{"id":122679,"date":"2024-07-24T05:03:07","date_gmt":"2024-07-24T05:03:07","guid":{"rendered":"https:\/\/www.controleng.com\/articles\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/"},"modified":"2025-04-23T18:57:37","modified_gmt":"2025-04-23T23:57:37","slug":"machine-learning-framework-speeds-predictions-for-material-thermal-properties","status":"publish","type":"post","link":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/","title":{"rendered":"Machine-learning framework speeds predictions for material thermal properties"},"content":{"rendered":"<p>If scientists could better predict how heat moves through semiconductors and insulators, they could design more efficient power generation systems. After all, it is estimated about 70% of the energy generated worldwide ends up as waste heat. However, the thermal properties of materials can be very difficult to model.<\/p>\n<p>The trouble comes from phonons, which are subatomic particles that carry heat. Some of a material\u2019s thermal properties depend on a measurement called the phonon dispersion relation, which can be incredibly hard to obtain, let alone utilize in the design of a system.<\/p>\n<p>A team of researchers from MIT and elsewhere tackled this challenge by rethinking the problem from the ground up. The result of their work is a new machine-learning framework that can predict phonon dispersion relations up to 1,000 times faster than other AI-based techniques, with comparable or even better accuracy. Compared to more traditional, non-AI-based approaches, it could be 1 million times faster.<\/p>\n<p>This method could help engineers design energy generation systems that produce more power, more efficiently. It could also be used to develop more efficient microelectronics, since managing heat remains a major bottleneck to speeding up electronics.<\/p>\n<p>\u201cPhonons are the culprit for the thermal loss, yet obtaining their properties is notoriously challenging, either computationally or experimentally,\u201d said Mingda Li, associate professor of nuclear science and engineering and senior author of a paper on this technique.<\/p>\n<h2>Predicting phonons<\/h2>\n<p>Heat-carrying phonons are tricky to predict because they have an extremely wide frequency range, and the particles interact and travel at different speeds.<\/p>\n<p>A material\u2019s phonon dispersion relation is the relationship between energy and momentum of phonons in its crystal structure. For years, researchers have tried to predict phonon dispersion relations using machine learning, but there are so many high-precision calculations involved that models get bogged down.<\/p>\n<p>\u201cIf you have 100 CPUs and a few weeks, you could probably calculate the phonon dispersion relation for one material. The whole community really wants a more efficient way to do this,\u201d said co-author Ryotaro Okabe, a chemistry graduate student.<\/p>\n<p>The machine-learning models scientists often use for these calculations are known as graph neural networks (GNN). A GNN converts a material\u2019s atomic structure into a crystal graph comprising multiple nodes, which represent atoms, connected by edges, which represent the interatomic bonding between atoms.<\/p>\n<p>While GNNs work well for calculating many quantities, like magnetization or electrical polarization, they are not flexible enough to efficiently predict an extremely high-dimensional quantity like the phonon dispersion relation. Because phonons can travel around atoms on X, Y and Z axes, their momentum space is hard to model with a fixed graph structure.<\/p>\n<p>To gain the flexibility they needed, Li and his collaborators devised virtual nodes.<\/p>\n<p>They create what they call a virtual node graph neural network (VGNN) by adding a series of flexible virtual nodes to the fixed crystal structure to represent phonons. The virtual nodes enable the output of the neural network to vary in size, so it is not restricted by the fixed crystal structure.<\/p>\n<p>Virtual nodes are connected to the graph in such a way that they can only receive messages from real nodes. While virtual nodes will be updated as the model updates real nodes during computation, they do not affect the accuracy of the model.<\/p>\n<p>\u201cThe way we do this is very efficient in coding. You just generate a few more nodes in your GNN. The physical location doesn\u2019t matter, and the real nodes don\u2019t even know the virtual nodes are there,\u201d said Abhijatmedhi Chotrattanapituk, an electrical engineering and computer science graduate student.<\/p>\n<figure id=\"attachment_544882\" aria-describedby=\"caption-attachment-544882\" style=\"width: 1460px\" class=\"wp-caption alignnone\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-544882\" src=\"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01.jpeg\" alt=\"A new method could help models predict a material's thermal properties, such as by revealing the dynamics of atoms in crystals, as illustrated here. \" width=\"1460\" height=\"973\" \/><figcaption id=\"caption-attachment-544882\" class=\"wp-caption-text\">A new method could help models predict a material&#8217;s thermal properties, such as by revealing the dynamics of atoms in crystals, as illustrated here. Courtesy: Massachusetts Institute of Technology<\/figcaption><\/figure>\n<h2>Cutting out complexity<\/h2>\n<p>Since it has virtual nodes to represent phonons, the VGNN can skip many complex calculations when estimating phonon dispersion relations, which makes the method more efficient than a standard GNN.<\/p>\n<p>The researchers proposed three different versions of VGNNs with increasing complexity. Each can be used to predict phonons directly from a material\u2019s atomic coordinates.<\/p>\n<p>Because their approach has the flexibility to rapidly model high-dimensional properties, they can use it to estimate phonon dispersion relations in alloy systems. These complex combinations of metals and nonmetals are especially challenging for traditional approaches to model.<\/p>\n<p>The researchers also found that VGNNs offered slightly greater accuracy when predicting a material\u2019s heat capacity. In some instances, prediction errors were two orders of magnitude lower with their technique.<\/p>\n<p>A VGNN could be used to calculate phonon dispersion relations for a few thousand materials in just a few seconds with a personal computer, Li says.<\/p>\n<p>This efficiency could enable scientists to search a larger space when seeking materials with certain thermal properties, such as superior thermal storage, energy conversion, or superconductivity.<\/p>\n<p>Moreover, the virtual node technique is not exclusive to phonons, and could also be used to predict challenging optical and magnetic properties.<\/p>\n<p>In the future, the researchers want to refine the technique so virtual nodes have greater sensitivity to capture small changes that can affect phonon structure.<\/p>\n<p>\u201cResearchers got too comfortable using graph nodes to represent atoms, but we can rethink that. Graph nodes can be anything. And virtual nodes are a very generic approach you could use to predict a lot of high-dimensional quantities,\u201d Li said.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>MIT researchers have developed a machine-learning framework designed to help engineers design more efficient energy-conversion systems and faster microelectronic devices, reducing waste heat.<\/p>\n","protected":false},"author":1121,"featured_media":122681,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"pgc_sgb_lightbox_settings":"","footnotes":""},"categories":[104044],"tags":[],"tracking-metrics":[],"display-location":[],"class_list":{"2":"type-post"},"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.9 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Machine-learning framework speeds predictions for material thermal properties - Control Engineering<\/title>\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.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Machine-learning framework speeds predictions for material thermal properties - Control Engineering\" \/>\n<meta property=\"og:description\" content=\"MIT researchers have developed a machine-learning framework designed to help engineers design more efficient energy-conversion systems and faster microelectronic devices, reducing waste heat.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/\" \/>\n<meta property=\"og:site_name\" content=\"Control Engineering\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/ControlEngineeringMagazine\" \/>\n<meta property=\"article:published_time\" content=\"2024-07-24T05:03:07+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-04-23T23:57:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"759\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Adam Zewe\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@controlengtips\" \/>\n<meta name=\"twitter:site\" content=\"@controlengtips\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Adam Zewe\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/\"},\"author\":{\"name\":\"Adam Zewe\",\"@id\":\"https:\/\/www.controleng.com\/#\/schema\/person\/b5719bf890b01107531c72f3cca52261\"},\"headline\":\"Machine-learning framework speeds predictions for material thermal properties\",\"datePublished\":\"2024-07-24T05:03:07+00:00\",\"dateModified\":\"2025-04-23T23:57:37+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/\"},\"wordCount\":903,\"publisher\":{\"@id\":\"https:\/\/www.controleng.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg\",\"articleSection\":[\"AI and Machine Learning\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/\",\"url\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/\",\"name\":\"Machine-learning framework speeds predictions for material thermal properties - Control Engineering\",\"isPartOf\":{\"@id\":\"https:\/\/www.controleng.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg\",\"datePublished\":\"2024-07-24T05:03:07+00:00\",\"dateModified\":\"2025-04-23T23:57:37+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#primaryimage\",\"url\":\"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg\",\"contentUrl\":\"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg\",\"width\":1024,\"height\":759,\"caption\":\"Courtesy: Massachusetts Institute of Technology\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.controleng.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Machine-learning framework speeds predictions for material thermal properties\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.controleng.com\/#website\",\"url\":\"https:\/\/www.controleng.com\/\",\"name\":\"Control Engineering\",\"description\":\"Control Engineering covers and educates about automation, control and instrumentation technologies\",\"publisher\":{\"@id\":\"https:\/\/www.controleng.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.controleng.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.controleng.com\/#organization\",\"name\":\"Control Engineering\",\"url\":\"https:\/\/www.controleng.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.controleng.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/12\/ce_logo.png\",\"contentUrl\":\"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/12\/ce_logo.png\",\"width\":300,\"height\":93,\"caption\":\"Control Engineering\"},\"image\":{\"@id\":\"https:\/\/www.controleng.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/ControlEngineeringMagazine\",\"https:\/\/x.com\/controlengtips\",\"https:\/\/www.linkedin.com\/company\/control-engineering-magazine\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.controleng.com\/#\/schema\/person\/b5719bf890b01107531c72f3cca52261\",\"name\":\"Adam Zewe\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.controleng.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/5dcf3a2c7ccbef894a2e8835d11829e00f699c7d530a9f5873e953bb9403c619?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/5dcf3a2c7ccbef894a2e8835d11829e00f699c7d530a9f5873e953bb9403c619?s=96&d=mm&r=g\",\"caption\":\"Adam Zewe\"},\"url\":\"https:\/\/www.controleng.com\/author\/adam-zewe\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Machine-learning framework speeds predictions for material thermal properties - Control Engineering","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.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/","og_locale":"en_US","og_type":"article","og_title":"Machine-learning framework speeds predictions for material thermal properties - Control Engineering","og_description":"MIT researchers have developed a machine-learning framework designed to help engineers design more efficient energy-conversion systems and faster microelectronic devices, reducing waste heat.","og_url":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/","og_site_name":"Control Engineering","article_publisher":"https:\/\/www.facebook.com\/ControlEngineeringMagazine","article_published_time":"2024-07-24T05:03:07+00:00","article_modified_time":"2025-04-23T23:57:37+00:00","og_image":[{"width":1024,"height":759,"url":"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg","type":"image\/jpeg"}],"author":"Adam Zewe","twitter_card":"summary_large_image","twitter_creator":"@controlengtips","twitter_site":"@controlengtips","twitter_misc":{"Written by":"Adam Zewe","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#article","isPartOf":{"@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/"},"author":{"name":"Adam Zewe","@id":"https:\/\/www.controleng.com\/#\/schema\/person\/b5719bf890b01107531c72f3cca52261"},"headline":"Machine-learning framework speeds predictions for material thermal properties","datePublished":"2024-07-24T05:03:07+00:00","dateModified":"2025-04-23T23:57:37+00:00","mainEntityOfPage":{"@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/"},"wordCount":903,"publisher":{"@id":"https:\/\/www.controleng.com\/#organization"},"image":{"@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#primaryimage"},"thumbnailUrl":"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg","articleSection":["AI and Machine Learning"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/","url":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/","name":"Machine-learning framework speeds predictions for material thermal properties - Control Engineering","isPartOf":{"@id":"https:\/\/www.controleng.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#primaryimage"},"image":{"@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#primaryimage"},"thumbnailUrl":"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg","datePublished":"2024-07-24T05:03:07+00:00","dateModified":"2025-04-23T23:57:37+00:00","breadcrumb":{"@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#primaryimage","url":"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg","contentUrl":"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/11\/CTL2407_WEB_IMG_MIT-Phonon-Prediction-01-Slider.jpg","width":1024,"height":759,"caption":"Courtesy: Massachusetts Institute of Technology"},{"@type":"BreadcrumbList","@id":"https:\/\/www.controleng.com\/machine-learning-framework-speeds-predictions-for-material-thermal-properties\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.controleng.com\/"},{"@type":"ListItem","position":2,"name":"Machine-learning framework speeds predictions for material thermal properties"}]},{"@type":"WebSite","@id":"https:\/\/www.controleng.com\/#website","url":"https:\/\/www.controleng.com\/","name":"Control Engineering","description":"Control Engineering covers and educates about automation, control and instrumentation technologies","publisher":{"@id":"https:\/\/www.controleng.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.controleng.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.controleng.com\/#organization","name":"Control Engineering","url":"https:\/\/www.controleng.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.controleng.com\/#\/schema\/logo\/image\/","url":"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/12\/ce_logo.png","contentUrl":"https:\/\/www.controleng.com\/wp-content\/uploads\/2024\/12\/ce_logo.png","width":300,"height":93,"caption":"Control Engineering"},"image":{"@id":"https:\/\/www.controleng.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/ControlEngineeringMagazine","https:\/\/x.com\/controlengtips","https:\/\/www.linkedin.com\/company\/control-engineering-magazine\/"]},{"@type":"Person","@id":"https:\/\/www.controleng.com\/#\/schema\/person\/b5719bf890b01107531c72f3cca52261","name":"Adam Zewe","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.controleng.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/5dcf3a2c7ccbef894a2e8835d11829e00f699c7d530a9f5873e953bb9403c619?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/5dcf3a2c7ccbef894a2e8835d11829e00f699c7d530a9f5873e953bb9403c619?s=96&d=mm&r=g","caption":"Adam Zewe"},"url":"https:\/\/www.controleng.com\/author\/adam-zewe\/"}]}},"_links":{"self":[{"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/posts\/122679","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/users\/1121"}],"replies":[{"embeddable":true,"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/comments?post=122679"}],"version-history":[{"count":0,"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/posts\/122679\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/media\/122681"}],"wp:attachment":[{"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/media?parent=122679"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/categories?post=122679"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/tags?post=122679"},{"taxonomy":"tracking-metric","embeddable":true,"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/tracking-metrics?post=122679"},{"taxonomy":"display-location","embeddable":true,"href":"https:\/\/www.controleng.com\/wp-json\/wp\/v2\/display-location?post=122679"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}