{"id":4293,"date":"2026-11-22T21:25:57","date_gmt":"2026-11-22T21:25:57","guid":{"rendered":"https:\/\/www.farmersforum.ie\/trends\/ai-tracks-cleaner-catalysts-a-bet-where-chemistry-makes-up-2-of-global-energy\/"},"modified":"2026-11-22T21:25:59","modified_gmt":"2026-11-22T21:25:59","slug":"ai-tracks-cleaner-catalysts-a-bet-where-chemistry-makes-up-2-of-global-energy","status":"publish","type":"post","link":"https:\/\/www.farmersforum.ie\/trends\/ai-tracks-cleaner-catalysts-a-bet-where-chemistry-makes-up-2-of-global-energy\/","title":{"rendered":"AI Tracks Cleaner Catalysts: A Bet Where Chemistry Makes Up 2% of Global Energy"},"content":{"rendered":"<p>A young Paris-based startup, Entalpic, is applying neural networks to the discovery of industrial catalysts. Its initial target is ammonia synthesis, a cornerstone of nitrogen-based fertilizers and a major consumer of energy. The approach exemplifies a shift in chemistry toward methods born from academic artificial intelligence.<\/p>\n<figure class=\"wp-block-image size-large\"><\/figure>\n<h2 class=\"wp-block-heading\">Founded in 2024 by three professionals from Quebec and digital health, Entalpic has raised \u20ac8.5 million<\/h2>\n<p>The company was established in 2024 by <strong>Mathieu Galtier<\/strong>, a former head of a health-focused applied AI company, together with Victor Schmidt and <strong>Alexandre Duval<\/strong>. The latter two come from <strong>Mila<\/strong>, the Quebec AI institute founded by Yoshua Bengio. Duval now serves as the <strong>scientific director<\/strong>.<\/p>\n<section class=\"incontent-related\"><span class=\"incontent-related__title\">Read also<\/span> <span class=\"incontent-related__desc\">The Pioneer anomaly: what happened to NASA probes at 20 astronomical units?<\/span><\/section>\n<p>Subsequently, an \u20ac8.5 million seed funding round was announced in September 2024, led by Breega, Cathay Innovation and Felicis. The team, based at Station F, numbers around thirty people. Moreover, its stated priority remains ammonia production catalysts.<\/p>\n<h2 class=\"wp-block-heading\">Ammonia synthesis accounts for about 2% of global final energy consumption<\/h2>\n<p>The <strong>Haber-Bosch<\/strong> process, developed in the early 20th century, combines atmospheric nitrogen and hydrogen under high pressure and high temperature. According to the <strong>International Energy Agency<\/strong>&#8216;s ammonia roadmap published in 2021, this production represents around 2% of global final energy consumption, equivalent to 8.6 exajoules.<\/p>\n<p>This energy weight partly stems from the <strong>catalyst<\/strong> used, an iron-based material that imposes extreme conditions. Consequently, a material more active at moderate temperatures would mechanically trim the bill. However, discovering it requires exploring an enormous space of chemical combinations.<\/p>\n<section class=\"incontent-related\"><span class=\"incontent-related__title\">Read also<\/span> <span class=\"incontent-related__desc\">A barn foundation stone in Moravia was a lance mold, and its stone from Hungary reveals a long journey<\/span><\/section>\n<h2 class=\"wp-block-heading\">With PhAST, neural networks cut simulation times by a factor of three to eight<\/h2>\n<p>Before founding the company, Alexandre Duval co-authored <strong>PhAST<\/strong>, a graph-neural-network framework dedicated to catalyst design. The work, released as a preprint in 2022, was published in 2024 in the Journal of Machine Learning Research, with notable contributors including Victor Schmidt, Yoshua Bengio and David Rolnick.<\/p>\n<p>This framework relies on the <strong>OC20<\/strong> dataset, produced by the Open Catalyst Project to train electrocatalysis models. Its authors modify three steps\u2014graph construction, atom representation, and the energy-prediction head. As a result, the claimed gains reach <strong>an 4% to 42% reduction in error<\/strong> and a computation time three to eight times faster.<\/p>\n<h2 class=\"wp-block-heading\">Predicting a structure is not enough, experimental validation remains the obligatory step for catalysts<\/h2>\n<p>These methods replace costly quantum-physics simulations with learned estimates drawn from millions of examples. Moreover, Entalpic\u2019s platform claims to combine predictive models, generative models, atomic simulations and laboratory tests. The principle is to <strong>filter<\/strong> millions of candidates before synthesizing a few.<\/p>\n<section class=\"incontent-related\"><span class=\"incontent-related__title\">Read also<\/span> <span class=\"incontent-related__desc\">On the edge: this strange insect seems to spend its life on a spider\u2019s web<\/span><\/section>\n<p>Yet, caution remains warranted regarding industrial results. No catalyst arising from this approach has been publicly documented at industrial scale, and gaps between prediction and measurement remain the rule in surface chemistry. Moreover, the performances reported so far pertain to <strong>benchmark data sets<\/strong>.<\/p>\n<p>However, the challenge goes beyond ammonia alone. The same tools target energy storage, hydrogen production and pollutant treatment\u2014areas where a catalyst dictates efficiency. Thus, surface chemistry becomes a testing ground to measure what machine learning truly brings to the discovery of materials.<\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":4294,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[2558,2812,2813,2811,689,688,2810],"class_list":["post-4293","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-bet","tag-catalysts","tag-chemistry","tag-cleaner","tag-energy","tag-global","tag-tracks","generate-columns","tablet-grid-50","mobile-grid-100","grid-parent","grid-50"],"_links":{"self":[{"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/posts\/4293","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/comments?post=4293"}],"version-history":[{"count":1,"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/posts\/4293\/revisions"}],"predecessor-version":[{"id":4295,"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/posts\/4293\/revisions\/4295"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/media\/4294"}],"wp:attachment":[{"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/media?parent=4293"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/categories?post=4293"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.farmersforum.ie\/trends\/wp-json\/wp\/v2\/tags?post=4293"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}