{"id":1990,"date":"2023-10-25T15:16:05","date_gmt":"2023-10-25T15:16:05","guid":{"rendered":"https:\/\/aurorasaurudev.wpengine.com\/?p=1990"},"modified":"2023-10-27T13:34:42","modified_gmt":"2023-10-27T13:34:42","slug":"keeping-it-real-how-to-spot-a-fake-aurora-photo","status":"publish","type":"post","link":"https:\/\/blog.aurorasaurus.org\/?p=1990","title":{"rendered":"Keeping it Real: How to Spot a Fake Aurora Photo"},"content":{"rendered":"

By Vincent Ledvina and Laura Edson
\n<\/span>With many thanks to aurora photographer Marybeth Kiczenski for reviewing the post<\/span><\/i><\/p>\n

As artificial intelligence (AI) becomes more popular, many are using it to create content, including about auroras. While it can be useful, in a social media world that values speed, clicks, and engagement it can be hard to discern AI photo art from real photos. AI may also use a <\/span>photographer\u2019s<\/span><\/a> or <\/span>artist\u2019s<\/span><\/a> work <\/span>without permission<\/span><\/a>. Not only may that present <\/span>copyright<\/span><\/a> issues, but it can remove meaningful work from its original context\u2014for example, with regard to issues of <\/span>cultural sovereignty<\/span><\/a> or an artist\u2019s <\/span>tributes to loved ones who have passed on<\/span><\/a>. AI also raises concerns about accurate scientific data and data ethics, so the best participatory science images are in RAW format, and unedited. In this post, we share some tips for telling the difference between real and AI-generated aurora pictures. This is by no means comprehensive, but we hope it provides a starting point.<\/span><\/p>\n

\"A<\/a>
Adobe advertisement for AI-generated aurora images<\/figcaption><\/figure>\n
\n

Color\u00a0<\/span><\/h2>\n

While auroras are sometimes poetically likened to rainbows, their colors are different. Aurora colors <\/span>layer by altitude<\/span><\/a> like a cake and are so consistent that they can be <\/span>used to tell<\/span><\/a> the elements and altitudes of different parts of the aurora (see diagram below.) Any deviation from these patterns\u2014for example, a \u201crainbow\u201d aurora where the colors change along the horizontal plane\u2014may be a sign the picture is AI-generated.<\/span><\/p>\n

\"\"<\/a>
Oxygen excited to different energy levels can produce both green and red colors. The green color occurs between 120 and 180 kilometers (75 and 110 miles) altitude and is caused by oxygen. The red color occurs above 200 kilometers (120 miles). Excited nitrogen gas between 120 and 180 kilometers (75 and 110 miles) glows blue. Below 100 kilometers (60 miles), nitrogen can give off both red and blue light, giving the lower edge of the aurora a reddish-purple to pink glow, especially during intense aurora.<\/figcaption><\/figure>\n

Occasionally there might appear to be other colors in an aurora because of rare atmospheric conditions or the way that our eyes interpret <\/span>colors of light mixing<\/span><\/a>. Because of this, people sometimes see colors like yellow or cyan in aurora. Special \u201castromodified<\/a>\u201d cameras can also make red tones look brighter. However, aurora colors will <\/span>never <\/b>appear in the same order as a rainbow.\u00a0<\/span><\/p>\n

\"A<\/a>
Auroral display photographed by Vincent Ledvina on March 2, 2021 near Grand Forks, ND. The orange fringe on the bottom of the aurora near the horizon may be due to shorter wavelengths of light being scattered by atmospheric dust. This is similar to the process that makes the setting sun look orange.<\/figcaption><\/figure>\n\n\n\n
\n

\"Above<\/a>
AI-generated aurora with unrealistic colors. The purely pink arcs on the left side of the image would be green if it were real.<\/figcaption><\/figure><\/td>\n
\n

\"Behind<\/a>
Real photo taken by Vincent Ledvina on October 11, 2021 near Grand Forks, ND with more realistic colors, showing red appearing at higher altitudes as expected.<\/figcaption><\/figure><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Shape<\/span><\/h2>\n

While aurora displays can evolve in many different ways, they often take on very distinctive shapes. Aurorasaurus places auroral shapes into three main categories for reporting: discrete, diffuse, and pulsating. You can find out more about each type <\/span>here<\/span><\/a>, but for this post we will focus on the brightest, most sharply defined, and most photographed: the curving, ribbonlike <\/span>discrete aurora<\/span><\/a>.\u00a0<\/span><\/p>\n

Aurora chasers and scientists <\/span>identify shapes<\/span><\/a> within discrete auroras, like curtains, arcs, curls, spirals, or rays. For example, one type is the auroral spiral, affectionately called \u201ccinnamon rolls\u201d by some aurora chasers.\u00a0<\/span><\/i><\/p>\n

\"A<\/a>
Real photo of a \u201ccinnamon roll\u201d aurora photographed by Vincent Ledvina on March 5, 2022 in Fort Yukon, Alaska.<\/figcaption><\/figure>\n

However, there are shapes auroras don\u2019t typically make, like right angles or polygons. In addition, while real-life discrete auroras occur in multiple ribbonlike sheets, the forms are <\/span>separated from one another<\/span><\/a> like the layers of a flaky pastry. In other words, real auroral forms should have gaps between them and never directly touch or cross one another.\u00a0<\/span><\/p>\n\n\n\n
\n

\"Smokelike<\/a>
Image of aurora depicted in square shapes that criss-cross. This would never happen in real life, so this photo is AI-generated.<\/figcaption><\/figure><\/td>\n
\n

\"Horizontal<\/a>
Bands of aurora are clearly separated in a real photo taken by Vincent Ledvina on March 3, 2022 in Fort Yukon, Alaska.<\/figcaption><\/figure><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Location<\/span><\/h2>\n

Auroras occur in an <\/span>oval<\/span><\/a> around the magnetic north and south poles. If the aurora is particularly strong, the oval can <\/span>expand to lower latitudes<\/span><\/a>, but it is highly unlikely to be close to the equator. If an image includes a popular landmark or landscape that usually doesn\u2019t see aurora, it\u2019s unlikely to be real unless there was a particularly strong event.\u00a0<\/span><\/p>\n

For example, a photo of the aurora above the Galapagos Islands (about 1\u00b0 South latitude) would require extremely improbable conditions. A photo over the Grand Canyon (about 36\u00b0 North latitude) would be more possible, but only if archives show strong auroras that night. To find out, you could look up the date on <\/span>Aurorasaurus<\/span><\/a> and see if there were other reports from that location. More reports from that area will give the image more credibility. If there wasn\u2019t activity on the night the photo was taken, then it is an artistic rendering, possibly AI.\u00a0<\/span><\/p>\n

\n

Star patterns<\/span><\/h2>\n

One of the best ways to tell between an aurora and a cloud is that <\/span>stars are visible through an aurora<\/span><\/a>, while clouds are opaque. Therefore, in a real photo you should be able to zoom in and see stars through the aurora. If you can\u2019t, the photo may be AI-generated.\u00a0<\/span><\/p>\n

In addition, at the time of writing AI is unable to depict accurate star locations. This is most obvious in AI-generated images of the Milky Way, which often misplace certain nebulas. With an image of the night sky in general, it can be harder to tell if the placement of the stars is realistic. Some sites like <\/span>astrometry.net<\/span><\/a> have tools that can tell you what stars you are seeing in a photo, so running an image through such a tool would tell you if star placement is accurate. AI photos would likely not pass this test since the \u201cstars\u201d are randomly generated.<\/span><\/p>\n\n\n\n
\n

\"An<\/a>
In this AI-generated image, the stars in the highlighted box are made up: there is no pattern of stars in the real sky that looks like this.<\/figcaption><\/figure><\/td>\n
\n

\"Above<\/a>
Real photo taken by Vincent Ledvina on March 1, 2022 in Fort Yukon, Alaska where known star patterns are clearly visible. Also, note the faint textures in the aurora.<\/figcaption><\/figure><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Smoothness<\/span><\/h2>\n

At the time of writing, AI-generated photos usually have a <\/span>telltale aesthetic<\/span><\/a> that can be easy to spot with practice. The sky and landscapes may look smooth\u2014almost painted\u2014and lack detail. The aurora may also look airbrushed in and have perfectly smooth gradients between colors. There may be uneven sharpness or <\/span>inconsistent details<\/span><\/a> throughout the image. For example, one giveaway is if some portions of the sky have stars and some do not. Some sections of the photo might also show stars \u201cin focus\u201d while other sections show blurry stars. An aurora image with perfectly lit and focused animals in the foreground would be nearly impossible to take with a camera and is a giveaway that the image is artistic\u2014either AI or edited with <\/span>special techniques<\/span><\/a>.\u00a0<\/span><\/p>\n

\"Unrealistically<\/a>
In this image, the auroras look unrealistically smooth. While occasionally editing styles can give real photos this look, AI-generated auroras more commonly appear this way.<\/figcaption><\/figure>\n
\n

The net upshot<\/span><\/h2>\n

AI will inevitably <\/span>grow<\/span><\/a> in usage and become more sophisticated, so it\u2019s a good reminder to think critically about images shared online. In addition, if a photo is real, the photographer will easily be able to tell you how they took and processed it. That also means that if they choose to share it with Aurorasaurus for science, we can ask questions and learn more about what they saw. AI-generated images, on the other hand, do not contain useful aurora science information. Unedited RAW shots are preferred for scientific analysis. So while aurora art may see a renaissance, for projects like Aurorasaurus it\u2019s important to keep it real.\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

By Vincent Ledvina and Laura Edson With many thanks to aurora photographer Marybeth Kiczenski for reviewing the post As artificial intelligence (AI) becomes more popular, many are using it to create content, including about auroras. While it can be useful, in a social media world that values speed, clicks, and engagement it can be hard… Read More »Keeping it Real: How to Spot a Fake Aurora Photo<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":1996,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"rop_custom_images_group":[],"rop_custom_messages_group":[],"rop_publish_now":"initial","rop_publish_now_accounts":[],"rop_publish_now_history":[],"rop_publish_now_status":"pending","neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"off","neve_meta_content_width":70,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"categories":[24,7,17,12],"tags":[20,23,28],"class_list":["post-1990","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-citizen-science","category-education","category-other-resources-for-aurora-hunters","category-understanding-the-aurora","tag-auroras","tag-northern-lights","tag-science"],"_links":{"self":[{"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=\/wp\/v2\/posts\/1990","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1990"}],"version-history":[{"count":0,"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=\/wp\/v2\/posts\/1990\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=\/wp\/v2\/media\/1996"}],"wp:attachment":[{"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1990"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1990"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.aurorasaurus.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1990"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}