China’s new ai-oreseeking system compresses mineral exploration from six months to about one week,…
china’s new ai-oreseeking system compresses mineral exploration from six months to about one week, and it has already been tested in hundreds of projects across more than ten provinces, while bhp’s $100m geoscience ai program found six greenfield targets that never appeared in conventional prospect inventories. oak ridge’s map-pod robot maps underground mines with hyperspectral sensors in minutes instead of weeks.
the deposits left to find are the ones human pattern recognition has been missing.
Context
Verified event date: China's Ministry of Natural Resources released the AI-OreSeeking system, developed by the China Geological Survey, on Sep 11, 2026 at the China Mining Conference and Exhibition in Tianjin (NCSTI; CGS). Global Times (Sep 13) says the AI systems cut mineral exploration from six months to one week.
BHP says it uses AI and advanced analytics to help geoscientists analyse large volumes of geological data, and runs a Central Data Platform for exploration data.
The six months to one week and the Sep 11 release match the Global Times and CGS coverage. The hundreds of projects in more than ten provinces, BHP's $100 million geoscience AI program with six greenfield targets and the Oak Ridge map-pod robot were not seen in the sources read, so unsupported here, not refuted. in the excerpts read. The hyperspectral underground mapping sources read are academic work, not an Oak Ridge mine robot. 'What human pattern recognition has been missing' is the author's.
Related work
Watch next
- Find the BHP $100 million program and the Oak Ridge mine mapping robot.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 1 October 2026 at 19:36 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 →