eudr.dev

Methodology

How the engine reaches a per-plot verdict. The data sources, the pipeline, the decision rules, and what the methodology does not claim.

Our implementation choice for the questions Reg. (EU) 2023/1115 asks, not a regulator-approved methodology. The operator stays the duty-bearer under Arts. 4 and 8–12.

The four upstream Earth-observation datasets the engine consults (Hansen GFC, ESA WorldCover, JRC GFC2020, RADD) are served via emem. The open-source Earth-memory protocol. Every band, every cell, every fact is signed upstream and content-addressed; the engine reproduces those signatures verbatim in the DDS receipt so the chain is verifiable end-to-end.

This page explains, in regulator-readable language, exactly what data the engine consults and how it converts those data into the verdict that lands in the Annex II Due Diligence Statement.

The question the engine answers

For each plot of land in a consignment, the engine answers:

Was this plot deforested on or after 2020-12-31, in the sense of Art. 2(13) of Reg. (EU) 2023/1115?

The output is one of three labels per plot:

• negligible: no post-cut-off forest loss detected on any sampled cell within the plot polygon.
• non_negligible: at least one sampled cell shows Hansen loss-year ≥ 2021 or a RADD alert dated on/after 2021-01-01.
• indeterminate: the engine could not retrieve enough cell evidence to reach a verdict (e.g. High cloud cover and no Hansen

signal); the operator is notified to supply additional evidence.

A consignment is "negligible risk" overall when every plot is negligible. If any plot fails, the consignment fails.

The four upstream data sources

The engine consults four open Earth-observation datasets. Each one is cited verbatim in the signed receipt, so anyone can re-derive the verdict on their own machine without trusting our infrastructure.

1. Hansen Global Forest Change (UMD)

Authoritative source for annual forest-loss data from 2001 onward. The University of Maryland (Hansen et al.) publishes a global 30-metre raster keyed by year of loss. The product we consume is v1.12 (covering loss years 2001–2024, expected to update annually).

Two bands matter:

• treecover2000 (%). Tree-canopy density in the reference year

(2000). Used to confirm the cell was forest at the time-zero baseline before the engine inquires about loss.

• lossyear (offset from 2000). The year forest cover was lost,

if it was. lossyear == 21 means 2021; lossyear == 0 means no loss recorded.

A cell is flagged post-cut-off when treecover2000 > 0 AND lossyear >= 21. The engine carries the raw lossyear value verbatim into the receipt so the auditor sees the integer Hansen returned.

2. ESA WorldCover 2021

Authoritative source for land-cover class as of 2021. The European Space Agency publishes a global 10-metre raster classifying every pixel into one of eleven classes. Tree cover, shrubland, grassland, cropland, built, bare, snow/ice, permanent water bodies, wetland, mangrove, moss/lichen.

We use WorldCover 2021 because:

• The 2021 release post-dates the EUDR cut-off (2020-12-31). If a

pixel was already non-forest in WorldCover 2021, it cannot have been deforested by the engine's evidence window. The loss, if any, pre-dates the cut-off.

• The 10 m grid means a single emem cell is sampled by many

WorldCover pixels, so the dominant class is solid to single-pixel noise.

The engine surfaces the WorldCover dominant class per cell in the report's land-cover panel.

3. JRC Global Forest Cover 2020 v3

The Joint Research Centre's forest baseline at the EUDR cut-off date. JRC GFC2020 v3 (released 2024) is the Commission-funded implementation of what the Regulation considers "forest" on 2020-12-31. It uses a different signal mix than Hansen (Sentinel-1 + Sentinel-2 + Landsat) and a different definition of "forest" (>= 10% canopy cover + >= 0.5 ha + >= 5 m height, the FAO definition the Regulation references).

The engine cross-checks Hansen against JRC GFC2020 for every cell, when the two agree, the verdict is high-confidence. When they disagree, the receipt records both verbatim and the engine emits a "baseline disagreement" trace event so the operator can investigate.

4. RADD Sentinel-1 alerts (Wageningen)

A near-real-time alert layer fused from Sentinel-1 SAR (10 m backscatter, ~weekly revisit) and Sentinel-2 optical (~5-day revisit, weather-permitting) for the tropics. RADD ("Radar for Detecting Deforestation") publishes new alerts within days of the loss event.

The engine uses RADD as a fast-moving signal that supplements Hansen's annual update. A plot that passes the Hansen check today may fail next month if RADD flags new loss; the optional continuous monitoring skill (eudr.monitor.subscribe) re-checks RADD on a cadence and emits a re-attestation event when a new alert appears.

How a polygon turns into evidence

The Regulation requires geolocation in GeoJSON polygons. The engine's pipeline takes that polygon and:

1. Computes the polygon's bounding box and the polygon's centroid.
2. Resolves the bbox to a set of emem cell64 cells. emem uses a

custom 64-bit Hilbert-ordered geospatial code (21 bits latitude, 22 bits longitude) at a canonical resolution of ~9.55 m at the equator. Cells are serialised as four dot-separated base-1024 bigrams (e.g. defi.zb493.xoso.zcb6a) so string prefixes preserve spatial locality. The deployment exposes a single resolution today, migrating toward H3-res-13 (~3.4 m) per emem's published spec.

1. Samples up to 16 cells (configurable via EMEM_MAX_CELLS_PER_PLOT)

from the cell set. The sampling is deterministic. A stratified sweep across the polygon. So re-running the same scenario produces the same evidence.

1. For each sampled cell, queries emem.dev for the four signals

above. emem returns each signal as a content-addressed fact with a CIDv1 anchor so the engine never has to trust an opaque API response. Every signal is verifiable by re-deriving the CID from the canonical bytes.

1. Aggregates the per-cell signals into the plot verdict using the

logic described above.

Why per-cell sampling, not whole-polygon analysis

The Regulation cares about the polygon's status, not any one pixel's. We could in principle aggregate at polygon level (one "forest fraction" number across the whole plot). We deliberately don't, because:

• An auditor reading the receipt wants to see which cell

triggered the flag, not a single aggregate. A per-cell receipt lets the operator look at the exact sub-area, send a field worker, and resolve the question.

• Polygon-level aggregation hides micro-deforestation. A 1-hectare

loss inside a 100-hectare plot becomes a 1% noise floor; per-cell sampling surfaces the same loss as one flagged cell among many.

• Per-cell evidence is replayable. The receipt carries the cell64

identifier verbatim, so the auditor can fetch the same cell from emem.dev next year and compare.

The trade-off is that per-cell evidence is verbose. The receipt for a 4-hectare plot may carry 32 cells × 4 signals = 128 fact CIDs. That is the verbosity at the EUDR's evidentiary bar.

The seven pipeline stages

The signed receipt records the pipeline as a 7-stage DAG. Each stage emits structured trace events that flow into the receipt's stage_traces block so the auditor sees exactly what ran and how long it took.

The DAG is fully observable. Calling GET /a2a/tasks/<id>/events streams the stage start/done events in real time over SSE; the final receipt carries the same events as a structured array.

Decision rules. What flips the verdict

The composite verdict label is derived from the per-cell evidence plus the country tier. The rules are:

1. Any post-cut-off Hansen loss → non_negligible. A single

sampled cell with lossyear >= 21 flips the plot. This is the strongest signal and the cheapest one to verify.

1. Any post-cut-off RADD alert → non_negligible. Same logic;

RADD picks up loss before Hansen's annual update lands.

1. JRC GFC2020 disagreement → indeterminate (escalation). When

Hansen says "no loss" but JRC says "non-forest in 2020", the plot is flagged for review. The receipt carries both verbatim.

1. No evidence retrieved → indeterminate. Happens when emem

has no coverage for the region (rare at the equator, common near the poles). The operator is notified to supply additional evidence.

1. All cells pass + country tier is low-risk → negligible (Art. 13).

Simplified due diligence applies; the operator can skip the Art. 10/11 risk-assessment + mitigation steps.

1. All cells pass + country tier is standard or high-risk → negligible.

The DDS is generated but the operator still owes the Art. 10/11 risk-mitigation paper trail under the standard regime.

The threshold for "any cell" is one cell. We do not aggregate. A 1-of-32 flag is still a flag.

What the methodology does NOT claim

• It does not detect commodity-specific deforestation drivers.

Hansen + RADD + JRC are agnostic. They detect canopy loss, not who or what removed the trees. The Regulation in turn defines deforestation in land-use terms, not driver terms, so this is acceptable.

• It does not verify that the operator has the to the

land. Tenure, land registration, FPIC, and indigenous-rights questions are out of scope of this baseline. A partner provider can plug in via the LegalityProvider trait.

• It does not verify labour, child-labour, or worker-safety

claims. Those belong in a separate audit; the Regulation references them in Art. 2(40) but does not require this engine to adjudicate them.

• It does not consider deforestation that occurred before

2020-12-31. That land is not the Regulation's concern.

Refresh cadence

Reproducibility

Every receipt the engine signs carries:

• The exact cell64 identifiers of every sampled cell.
• The CIDv1 of every signed fact returned by emem.
• The Hansen vintage (loss-year range).
• The ESA WorldCover vintage (year + product version).
• The country-table as_of date (Implementing Regulation reference).
• The engine's own version + the ed25519 pubkey that signed the receipt.

An auditor can take a receipt issued today, re-fetch the same cells from emem.dev one year later, and recover the same per-cell facts. Hansen's annual update may add a new loss year (which would change a future compile) but the historical facts are immutable. That's the point of content-addressed evidence.

See also

• About EUDR. The regulation in plain English
• Architecture. Pipeline + receipts + CIDs
• Verifying a receipt offline
• emem.dev's published methodology for each band (linked from every fact CID).