Skip to main content

Inference results

Inference applies a trained model version to imagery that passes the model picker's eligibility checks and adds the generated result to a workspace.

Eligibility and wavelength coverage​

Clarity offers model versions whose:

  • status is trained rather than draft or deprecated;
  • processing level matches the selected image layer;
  • wavelengths overlap the common wavelength range of the selected image layers; and
  • project and account access permit their use.

These checks establish product eligibility, not scientific comparability. A matching processing-level name does not prove that two layers have the same units, calibration, atmospheric correction, or acquisition conditions. Review that provenance before inference.

The model picker marks a version Exact wavelengths match or Will be resampled. An exact match preserves the model's wavelength axis. When the source can supply every model-band position, Clarity linearly resamples it to the model wavelengths.

Partial wavelength coverage

The current eligibility check requires only some wavelength-range overlap. If the source cannot supply every model-band position, Clarity resamples the available bands and fills missing positions with zeros. This is a current limitation: zero-filled bands are not measured spectral evidence and can put the input outside the model's training distribution. Do not use partial-coverage inference unless the model has been validated for that exact missing-band pattern.

Generate from Files​

  1. Open Files.
  2. Open an image's context menu and select Generate results.
  3. Choose the image layer or layers.
  4. Select an eligible model and version, then review its wavelength coverage.
  5. Select Generate.
  6. When generation completes, select Add to workspace if the result is not already open.

Generate from a workspace​

  1. Open the image in a workspace and select Explore.
  2. Expand the image source and its Analysis layers subsection.
  3. Select Generate analysis layers > Model inference.
  4. Choose the input layer and an eligible model version, then review its wavelength coverage.
  5. Generate the result.

The output appears as an inference layer in the workspace. Its rendering depends on the model type: a categorical layer for classification, class response layers for unmixing, a target score layer for Target Detection, or continuous attribute layers for regression.

Test predictions are different​

The model drawer's Test Predictions tab contains predictions generated from the designated Test bucket. Those predictions are an independent held-out measure only if the Test data remained untouched during model selection. Use Generate results or Generate analysis layers > Model inference for operational imagery that is not part of the model test run.

If no model is offered, check the version status, processing level, wavelength metadata and overlap, and project access.