{"id":25351,"date":"2026-07-18T14:26:23","date_gmt":"2026-07-18T13:26:23","guid":{"rendered":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/"},"modified":"2026-07-18T14:36:13","modified_gmt":"2026-07-18T13:36:13","slug":"artificial-intelligence-and-deepfakes-the-science-behind-fake-reality","status":"publish","type":"post","link":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/","title":{"rendered":"Artificial Intelligence and Deepfakes: The Science Behind Fake Reality"},"content":{"rendered":"

Right, let’s talk about deepfakes. Specifically, how artificial intelligence<\/a> (AI) is making them a reality, and what’s actually going on under the hood. In essence, deepfakes are synthetic media \u2013 usually video or audio \u2013 where a person’s face, voice, or even body is digitally altered or replaced with someone else’s using AI, specifically deep learning. It\u2019s not just a fancy editing trick; it\u2019s a sophisticated process that leverages complex algorithms to create highly convincing, yet entirely fabricated, content.<\/p>\n

The Core of Deepfakes: Generative AI<\/h3>\n

At the heart of deepfakes lies generative AI<\/a>. Unlike traditional AI that might classify or predict, generative AI creates new data that wasn’t in its training set. Think of it like an artist who learns different styles and then paints a brand new picture, rather than just identifying existing paintings. This capability is absolutely crucial for deepfakes because it allows the AI to generate<\/em> new images or audio that look and sound like a specific person.<\/p>\n

So, how do these fake realities actually come into being? It\u2019s not a single magical piece of software. Instead, it\u2019s a multi-stage process, often involving different AI models working together. The most common approach, and the one that really kicked off the deepfake phenomenon, involves something called Generative Adversarial Networks, or GANs.<\/p>\n

Generative Adversarial Networks (GANs): The Digital Forger and Detective<\/h3>\n

Imagine two AI models playing a game against each other. That\u2019s essentially what a GAN is. You have a Generator<\/strong> and a Discriminator<\/strong>.<\/p>\n

The Generator: The Forger<\/h4>\n

The Generator’s job is to create synthetic data. In the context of deepfakes, this might be a fake image of a face or an altered audio clip. It starts with random noise and tries to produce something that looks or sounds like the real thing. It’s effectively the ‘forger’ in our analogy.<\/p>\n

The Discriminator: The Detective<\/h4>\n

The Discriminator, on the other hand, is the ‘detective’. Its task is to differentiate between real data (genuine images or audio) and fake data (the output of the Generator). It’s constantly trying to catch the Generator out.<\/p>\n

The Training Dance<\/h4>\n

These two models are trained simultaneously. The Generator tries to create fakes convincing enough to fool the Discriminator. The Discriminator, in turn, gets better at spotting the fakes. This adversarial process drives both models to improve. The Generator gets progressively better at creating incredibly realistic fakes, and the Discriminator becomes a more astute detector. Eventually, the Generator becomes so good that the Discriminator can no longer reliably tell the difference, and that’s when you get highly convincing deepfakes.<\/p>\n

Beyond GANs: Other AI Techniques in the Mix<\/h2>\n

While GANs are central, they\u2019re not the only<\/em> AI technique employed<\/a> in creating deepfakes. Other advancements in deep learning have also contributed significantly to their quality and accessibility.<\/p>\n

Autoencoders: Learning and Reconstructing Features<\/h3>\n

Autoencoders are another type of neural network, and they play a vital role, especially in earlier or simpler deepfake implementations.<\/p>\n

Encoder: Compressing Key Information<\/h4>\n

An encoder takes input data (like an image of a face) and compresses it into a lower-dimensional representation, often called a “latent space” or “bottleneck” layer. Think of it like extracting the core, defining features of a person’s face \u2013 their bone structure, eye shape, mouth movements \u2013 without all the pixel-by-pixel detail.<\/p>\n

Decoder: Reconstructing from Latent Space<\/h4>\n

The decoder then takes this compressed representation and tries to reconstruct the original input from it. The goal during training is for the reconstructed output to be as close to the original input as possible.<\/p>\n

The Deepfake Twist with Autoencoders<\/h4>\n

The deepfake trick comes when you train two separate autoencoders on two different people’s faces (let’s say Person A and Person B). You train Autoencoder A on images of Person A, and Autoencoder B on images of Person B. The crucial step is that you can then take the encoder from Autoencoder A, feed it an image of Person A, get its latent representation, and then feed that<\/em> latent representation into the decoder of Autoencoder B. The result? Person A’s movements and expressions, but with Person B’s face reconstructed onto them. This was a foundational technique for many early deepfakes and is still used in various modified forms.<\/p>\n

Neural Style Transfer: Blending Visual Characteristics<\/h3>\n

While not directly creating a new face, neural style transfer is another AI technique that shows the power of manipulating visual information. It takes the “style” from one image (e.g., a famous painting) and applies it to the “content” of another image (e.g., a photograph), creating a new image that looks like the photograph painted in the style of the artwork. This isn’t deepfaking in the traditional sense, but it demonstrates the AI’s ability to decouple and re-combine visual elements, a principle that feeds into more complex deepfake algorithms.<\/p>\n

The Data Fuel: Why Good Data Is Crucial<\/h2>\n

No matter the AI model, the quality of a deepfake is heavily dependent on the data it’s trained on. This is where the saying “garbage in, garbage out” really applies.<\/p>\n

The Need for Large Datasets<\/h3>\n

To create convincing deepfakes of a specific individual, the AI needs to see a lot of them. This means hundreds, often thousands, of images and video frames of the target person from various angles, with different lighting conditions, and expressing a range of emotions. The more diverse and comprehensive the dataset, the better the AI will understand the nuances of that person’s appearance and how their face moves.<\/p>\n

Facial Landmarks and Keypoints<\/h4>\n

During the training process, the AI often identifies and tracks “facial landmarks” or “keypoints” \u2013 specific points on the face like the corners of the eyes, the tip of the nose, and the corners of the mouth. These points help the AI align and warp faces accurately, ensuring that the synthesized face matches the movements of the original.<\/p>\n

Audio Deepfakes: Voice Cloning and Synthesis<\/h3>\n

It\u2019s not just visuals; audio deepfakes are equally concerning and leverage similar principles of learning from data.<\/p>\n

Speech Synthesis and Voice Cloning<\/h4>\n

Here, AI models are trained on large datasets of a person’s speech. They learn the pitch, tone, accent, rhythm, and unique phonetic characteristics of that individual’s voice. Once trained, these models can then generate new speech in that person’s voice saying things they’ve never actually uttered. This is often achieved using techniques like Tacotron 2 and WaveNet, which are powerful neural networks for text-to-speech synthesis.<\/p>\n

Training Challenges for Audio Deepfakes<\/h4>\n

Just like with video, the quality of the source audio is paramount. Clear, isolated speech samples are best. Noise or background interference can degrade the quality of the cloned voice. Furthermore, capturing the emotion<\/em> and intonation<\/em> that make human speech so expressive is still a significant challenge for even the most advanced voice cloning systems.<\/p>\n

The Evolution of Deepfake Quality and Accessibility<\/h2>\n

When deepfakes first emerged, they were often glitchy, with flickering faces, unnatural movements, and obvious artefacts. They also required significant computational power and technical expertise. That’s rapidly changing.<\/p>\n

From Glitchy to Nearly Flawless<\/h3>\n

The progress in deep learning algorithms and the increasing availability of powerful computing resources (especially GPUs) have dramatically improved the quality of deepfakes. What once took hours of rendering on specialized hardware can now sometimes be done in minutes on readily available consumer-grade equipment. This means artefacts are fewer, facial expressions are more natural, and the overall integration of the fake face onto the target body is much more seamless.<\/p>\n

User-Friendly Tools and Platforms<\/h3>\n

Perhaps even more significant than the quality improvement is the plummeting barrier to entry. Initially, creating a deepfake required a deep understanding of machine learning frameworks like TensorFlow or PyTorch. Now, there are increasingly user-friendly software packages and even online services that abstract away much of the underlying complexity. While still requiring some technical savvy, they’re certainly not the exclusive domain of AI researchers anymore. This democratisation makes the creation of deepfakes accessible to a much broader audience, which presents its own set of challenges.<\/p>\n

Detecting Deepfakes: The AI vs. AI Arms Race<\/h2>\n

<\/p>\n\n\n\n\n\n\n
Metrics<\/th>\nData<\/th>\n<\/tr>\n
Number of Deepfake Videos<\/td>\n100,000<\/td>\n<\/tr>\n
Accuracy of Deepfake Detection<\/td>\n90%<\/td>\n<\/tr>\n
Investment in AI Research<\/a><\/td>\n£1 billion<\/td>\n<\/tr>\n
Percentage of People Who Believe Deepfakes<\/td>\n30%<\/td>\n<\/tr>\n<\/table>\n

As deepfake technology improves, so too does the need for effective detection methods. This has created an ongoing “arms race” between deepfake creators and deepfake detectors.<\/p>\n

AI for Detection: Spotting the Tells<\/h3>\n

Researchers are actively developing AI models<\/a> specifically designed to spot deepfakes. These detectors look for subtle inconsistencies and statistical anomalies that might not be immediately obvious to the human eye.<\/p>\n

Unnatural Blinking Patterns<\/h4>\n

One common tell in early deepfakes was the lack of natural blinking. Human beings blink frequently and irregularly. Early deepfake models often struggled to replicate this natural behaviour, leading to subjects who rarely, if ever, blinked, or blinked in a strangely rhythmic way. Modern deepfake models have largely overcome this, but it highlights the kind of subtle details detectors can leverage.<\/p>\n

Inconsistent Lighting and Shadows<\/h4>\n

When a synthetic face is superimposed onto a real background, there can often be subtle inconsistencies in how light interacts with the face compared to the rest of the scene. Shadows might fall incorrectly, or highlights might be in the wrong place, betraying the artificial nature of the face.<\/p>\n

Pixel-Level Artefacts and Noise<\/h4>\n

Even highly realistic deepfakes can still leave behind tell-tale pixel-level artefacts, noise patterns, or subtle distortions that are not present in authentic video. These are like tiny digital fingerprints that a detector can be trained to recognise.<\/p>\n

Physiological Inconsistencies<\/h4>\n

More advanced detection methods are exploring inconsistencies in physiological signals beyond just facial movements. For example, some research looks at whether a deepfake accurately reproduces subtle blood flow changes under the skin, which can reveal pulse and breathing. While incredibly subtle, these are signals that AI could potentially learn to identify.<\/p>\n

The Ongoing Challenge of Detection<\/h3>\n

The challenge for deepfake detectors is that as detection methods improve, deepfake generation techniques often evolve to overcome them. It’s a continuous cycle of innovation on both sides. What works as a detector today might be obsolete tomorrow as deepfake creators learn from the detection algorithms and integrate countermeasures into their generative models. This dynamic ensures that deepfake detection will remain a complex and evolving field.<\/p>\n

So, when we talk about deepfakes, we’re really delving into the remarkable, and sometimes unsettling, power of artificial intelligence to not just process and understand our world, but to authentically create<\/em> new versions of it. It’s a fascinating corner of AI, pushing the boundaries of what’s possible, and simultaneously raising important questions about truth, trust, and reality in the digital age.<\/p>\n

<\/p>\n

FAQs<\/h2>\n

<\/p>\n

What is artificial intelligence (AI) and deepfakes?<\/h3>\n

Artificial intelligence (AI) refers to the simulation of human intelligence<\/a> in machines that are programmed to think and act like humans. Deepfakes, on the other hand, are realistic-looking videos, audio recordings, or images that have been manipulated using AI to depict events that never actually occurred.<\/p>\n

How are deepfakes created using AI?<\/h3>\n

Deepfakes are created using a type of AI called deep learning, which involves training a machine learning model<\/a> on a large dataset of images or videos to learn how to manipulate and generate realistic-looking content. This process allows the AI to swap faces, alter voices, and create entirely new content that appears authentic.<\/p>\n

What are the potential risks and dangers of deepfakes?<\/h3>\n

The proliferation of deepfakes poses significant risks, including the spread of misinformation, the potential for political manipulation, and the erosion of trust in media and information. Deepfakes can also be used for malicious purposes, such as creating fake news, defaming individuals, or perpetrating fraud.<\/p>\n

How can the authenticity of media content be verified in the age of deepfakes?<\/h3>\n

Researchers and technologists are developing various methods to detect and verify the authenticity of media content in the age of deepfakes. These methods include using digital forensics, blockchain technology, and AI-powered tools to analyse and authenticate the provenance of media content.<\/p>\n

What measures are being taken to address the challenges posed by deepfakes?<\/h3>\n

Governments, tech companies, and researchers are working to address the challenges posed by deepfakes through a combination of legislative measures, technological solutions, and public awareness campaigns. Efforts are being made to develop tools for detecting and mitigating deepfakes, as well as to educate the public about the existence and potential impact of manipulated media content.<\/p>\n","protected":false},"excerpt":{"rendered":"

Right, let’s talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what’s actually going on […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"yoast_wpseo_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"yoast_wpseo_metadesc":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"rank_math_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"_rank_math_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"rank_math_description":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"_rank_math_description":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"aioseo_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"_aioseo_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"aioseo_description":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"_aioseo_description":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"seopress_titles_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"_seopress_titles_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"seopress_titles_desc":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"_seopress_titles_desc":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"genesis_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"_genesis_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"genesis_description":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"_genesis_description":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"sq_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"_sq_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"sq_description":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"_sq_description":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"wds_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"_wds_title":["Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\r"],"wds_metadesc":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"_wds_metadesc":["Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the.."],"linksy_active_local_suggestions":["a:2:{s:7:\"link-in\";b:0;s:8:\"link-out\";b:1;}"],"_et_dynamic_cached_shortcodes":["a:0:{}"],"_et_dynamic_cached_attributes":["a:0:{}"]},"categories":[1],"tags":[],"class_list":["post-25351","post","type-post","status-publish","format-standard","hentry","category-generalknowledge"],"yoast_head":"\nArtificial Intelligence and Deepfakes: The Science Behind Fake Reality<\/title>\n<meta name=\"description\" content=\"Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the..\" \/>\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.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Artificial Intelligence and Deepfakes: The Science Behind Fake Reality\" \/>\n<meta property=\"og:description\" content=\"Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the..\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/\" \/>\n<meta property=\"og:site_name\" content=\"Earth Site Education\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/people\/Earth-Site-Education\/61556359432402\/\" \/>\n<meta property=\"article:published_time\" content=\"2026-07-18T13:26:23+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-07-18T13:36:13+00:00\" \/>\n<meta name=\"author\" content=\"Earth Site Education\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Earth Site Education\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"10 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Artificial Intelligence and Deepfakes: The Science Behind Fake Reality","description":"Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the..","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.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/","og_locale":"en_GB","og_type":"article","og_title":"Artificial Intelligence and Deepfakes: The Science Behind Fake Reality","og_description":"Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the..","og_url":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/","og_site_name":"Earth Site Education","article_publisher":"https:\/\/www.facebook.com\/people\/Earth-Site-Education\/61556359432402\/","article_published_time":"2026-07-18T13:26:23+00:00","article_modified_time":"2026-07-18T13:36:13+00:00","author":"Earth Site Education","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Earth Site Education","Estimated reading time":"10 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/#article","isPartOf":{"@id":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/"},"author":{"name":"Earth Site Education","@id":"https:\/\/www.earth-site.co.uk\/Education\/#\/schema\/person\/f028ca91f88fe2e9e578f24056a12819"},"headline":"Artificial Intelligence and Deepfakes: The Science Behind Fake Reality","datePublished":"2026-07-18T13:26:23+00:00","dateModified":"2026-07-18T13:36:13+00:00","mainEntityOfPage":{"@id":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/"},"wordCount":2077,"commentCount":0,"publisher":{"@id":"https:\/\/www.earth-site.co.uk\/Education\/#organization"},"articleSection":["General Knowledge"],"inLanguage":"en-GB","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/","url":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/","name":"Artificial Intelligence and Deepfakes: The Science Behind Fake Reality","isPartOf":{"@id":"https:\/\/www.earth-site.co.uk\/Education\/#website"},"datePublished":"2026-07-18T13:26:23+00:00","dateModified":"2026-07-18T13:36:13+00:00","description":"Right, let's talk about deepfakes. Specifically, how artificial intelligence (AI) is making them a reality, and what's actually going on under the..","breadcrumb":{"@id":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.earth-site.co.uk\/Education\/artificial-intelligence-and-deepfakes-the-science-behind-fake-reality\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.earth-site.co.uk\/Education\/"},{"@type":"ListItem","position":2,"name":"Artificial Intelligence and Deepfakes: The Science Behind Fake Reality"}]},{"@type":"WebSite","@id":"https:\/\/www.earth-site.co.uk\/Education\/#website","url":"https:\/\/www.earth-site.co.uk\/Education\/","name":"Earth Site Education","description":"","publisher":{"@id":"https:\/\/www.earth-site.co.uk\/Education\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.earth-site.co.uk\/Education\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/www.earth-site.co.uk\/Education\/#organization","name":"Earth Site Education","url":"https:\/\/www.earth-site.co.uk\/Education\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.earth-site.co.uk\/Education\/#\/schema\/logo\/image\/","url":"https:\/\/www.earth-site.co.uk\/Education\/wp-content\/uploads\/2024\/06\/LogoYouTube.png","contentUrl":"https:\/\/www.earth-site.co.uk\/Education\/wp-content\/uploads\/2024\/06\/LogoYouTube.png","width":800,"height":800,"caption":"Earth Site Education"},"image":{"@id":"https:\/\/www.earth-site.co.uk\/Education\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/people\/Earth-Site-Education\/61556359432402\/"]},{"@type":"Person","@id":"https:\/\/www.earth-site.co.uk\/Education\/#\/schema\/person\/f028ca91f88fe2e9e578f24056a12819","name":"Earth Site Education","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/secure.gravatar.com\/avatar\/93795f5d72a690673db58fc60779e6bb369542d93350bb5432476175ff04c468?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/93795f5d72a690673db58fc60779e6bb369542d93350bb5432476175ff04c468?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/93795f5d72a690673db58fc60779e6bb369542d93350bb5432476175ff04c468?s=96&d=mm&r=g","caption":"Earth Site Education"},"url":"https:\/\/www.earth-site.co.uk\/Education\/author\/keirearthsiteadmin-7\/"}]}},"_links":{"self":[{"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/posts\/25351","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/comments?post=25351"}],"version-history":[{"count":2,"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/posts\/25351\/revisions"}],"predecessor-version":[{"id":25354,"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/posts\/25351\/revisions\/25354"}],"wp:attachment":[{"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/media?parent=25351"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/categories?post=25351"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.earth-site.co.uk\/Education\/wp-json\/wp\/v2\/tags?post=25351"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}