Skip to main content
New: Groundwater program in developmentFor growersFor water sponsors

Case study · live deployment

A California operation.2,000+ acres of citrus and pistachios.

What a full AgWaterAI deployment actually looks like on a working orchard operation under SGMA allocation pressure: instrumented, verified, and running live today. We never name customers. The numbers below come from this deployment's own sensor and meter records; the signed reading summaries behind them can be checked with our public key.

2,000+

Acres under management

Citrus and pistachios, block by block

30+

Live soil-sensor sites

Multi-depth probes, 10-100cm, streaming continuously

Metered

Well flow telemetry

Live pump and flow telemetry where a meter is installed; unmetered wells are labeled estimates

Signed

Reading summaries

Signed at attestation; certificates checkable with the public key

The starting point

Thousands of acres, one water year, no room for guesswork.

Permanent crops under a SGMA allocation cap mean every acre-foot has to be placed where the trees actually need it. Cold soil can shut down root uptake while moisture reads fine. Salt builds where roots feed. A pistachio year is decided by stress timing around hull split. The operation needed block-level evidence, and records that show what was recorded and whether it changed after signing.

The deployment

Four steps, all running today.

01

Instrument

Multi-depth soil probes across 30+ sites and flow meters on the wells that have them, streaming into one platform.

02

Verify

Reading summaries signed at attestation into a chain that is tamper-evident from signing forward. Attested records cannot be silently altered afterward.

03

Advise

Three trained AI models are live in the irrigation decision (SENTRY, WATCHDOG, PULSE). Model outputs depend on the site's data and promotion status; planning outputs remain labeled as estimates. The operation gets a Monday written briefing and a Thursday water order, plus a live dashboard.

04

Account

SGMA allocation tracked per entity in real time, with signed reading summaries behind the figures for any reporting or verification ask.

What the operation gets

Instrument-grade eyes on every block, every day.

A live operations dashboard

Every ranch card shows current soil moisture by depth, pump activity, SGMA allocation burn, and the AI insights row. Accessible from the office or the truck.

AI intelligence on every ranch card

Four live reads per card: stress buffer, cold-soil uptake, water-year burn rate, and the hull split window on pistachio blocks, projected weeks ahead. Salt and flushing guidance is in testing.

Twice-weekly written guidance

Model outputs depend on the site's data and promotion status; planning outputs remain labeled as estimates. The operation receives written irrigation guidance twice a week, reviewed by our agronomist, plus alerts when something needs attention sooner.

SGMA allocation tracking per entity

Live usage against allocation for every entity, with over-allocation exposure estimates. Exports in the format the GSA files in are coming.

Tamper-evident verification

Reading summaries are signed at attestation and chained per site, tamper-evident from signing forward. Water-use certificates built on them are Ed25519-signed and re-checked against our public key every time their verify page opens. Issued water orders are kept with the readings behind them and are not signed. Tamper-evident records preserve attested readings and reports; they do not by themselves establish measurement accuracy, water savings or regulatory compliance.

Sensor and equipment health watch

The platform monitors its own instruments: probes that stop reporting or return error values get flagged so the data feeding decisions stays trustworthy.

The platform behind it

This deployment runs on AgWaterAI's decision systems: three trained AI models live in the irrigation decision (SENTRY, WATCHDOG, PULSE), validated walk-forward and on held-out sites across 320 site-years of daily multi-depth soil data recorded since 2016 on the oldest site. Model outputs depend on the site's data and promotion status; planning outputs remain labeled as estimates.

What we do not claim: water savings attributed to the AI. Any savings on a precision-managed orchard come from the whole system (sensors and agronomy), and we publish outcome numbers only when a full season has been measured and verified. That discipline is why our records are worth signing.

See the same product with sample data.

The demo is the same product: ranch cards, AI insights row, allocation tracking, signed records. Click into a pistachio card and look for the hull split window.