Science & support

HydroFlux: scope, support and how to read a result

Scientific honesty is part of the product. HydroFlux reports where the evidence is strong, where local verification is required and where it will not produce an estimate.

SCIENTIFIC ARCHITECTURE

Beyond a map. A model of the exchange.

The difference is how we connect observations, time and uncertainty.

01 / TIME

The past informs. The future stays out.

We investigate backward-only lags and site-local calendars to prevent temporal leakage in evaluation.

LOCAL CALENDAR / BACKWARD-ONLY
02 / OBSERVATION

One perspective is not enough.

We combine Sentinel-2 optical signals, Sentinel-1 radar and Landsat surface temperature with meteorological context.

OPTICAL + RADAR + THERMAL
03 / CONFIDENCE

An estimate needs boundaries.

We evaluate conformal intervals and observed coverage by domain. A nominal 90% level does not guarantee coverage in every crop or region.

SPLIT-CONFORMAL / EVALUATION
DATA SOURCES / NO IMPLIED AFFILIATION
ESA Sentinel-1 / 2NASA / USGS LandsatERA5-LandFLUXNET / ONEFlux
Current HydroFlux engine

HydroFlux

A support-aware AI system for agricultural evapotranspiration, combining satellite observations, weather, terrain and field context with training evidence from eddy-covariance measurements.

Spatial output
30 m ET grid
Result contract
ET or null · uncertainty · age · support
Ground evidence
Eddy-covariance training observations
01 — SUPPORT CONTRACT

Where HydroFlux is supported

Support is evaluated for every pixel and request. A crop name or country alone never guarantees support.

SUPPORTED

Strongest established domain

North American annual crops and forage when climate, land cover, sensor freshness and required context pass the support checks.

Typical examples: corn, soybean, wheat, forage and comparable annual cropping systems with usable observations.

LIMITED SUPPORT

Broader agricultural screening

Agricultural pixels outside the strongest evidence envelope, including specialty or perennial systems, may be returned with limited support and wider uncertainty.

Examples: vineyards, orchards, new climates, weak land-cover confidence or missing phenology and irrigation context. Verify locally.

ABSTAINED / OOD

No defensible estimate

HydroFlux returns null when critical evidence is stale, missing or contradictory, or when the pixel is outside the supported agricultural domain.

Examples: no usable optical and radar evidence, a clear observation older than 32 days, unresolved domain conflicts or non-agricultural surfaces.

SUPPORTED describes resemblance to the established evidence and input contract. It is not a claim of field-specific calibration or ground-truth certainty.

02 — SUPPORT-FIRST ROUTING

How a request becomes a supported result

The public contract is intentionally simple: inspect the evidence first, estimate only where support is defensible, and expose the reasons.

01

Inputs and domain assessment

The system evaluates sensor availability, crop and land cover, climate, terrain, irrigation, phenology and recent field history.

  • Sentinel-2 · Sentinel-1 · Landsat
  • ERA5-Land + daily weather
  • Crop + land cover
  • SRTM terrain
  • HydroMemory
02
HYDROFLUX

HydroFlux

Support-aware evapotranspiration engine

30 m
03

Conservative support decision

The system prefers a transparent null over unsupported extrapolation.

Strongest established domain

Estimate inside the strongest evidence envelope.

Broader agricultural screening

Estimate supplied with a clear verification warning.

No defensible estimate

No value supplied when evidence is insufficient.

04

Daily ET at 30 m — or null

Every pixel includes uncertainty, observation age, support status and human-readable reasons.

This diagram documents the product contract without exposing private implementation details. Support can vary within the same field.

03 — DAILY PRODUCT

How the daily product is derived

A daily map combines the latest valid multi-sensor HydroFlux anchor with daily weather and reference ET. It always declares how final the result is.

Latest valid HydroFlux anchor

Multi-sensor crop state over the 16-day observation window

Daily weather + FAO-56 ET0

Radiation, temperature, humidity, wind and rainfall

30 M GRID

Daily evapotranspiration map

Uncertainty · observation age · support status · temporal status

ForecastProvisionalReconciled
04 — INTERPRETATION

How to read a result

Four fields decide how much weight a number deserves.

01

Support status

Whether the pixel sits inside the validated domain. Limited support is a signal to verify locally, not a defect to hide.

02

Uncertainty

An operational range that widens as evidence weakens. Treat it as a heuristic band, not as validated probabilistic coverage.

03

Observation age

Days since the last clear Sentinel-2 or Landsat observation for that pixel. Older evidence caps support and widens uncertainty.

04

Abstention

A pixel with no usable estimate returns null. An abstention is information, not a gap to fill with a candidate value.

05 — LIMITATIONS

Current limitations

  • The strongest established support is for North American annual crops and forage. Broader agricultural coverage is not a universal validation claim.
  • Uncertainty is an operational heuristic. It is not a validated probabilistic coverage interval.
  • Historical ERA5-Land context is sampled at roughly 11 km at the field centroid. It is not an independent 30 m climate observation per cell.
  • A clear observation older than 32 days forces abstention rather than extrapolation.
  • HydroFlux can show a water estimate and its support status. Irrigation prescriptions stay outside it. Whether a difference should change an action is a separate decision. Water-response validation is still in progress.