[{"data":1,"prerenderedAt":27},["ShallowReactive",2],{"nr-en-nasa-ibm-open-source-ki-mondkartierung":3},{"slug":4,"title":5,"dek":6,"date":7,"time":8,"publishedAt":9,"updated":10,"updatedAt":10,"dateFmt":11,"updatedFmt":10,"kind":12,"tier":13,"author":14,"authorName":15,"topics":16,"tracker":10,"trackerLabel":10,"headlineStat":10,"image":22,"ogImage":23,"imageAlt":5,"csv":10,"minutes":24,"words":25,"html":26},"nasa-ibm-open-source-ki-mondkartierung","NASA and IBM Release Open-Source AI Model for Lunar Mapping","A joint AI model will accelerate the processing of millions of lunar photographs from the Lunar Reconnaissance Orbiter spacecraft. The project demonstrates how space agencies are embracing open technology.","2026-09-17","11:47","2026-09-17T11:47:00+02:00","","September 17, 2026","news","standard","ideal-syka","Ideal Syka",[17,18,19,20,21],"AI in space exploration","Open-source models","Automated image analysis","NASA","IBM","\u002Fnewsroom\u002Fimg\u002Fnasa-ibm-open-source-ki-mondkartierung.webp","\u002Fog-nr\u002Fnasa-ibm-open-source-ki-mondkartierung.en.png",2,456,"\u003Cp>NASA and IBM have developed an \u003Cstrong>open-source AI model\u003C\u002Fstrong> designed to automate the mapping of the lunar surface. The system processes image data from the \u003Cstrong>Lunar Reconnaissance Orbiter\u003C\u002Fstrong> (LRO), which has been collecting high-resolution photographs of the Moon for years. Instead of analyzing images manually, the artificial intelligence will handle this task in the future – faster and more consistently.\u003C\u002Fp>\n\u003Ch2>Key Facts\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cstrong>Collaboration\u003C\u002Fstrong>: NASA and \u003Cstrong>IBM\u003C\u002Fstrong> jointly developed an \u003Cstrong>open-source AI model\u003C\u002Fstrong> for lunar image analysis\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Data source\u003C\u002Fstrong>: The model processes images from the \u003Cstrong>Lunar Reconnaissance Orbiter\u003C\u002Fstrong> spacecraft\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Open strategy\u003C\u002Fstrong>: The model is released as open source – researchers worldwide can use and further develop it\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Application\u003C\u002Fstrong>: Automated mapping and classification of lunar surface features\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>Why Open Source for Lunar Research?\u003C\u002Fh2>\n\u003Cp>The decision to publish the model as open source reflects a growing strategy among space agencies: rather than restricting research results, they make them accessible to the global scientific community. This accelerates innovation and enables universities, smaller research institutions, and even private companies to build on the same tools. For NASA, this also means more eyes on the data and more potential improvements to the model.\u003C\u002Fp>\n\u003Cp>The \u003Cstrong>Lunar Reconnaissance Orbiter\u003C\u002Fstrong> has collected an enormous volume of lunar photographs since its deployment. Manually analyzing each one is impossible for humans – this is where AI comes in. The IBM-NASA model is designed to automatically recognize and classify surface features.\u003C\u002Fp>\n\u003Ch2>Practical Benefits for Lunar Missions\u003C\u002Fh2>\n\u003Cp>Automated mapping offers several advantages: it saves time in data analysis, reduces human error, and enables faster planning of new missions. When scientists know precisely where certain rock types or water ice deposits are located, they can select landing sites for future lunar missions more strategically. This is relevant not only for NASA but also for international space agencies and private companies planning lunar missions.\u003C\u002Fp>\n\u003Cp>The model also demonstrates how \u003Cstrong>machine learning\u003C\u002Fstrong> is becoming routine in space research. Beyond image analysis, AI systems are now standard for predicting system failures, optimizing mission routes, and compressing data.\u003C\u002Fp>\n\u003Ch2>What This Means for German Companies\u003C\u002Fh2>\n\u003Cp>For German aerospace and technology companies, this project sends a clear signal: open-source AI is becoming the norm even in highly specialized fields. Anyone who wants to bid on space projects in the future – whether in data analysis, mission planning, or instrument development – should understand how to work with open AI models and adapt them. At the same time, it becomes clear: those who build expertise in \u003Cstrong>domain-specific AI applications\u003C\u002Fstrong> can later transfer these skills to other industries. The combination of aerospace competence and AI know-how becomes a competitive advantage.\u003C\u002Fp>\n\u003Ch2>Sources\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fwww.golem.de\u002Fnews\u002Fmondkartierung-ki-modell-von-ibm-und-nasa-verarbeitet-monddaten-2609-213037.html\">Golem\u003C\u002Fa>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>\u003Cem>Editorially owned by \u003Ca href=\"\u002Fen\u002Fautor\u002Fideal-syka\">Ideal Syka\u003C\u002Fa>. Sources and method: \u003Ca href=\"\u002Fen\u002Fredaktion\">Newsroom & method\u003C\u002Fa>. Tips and corrections: \u003Ca href=\"mailto:ai@i6eal.de\">ai@i6eal.de\u003C\u002Fa>.\u003C\u002Fem>\u003C\u002Fp>\n",1789638862264]