A geographic sciences multi-modal Large Language Model (LLM), the first of its kind in the world, was unveiled in Beijing on Thursday. It could support the integration of geography and artificial intelligence and help accelerate geographical discoveries.
The model, named Sigma Geography, was developed by a team of researchers from the Institute of Geographic Sciences and Natural Resources Research (IGSNRR), the Institute of Tibetan Plateau Research and the Institute of Automation, all under the Chinese Academy of Sciences, and other organizations.
Sigma Geography can answer professional geographical questions, analyze geographical articles, undertake querying and in-depth analysis of geographical data and draw thematic maps, said Su Fenzhen, deputy director of IGSNRR.
Compared to general LLMs, Sigma Geography has a deeper understanding of the language patterns, domain-specific terminology and professional knowledge in the field of geography, enabling it to better handle specialized issues, Su said.
In addition to answering geographical questions, Sigma Geography can also match the generated textual answers with geographical landscape photos, thematic maps or schematic charts to help users understand the textual answers in a more visual and imaginative way, he added.
The research assistant function developed by the team, based on Sigma Geography, can complete processes such as concept understanding, data acquisition, information analysis and mapping according to user instructions, and ultimately generate professional geographic charts that users need.
The model could help broaden the general public’s understanding of geographic sciences, and support academic research and studies to uncover major geographic scientific discoveries.
So far, Sigma Geography has been used by over 10 papers published in academic journals such as sub-journals of Nature, The Innovation, and Earth’s Future.
The team will continue to upgrade Sigma Geography, aiming to enable it to comprehend maps, and create a platform to facilitate scientists and research teams to collaborate through the sharing of data, models and research ideas.
（Source: Xinhua）
