{"id":18912,"date":"2024-08-30T09:26:25","date_gmt":"2024-08-30T01:26:25","guid":{"rendered":"https:\/\/www.1ai.net\/?p=18912"},"modified":"2024-08-30T09:26:25","modified_gmt":"2024-08-30T01:26:25","slug":"%e4%b8%ad%e5%9b%bd%e7%a7%91%e5%ad%a6%e9%99%a2%e3%80%81%e9%98%bf%e9%87%8c%e4%ba%91%e5%8f%91%e5%b8%83%e9%a6%96%e4%b8%aa%e6%9c%88%e7%90%83%e4%b8%93%e4%b8%9a%e5%a4%a7%e6%a8%a1%e5%9e%8b%ef%bc%8c%e6%92%9e","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/18912.html","title":{"rendered":"Chinese Academy of Sciences and Alibaba Cloud released the first professional large-scale lunar model, with an accuracy rate of over 80% in determining the age of impact craters"},"content":{"rendered":"<p>according to<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e9%98%bf%e9%87%8c%e4%ba%91\" title=\"_Other Organiser\" target=\"_blank\" >Alibaba Cloud<\/a>Today&#039;s news, at the 2024 Big Data Expo on August 29,<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e4%b8%ad%e5%9b%bd%e7%a7%91%e5%ad%a6%e9%99%a2\" title=\"Look at the article with the label\" target=\"_blank\" >Chinese Academy of Sciences<\/a>The Institute of Geochemistry and Alibaba Cloud jointly launched the world&#039;s first &quot;Lunar Science Multimodal Professional<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [large models]]\" target=\"_blank\" >Large Model<\/a>&quot;This large model is built based on Alibaba Cloud Tongyi series models.<strong>At present, the accuracy rate of lunar crater age and morphology identification has reached more than 80%<\/strong>.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-18913\" title=\"553002a0j00sj0bza006jd000u001hcm\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/08\/553002a0j00sj0bza006jd000u001hcm.jpg\" alt=\"553002a0j00sj0bza006jd000u001hcm\" width=\"1080\" height=\"1920\" \/><\/p>\n<p>According to Alibaba Cloud, the lunar professional big model is based on a series of common models such as vision, multimodality and natural language, combined with RAG search enhancement and other technologies, and fine-tuned and trained on Alibaba Cloud Bailian exclusive version. At present, the best landing scenario for the lunar professional big model is<strong>Lunar impact crater identification,<\/strong>and<strong>The accuracy has reached 80%<\/strong>\u00a0above.<\/p>\n<p>In addition to detecting and returning samples, human research on lunar geological evolution mainly relies on the study of lunar geological objects such as impact crater identification. The size, depth, shape and other characteristics of impact craters are important bases for studying lunar geological evolution.<\/p>\n<p>According to statistics, there are more than 1 million lunar impact craters with a diameter of more than one kilometer on the moon, and the number of impact craters with a diameter of less than one kilometer has not been determined. If it is completely dependent on manual work, it is &quot;almost impossible&quot; to complete the identification of all lunar impact craters.<\/p>\n<p>The application of large professional lunar models has greatly improved scientific research efficiency:<strong>Researchers only need to input lunar crater images and related questions<\/strong>The lunar professional large model can call the general vision and multimodal model to determine the modal type corresponding to the image from 17 types of multimodal data (including spectrum, elevation, gravity and other data).<\/p>\n<p>At the same time, by searching the knowledge base and calling the general language model, the lunar professional large model can answer the impact crater<strong>Shape, size, age<\/strong>Liu Jianzhong, a researcher at the Institute of Geochemistry, Chinese Academy of Sciences, said: &quot;By accurately grasping the massive data, the large model can not only classify the impact craters, but also solve some scientific problems that have not yet been solved.&quot;<\/p>\n<p>Next, the moon professional large model will be embedded<strong>&quot;Digital Lunar Cloud Platform&quot;<\/strong>, promoting the intelligent upgrade of the &quot;Lunar Cloud Platform&quot;. IT Home learned that the &quot;Digital Lunar Cloud Platform&quot; was built by the Institute of Geochemistry, Chinese Academy of Sciences. It is the cloud platform with the most complete lunar exploration data in the world, integrating scientific research, engineering applications and popular science education.<strong>Together with large scientific facilities such as FAST, it has become an important part of the scientific research infrastructure, helping to accelerate my country&#039;s lunar and planetary scientific research innovation.<\/strong>.<\/p>","protected":false},"excerpt":{"rendered":"<p>According to AliCloud today, at the 2024 Digital Expo on August 29, the Institute of Geochemistry of the Chinese Academy of Sciences (IGAC) and AliCloud jointly released the first international \"Multimodal Professional Large Model for Lunar Science\". The large model is built based on AliCloud's Tongyi series of models, and the accuracy rate has reached more than 80% on the age and morphology of lunar impact craters. According to AliCloud, the lunar professional big model is based on the visual, multimodal and natural language generalized series models, combined with RAG retrieval enhancement and other technologies, and fine-tuned and trained in AliCloud Hundred Refined Exclusive Edition. At present, the best landing scenario of the lunar professional big model is the lunar impact crater identification, and the accuracy rate has reached more than 80%. In addition to the samples returned from exploration, human research on the geological evolution of the Moon mainly relies on impact crater identification.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[148,146],"tags":[4192,216,334],"collection":[],"class_list":["post-18912","post","type-post","status-publish","format-standard","hentry","category-headline","category-news","tag-4192","tag-216","tag-334"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/18912","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=18912"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/18912\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=18912"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=18912"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=18912"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=18912"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}