For decades utilities sent out armies of technicians with listening sticks to find pipe leaks by…
for decades utilities sent out armies of technicians with listening sticks to find pipe leaks by ear, and now satellite-based ai finds water leaks up to 10 feet underground across up to 1,000 square miles per pass, while ai-driven district analysis collapses the detection-to-action cycle from months to hours. suez alone has logged leak sounds across 100,000 km of french networks to train its acoustic model.
the most essential utility on earth is being digitized by the least glamorous ai.
Context
ASTERRA's Recover product uses satellite imagery to locate and analyze moisture leaking from underground pipes across whole city systems. A satellite radar leak detection talk cites L-band synthetic aperture radar for ground penetration, and a Utilis program sheet gives a survey area of 800 to 1,400 square miles.
SUEZ describes Aquadvanced networks that detect leaks in real time, and says Greater Poitiers saved around 960,000 cubic meters of water over two years.
Satellite leak detection on large areas matches ASTERRA and the Utilis material. The 10 feet depth, the 1,000 square miles per pass and the months-to-hours claim were not seen in the sources read, so unsupported here, not refuted. in the excerpts read. Suez's 100,000 km of French network sound data for training an acoustic model was not seen in the sources read, so unsupported here, not refuted. too; the SUEZ pages read cover digital monitoring and a fiber optic pilot. 'The least glamorous AI' is the author's.
Related work
Watch next
- Find the depth and area per pass figures and Suez's acoustic dataset size.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 1 October 2026 at 19:48 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 →