UT San Antonio builds a solar powered flood sensor that runs its model on the device instead of a server
The University of Texas at San Antonio published an account on September 8th, 2026 of a field ready prototype flood warning node. A team led by an assistant professor of electrical engineering combined four things. Solar energy harvesting, environmental sensing, long range radio and a machine learning model compressed to run on the microcontroller itself. The design point is that the node evaluates flood risk where it stands rather than sending readings to a server. It keeps working when power and network fail in a storm. The university reports a validation accuracy figure from assessment after training rather than a measurement against a real flood. Funding is named as a Texas Coastal Management Program grant awarded by the National Oceanic and Atmospheric Administration. The account names no installation site and no agency operating it, so what exists is a prototype.
How to take part
The university's own account is public and names the lead researcher and the laboratory. No comment window or public proceeding attaches to a research prototype.
Where
1 county. In San Antonio-New Braunfels.
Timeline
- filed
Date the university published the account
- 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.
- 2026-09-18
Admitted on the university's own account. What exists is a prototype, and the accuracy figure the account gives comes from assessment after training rather than from a flood.
- 2026-09-21
The university's account of the flood node still reads as the record holds it. The model still runs on the device rather than somewhere a network has to reach, which is the whole point of the design.
- 2026-09-24
The flood sensor is still described as running its model on the device itself. No network has to reach it for the model to work.
- 2026-09-27
The university's account of the flood sensor that runs its model on the device still reads as published.
The evidence
Every fact above rests on one of these. The words are the source's own.
Our system is an off-grid solution. It generates its own power, evaluates flood risk locally right on the device and sends timely warnings without needing external electricity or expensive network lines.UT San Antonio Today Primary source, official · news.utsa.edu
a branch of computer science that compresses machine learning algorithms so they can run directly on small, low-power microcontrollersUT 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
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 an account on September 8th, 2026 of a field ready prototype flood warning node. A team led by an assistant professor of electrical engineering combined four things. Solar energy harvesting, environmental sensing, long range radio and a machine learning model compressed to run on the microcontroller itself. The design point is that the node evaluates flood risk where it stands rather than sending readings to a server. It keeps working when power and network fail in a storm. The university reports a validation accuracy figure from assessment after training rather than a measurement against a real flood. Funding is named as a Texas Coastal Management Program grant awarded by the National Oceanic and Atmospheric Administration. The account names no installation site and no agency operating it, so what exists is a prototype.
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's own account is public and names the lead researcher and the laboratory. No comment window or public proceeding attaches to a research prototype. 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 in the San Antonio-New Braunfels, TX area.
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 27th, 2026.
Cite this
Texas AI Docket, UT San Antonio builds a solar powered flood sensor that runs its model on the device instead of a server. Tracked since September 8th, 2026. Last verified September 27th, 2026. https://texasaidocket.com/item/tx-2026-0167/. Reuse permitted under CC BY 4.0 with attribution. The same entry is in the docket JSON as item tx-2026-0167.
Beat
Filed under Research and science, with every other decision on that beat.