UT San Antonio builds a solar powered flood sensor that runs its model on the chip rather than in the cloud
The University of Texas at San Antonio published on September 8th, 2026 that it has a field ready prototype flood warning node. The node is for street level water and the team is led by Chen Pan. It harvests its own solar power and carries temperature, humidity, light and precipitation sensing plus four optical water level sensors at different heights. It runs a compressed machine learning model on the microcontroller itself rather than sending readings to a server. It reports over long range radio instead of a cell tower, so it keeps warning when the grid and the network are down, which is when the water rises. The work was funded in part by a Texas Coastal Management Program grant from the National Oceanic and Atmospheric Administration. It is a prototype and the announcement names no place that has installed one.
How to take part
The university publishes the account of the system, names the researchers and names the federal program that funded it. There is no comment window and no meeting. A reader who wants the underlying method contacts the laboratory the announcement names.
Where
1 county. In San Antonio-New Braunfels.
Timeline
- filed
The university published the prototype and its funding source
- Today
How this decision moved
One dated line per check, oldest first. A line that says nothing changed means somebody looked and it had not.
- 2026-09-10
The university's account is published and names the researchers, the sensing package, where the model runs and the federal program that funded the work. It is a prototype and no installation site is named.
The evidence
Every fact above rests on one of these. The words are the source's own.
Researchers at The University of Texas at San Antonio have developed a self-sustaining, artificial intelligence-powered flood warning system designed to spot dangerous water accumulation at the street level.UT San Antonio Today Primary source, official · news.utsa.edu
Led by Chen Pan , PhD, assistant professor of electrical engineering in the Margie and Bill Klesse College of Engineering and Integrated Design, the team engineered a field-ready prototype that combines solar energy harvesting, multi-sensor environmental tracking, long-range wireless radios and on-device machine learning.UT San Antonio Today Primary source, official · news.utsa.edu
In many rural areas or coastal communities, power infrastructure can fail right when severe weather strikes,UT San Antonio Today Primary source, official · news.utsa.edu
This on-device AI evaluates current and recent sensor data to predict localized, imminent flood risk without relying on a central server.UT San Antonio Today Primary source, official · news.utsa.edu
So far, the AI has performed well, achieving 98.82% validation accuracy in initial assessments post-training.UT San Antonio Today Primary source, official · news.utsa.edu
This project was funded in part by a Texas Coastal Management Program grant awarded by the National Oceanic and Atmospheric Administration (NOAA).UT San Antonio Today Primary source, official · news.utsa.edu
The resulting prototype combines temperature, humidity, light and precipitation sensing, as well as four optical water-level sensors mounted at varying heights.UT San Antonio Today Primary source, official · news.utsa.edu
Existing commercial flood-monitoring stations also come with drawbacks, from prohibitively high costs to reliance on grid power or frequent battery replacements, which leaves them vulnerable during multi-day storms or power outages.UT San Antonio Today Primary source, official · news.utsa.edu
Questions about this decision
Answered from the record itself. Every answer is assembled from stored fields, so an answer the record has no basis for is left out rather than guessed.
What is this decision?
The University of Texas at San Antonio published on September 8th, 2026 that it has a field ready prototype flood warning node. The node is for street level water and the team is led by Chen Pan. It harvests its own solar power and carries temperature, humidity, light and precipitation sensing plus four optical water level sensors at different heights. It runs a compressed machine learning model on the microcontroller itself rather than sending readings to a server. It reports over long range radio instead of a cell tower, so it keeps warning when the grid and the network are down, which is when the water rises. The work was funded in part by a Texas Coastal Management Program grant from the National Oceanic and Atmospheric Administration. It is a prototype and the announcement names no place that has installed one.
Who decides it?
The University of Texas at San Antonio decides. The record names the deciding body for every entry it carries.
Can the public take part?
The university publishes the account of the system, names the researchers and names the federal program that funded it. There is no comment window and no meeting. A reader who wants the underlying method contacts the laboratory the announcement names. No dated public window is on the record. The deciding body is named and reachable.
Where in Texas does it apply?
It covers Bexar County.
Has it been decided?
It has been decided. The dates on the item page carry when.
What happens next?
No future date is on the record. The last dated step on it was filed on September 8th.
When did it start?
The earliest date on its record is September 8th, 2026.
What kind of decision is it?
It is filed under research and science.
What sources back it?
One source backs it. It is primary.
Is it on the ERCOT grid?
Yes. It sits inside the ERCOT interconnection.
When was it last checked?
Every fact on it was last verified against its source on September 10th, 2026.
Cite this
Texas AI Docket, UT San Antonio builds a solar powered flood sensor that runs its model on the chip rather than in the cloud. Tracked since September 8th, 2026. Last verified September 10th, 2026. https://texasaidocket.com/item/tx-2026-0141/. Reuse permitted under CC BY 4.0 with attribution. The same entry is in the docket JSON as item tx-2026-0141.
Beat
Filed under Research and science, with every other decision on that beat.