. Recent years have seen the discovery of new hybrids of glass and metal<\/a>, new properties of two-dimensional materials<\/a> like graphene, new electrolytes<\/a> for electric batteries, and the analysis of new silicon-germanium structures<\/a> that work better thermally than current ones.<\/p>\n

The list keeps growing every day, and this field has long ceased to be confined to the lab. The new aluminum alloys are already being used in applications like automobiles and pressure vessels. It\u2019s only been a couple of years since machine learning tools started \u2018combing\u2019 the PoLyInfo database, but tens of thousands of promising lines of research have already been identified.<\/p>\n

There\u2019s no doubt that artificial intelligence is going to transform the way we find new materials<\/strong>, which will, in turn, lead to new challenges. If the biggest difficulty in the time before AI was in the cost of testing materials and determining their properties, the challenges of the AI era are computing power, data quality, and filtering information.<\/p>\n

An article by Marcos Mart\u00ednez<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

Could artificial intelligence help us design new materials? In mid-2018, a promising article was published in the journal Science Advances. A team of researchers had discovered metallic glasses in an \u201caccelerated manner.\u201d To do so, they had used machine learning. One of the biggest challenges of materials engineering is finding the right substance for a […]<\/p>\n","protected":false},"featured_media":43001,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"nivel-1":[],"nivel-2":[4747,5989,4757],"nivel-3":[],"nivel-4":[],"nivel-5":[],"topic":[7296,7299,7300],"coauthors":[2413],"class_list":["post-43008","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","nivel-2-artificial-intelligence","nivel-2-corporate","nivel-2-materials","topic-construction-and-infrastructure","topic-management-and-strategy","topic-technology-and-innovation"],"acf":[],"yoast_head":"\nCan artificial intelligence design new materials?<\/title>\n<meta name=\"description\" content=\"In mid-2018, a team of researchers had discovered metallic glasses in an \u201caccelerated manner.\u201d To do so, they had used machine learning.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Can artificial intelligence design new materials?\" \/>\n<meta property=\"og:description\" content=\"In mid-2018, a team of researchers had discovered metallic glasses in an \u201caccelerated manner.\u201d To do so, they had used machine learning.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/\" \/>\n<meta property=\"og:site_name\" content=\"Ferrovial\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/ferrovial\" \/>\n<meta property=\"article:published_time\" content=\"2022-02-02T07:17:34+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-11T23:30:51+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/static.ferrovial.com\/wp-content\/uploads\/sites\/3\/2022\/01\/31131916\/ave-calvar-nqxqlphdbvu-unsplash-1200px.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"703\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@ferrovial_es\" \/>\n<meta name=\"twitter:site\" content=\"@ferrovial_es\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Marcos Mart\u00ednez\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Can artificial intelligence design new materials?","description":"In mid-2018, a team of researchers had discovered metallic glasses in an \u201caccelerated manner.\u201d To do so, they had used machine learning.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/","og_locale":"en_US","og_type":"article","og_title":"Can artificial intelligence design new materials?","og_description":"In mid-2018, a team of researchers had discovered metallic glasses in an \u201caccelerated manner.\u201d To do so, they had used machine learning.","og_url":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/","og_site_name":"Ferrovial","article_publisher":"https:\/\/www.facebook.com\/ferrovial","article_published_time":"2022-02-02T07:17:34+00:00","article_modified_time":"2025-12-11T23:30:51+00:00","og_image":[{"width":1200,"height":703,"url":"https:\/\/static.ferrovial.com\/wp-content\/uploads\/sites\/3\/2022\/01\/31131916\/ave-calvar-nqxqlphdbvu-unsplash-1200px.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_creator":"@ferrovial_es","twitter_site":"@ferrovial_es","twitter_misc":{"Written by":"Marcos Mart\u00ednez","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/#article","isPartOf":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/"},"headline":"Can artificial intelligence design new materials?","datePublished":"2022-02-02T07:17:34+00:00","dateModified":"2025-12-11T23:30:51+00:00","mainEntityOfPage":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/"},"wordCount":863,"commentCount":0,"publisher":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/#organization"},"image":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/#primaryimage"},"thumbnailUrl":"https:\/\/static.ferrovial.com\/wp-content\/uploads\/sites\/3\/2022\/01\/31131916\/ave-calvar-nqxqlphdbvu-unsplash-1200px.jpg","inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/","url":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/","name":"Can artificial intelligence design new materials?","isPartOf":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/#primaryimage"},"image":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/#primaryimage"},"thumbnailUrl":"https:\/\/static.ferrovial.com\/wp-content\/uploads\/sites\/3\/2022\/01\/31131916\/ave-calvar-nqxqlphdbvu-unsplash-1200px.jpg","datePublished":"2022-02-02T07:17:34+00:00","dateModified":"2025-12-11T23:30:51+00:00","description":"In mid-2018, a team of researchers had discovered metallic glasses in an \u201caccelerated manner.\u201d To do so, they had used machine learning.","breadcrumb":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/#primaryimage","url":"https:\/\/static.ferrovial.com\/wp-content\/uploads\/sites\/3\/2022\/01\/31131916\/ave-calvar-nqxqlphdbvu-unsplash-1200px.jpg","contentUrl":"https:\/\/static.ferrovial.com\/wp-content\/uploads\/sites\/3\/2022\/01\/31131916\/ave-calvar-nqxqlphdbvu-unsplash-1200px.jpg","width":1200,"height":703},{"@type":"BreadcrumbList","@id":"https:\/\/www.ferrovial.com\/blog\/en\/2022\/02\/can-artificial-intelligence-design-new-materials\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ferrovial.com\/blog\/en\/"},{"@type":"ListItem","position":2,"name":"Can artificial intelligence design new materials?"}]},{"@type":"WebSite","@id":"https:\/\/www.ferrovial.com\/blog\/en\/#website","url":"https:\/\/www.ferrovial.com\/blog\/en\/","name":"Ferrovial","description":"Aeropuertos, autopistas, construcci\u00f3n y servicios (smart cities).","publisher":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.ferrovial.com\/blog\/en\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.ferrovial.com\/blog\/en\/#organization","name":"Ferrovial S.A.","url":"https:\/\/www.ferrovial.com\/blog\/en\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ferrovial.com\/blog\/en\/#\/schema\/logo\/image\/","url":"https:\/\/static.ferrovial.com\/wp-content\/uploads\/sites\/3\/2018\/03\/13150646\/logo-vector-ferrovial.jpg","contentUrl":"https:\/\/static.ferrovial.com\/wp-content\/uploads\/sites\/3\/2018\/03\/13150646\/logo-vector-ferrovial.jpg","width":525,"height":156,"caption":"Ferrovial S.A."},"image":{"@id":"https:\/\/www.ferrovial.com\/blog\/en\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/ferrovial","https:\/\/x.com\/ferrovial_es","https:\/\/www.linkedin.com\/company\/ferrovial","https:\/\/www.youtube.com\/ferrovial"]},{"@type":"Person","@id":"https:\/\/www.ferrovial.com\/blog\/en\/#\/schema\/person\/ca7a4e9cd7d5f4ee20be1e888d5f18dd","name":"Marcos Mart\u00ednez","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/54664e4745a664be5277401dbe0594413d356858e2c0a63c99ed7be4c688a8d5?s=96&d=mm&r=g7e0b705851e6b04d4040ce859b3f2862","url":"https:\/\/secure.gravatar.com\/avatar\/54664e4745a664be5277401dbe0594413d356858e2c0a63c99ed7be4c688a8d5?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/54664e4745a664be5277401dbe0594413d356858e2c0a63c99ed7be4c688a8d5?s=96&d=mm&r=g","caption":"Marcos Mart\u00ednez"},"description":"Inquieto por naturaleza, me gusta tener m\u00e1s de un trabajo a la vez. He trabajado como ingeniero en telecomunicaciones y dise\u00f1o de producto orientado a eficiencia energ\u00e9tica y como redactor de contenido para varias marcas y proyectos culturales. Me interesa formar parte de proyectos con potencial y cuyo valor de cara al usuario sea relevante a nivel social, que tengan incidencia sobre el futuro que construimos para la generaci\u00f3n de nuestros nietos.","sameAs":["http:\/\/marcosmartinez.me"]}]}},"_links":{"self":[{"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/posts\/43008","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/comments?post=43008"}],"version-history":[{"count":4,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/posts\/43008\/revisions"}],"predecessor-version":[{"id":53487,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/posts\/43008\/revisions\/53487"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/media\/43001"}],"wp:attachment":[{"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/media?parent=43008"}],"wp:term":[{"taxonomy":"nivel-1","embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/nivel-1?post=43008"},{"taxonomy":"nivel-2","embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/nivel-2?post=43008"},{"taxonomy":"nivel-3","embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/nivel-3?post=43008"},{"taxonomy":"nivel-4","embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/nivel-4?post=43008"},{"taxonomy":"nivel-5","embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/nivel-5?post=43008"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/topic?post=43008"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.ferrovial.com\/blog\/en\/wp-json\/wp\/v2\/coauthors?post=43008"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}