Archaeology is moving before the shovel
archaeology is moving before the shovel: ibm-assisted ai found 300 new nasca geoglyphs in six months, nearly doubling the known count, and tsinghua’s fragment-matching algorithm cut bronze altar reassembly time by 80 percent at sanxingdui. carbonized scrolls are being read by models.
the past is becoming a dataset.
Context
IBM Research and Yamagata University's PNAS paper (reported Sep 23, 2024) describes an AI-accelerated Nazca survey that nearly doubles the number of known figurative geoglyphs; IBM says it took nearly a century to find the 430 known figures. National Geographic's May 11, 2026 article says AI discovery has been supercharged, with many found in just six months.
Tsinghua's graphics group has published work on automatic reassembly of broken 3D solids by geometric matching, and FragmentDiff for fractured object assembly. Xinhua reported in June 2022 that a bronze sculpture part at Sanxingdui was matched with another after about 3,000 years.
The AI-accelerated Nazca survey and its near doubling of known figures match IBM and Yamagata. The exact 300 new count is not seen in the sources read, so unsupported here, not refuted. The 80 percent reduction in bronze altar reassembly time at Sanxingdui and the carbonized scroll reading are not seen in the sources read, so unsupported here, not refuted. Tsinghua's papers read are general reassembly research, not confirmed as the Sanxingdui work.
Related work
Watch next
- Find the Sanxingdui reassembly report that gives the 80 percent figure.
Sources
- IBM Research, Sep 23, 2024research.ibm.com
- National Geographic, May 11, 2026nationalgeographic.com
- Xinhua, Jun 17, 2022english.news.cn
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 2 October 2026 at 09:04 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →