Book a call
Forestry & environment // Label type 10

Clear-cut and logging labeling from satellite imagery

Clear-cut labeling outlines forest blocks that have been logged or cleared, together with the logging roads that lead to them. It shows where harvesting happens and whether it stays inside permitted areas.

Landsat image of rainforest in Peru: a geometric grid of cleared plantation land beside a winding river.
RawLabeled
  • Cleared block2 polygons
  • Recent clearing4 polygons
  • Logging road2 lines
  • River1 line
Example: Yurimaguas, Peru, 10 July 2019, Landsat 8 OLI (NASA Earth Observatory / USGS). Labels drawn by IKT Spīdolas for illustration.

What clear-cuts labeling is

Clear-cuts have sharp, straight edges that set them apart from natural disturbance; new roads usually appear first. We label cut blocks, fresh clearings and access roads, and date them across an image series. In the example, a plantation grid has been cut into rainforest beside a river in Peru.

How we label it

Cut blocks are polygons with a cut date; roads are lines with a first-seen date. Partial or selective logging, which leaves canopy standing, is a separate class labeled on high-resolution imagery.

Who uses clear-cuts labels

  • Forest management

    Map harvested blocks against cutting permits and management plans.

  • Illegal logging detection

    Training data for models that spot new roads and cuts outside concessions.

  • Timber and pulp supply chains

    Show where material is being harvested, for certification and due diligence.

  • EUDR and carbon

    Separate harvest in managed forest from conversion to other land use.

How a project runs

Four steps, each ending in something you can check before the next one starts.

  1. Brief

    Area, dates and class list agreed in writing, with example images for every class and its edge cases.

    You getWritten labeling guideline

  2. Imagery

    Your imagery, or sourced for you: free Sentinel and Landsat, or commercial high-resolution scenes.

    You getScene list with dates and resolution

  3. Labeling

    Annotators work to the guideline. Anything the imagery cannot settle is flagged, not guessed.

    You getLabels plus a log of flagged cases

  4. Check & delivery

    Every class is reviewed against a sample before the data leaves us.

    You getData and per-class accuracy, in your format and CRS

Questions about clear-cuts

Can you see selective logging from space?

Partly. Roads and log landings are visible on high-resolution imagery; single felled trees under a closed canopy usually are not.

How is a clear-cut different from canopy loss?

Canopy loss is any lost tree cover; clear-cut labeling adds the harvest pattern (blocks, roads, dates) that forest managers and regulators work with.

Can you label against our concession boundaries?

Yes. Send them and each cut is tagged as inside or outside.

Related label types

Next step

Need clear-cuts labeled?

Tell us your area, your imagery and what your model has to learn. We reply with a proposed class list and a quote.

Book a call