TerraKeepKeeping Earth within its limits
Cloud-free satellite view around Nova Maringá, Mato Grosso (Brazil) — tile 1/2, with the finding area outlined
12.23°S 57.23°WNASA Blue Marble via GIBS · outline = finding area
Published

1,346.7 ha of forest loss flagged near Nova Maringá, Mato Grosso, over 90 days

Nova Maringá, Mato Grosso (Brazil) — tile 1/2 · seen · published

Between 30 June and 28 September 2026, satellite alert systems recorded 111,920 high-confidence deforestation alerts across a watch tile near Nova Maringá, Mato Grosso, covering 1,346.7 hectares. An independent optical check using Sentinel-2 imagery supports it: median greenness (NDVI) across the tile fell by -0.165 between 16 May and 28 September, with 100% of pixels usable in both composites — so cloud is not hiding the picture here.

What this is not: the alerts cannot tell clearing apart from fire, storm damage, selective logging or plantation harvest, and none of it speaks to who acted or whether it was lawful. Conditions argue for caution too — a strong El Niño (ONI 1.8) can push vegetation indices down through drought alone, and the tile is already 31.3% converted land, where regrowth and harvest cycles mimic loss. Notably, alert density here is 0.721× the surrounding 25 km ring, so this tile is quieter than its neighbourhood.

What would change our mind: high-resolution imagery showing burn scars or standing-but-stressed canopy, fire-detection records for the window, or concession and protected-area layers reframing the event.

Written by AI, then checked by a separate reviewer before publication. Every claim points at the evidence below.

What we saw

  • Area: 1,347 hectares — about 1,900 football fields
  • Nature’s work at stake: about $9M a year (a rough estimate of what this land does for people — clean water, carbon, food).
  • Global Forest Watch alerts — 111920 alerts (≥ high confidence), 1346.7 ha, 2026-06-30…2026-09-28. (Sep 28, 2026) See the source ↗
  • Sentinel-2 satellite images — Median-composite NDVI changed -0.165 (2026-05-16 → 2026-09-28); valid pixels 100% / 100%. Scenes: [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] (Sep 28, 2026)

What it might not be

  • Alerts cannot separate legal clearing, fire, storm damage or selective logging from illegal clearing.
  • Alerts lag reality by roughly 1–2 weeks, so a late burst would be undercounted.
  • Regrowth and plantation harvest cycles can look like loss in a tile that is already 31.3% converted.
  • El Niño (ONI 1.8) drought can depress NDVI without canopy removal.
  • Alert density is 0.721× the 25 km neighbourhood — below the regional rate, not a local outlier.
  • Living-value figures in the context notes are order-of-magnitude benefit transfers, not prices; they are not cited here as measurements.
  • Coverage is 30°N–30°S only — zero alerts outside the tropics means 'not monitored', not 'no loss'.
  • Cannot distinguish legal clearing, fire, storm damage and selective logging from illegal clearing; attribution needs concession/protected-area layers (M3).
  • Alerts lag reality by ~1–2 weeks; a burst just before the sweep is undercounted.
  • Regrowth and plantation harvest cycles look like loss; the baseline ring only partly compensates.
  • Persistent cloud can delay optical confirmation for months (SAR-only RADD alerts stay 'candidate').

What would change our mind

Newer satellite images that show no change, a correction from the data source, or a reply with evidence from the ground. If that happens, the case is marked “Turned out wrong” — in public — and it stays on this site.

Why this was published

Two separate sources agreed — Global Forest Watch alerts, then Sentinel-2 satellite images — and a reviewer checked the evidence before it went up.

Replies

Know this place? Say what you see. Replies are checked before they appear. No account, no email.

Replies are open on the interactive site (it needs JavaScript).

Ledger id 01a0e554-4c3e-70d9-af19-0e0f270485c4

Technical details rule, evidence ids, history, proof
Rule
forest_loss v1.0
Tier
T1
Tags
forest-hotspot, discovered, bra, brazil, mato-grosso, nova-maringa
Confirmed
Yes — independent sensor signal, 2026-09-28
Rule FP rate
33 % · 4 of 12 decided
Location
12.23°S 57.23°W
Observed
2026-09-28
Opened
2026-09-28 by automatic rule forest_loss v1.0
  1. candidate
  2. confirmed
  3. published
  4. resolved

Evidence2

alertgfw-integrated-alerts

111920 alerts (≥ high confidence), 1346.7 ha, 2026-06-30…2026-09-28.

alerts 111920ha 1346.7high_alerts 109048high_ha 1312.13highest_alerts 2872highest_ha 34.57living_value_100y_npv2_usd 389916433living_value_100y_usd 904713100living_value_usd_yr 9047131watch_area_converted_pct 31.3
· forest_alerts v1.0 · gfw-integrated-bra-12-77-1-2026-06-30..2026-09-28
Source ↗
scenesentinel-2-l2aConfirming signal

Median-composite NDVI changed -0.165 (2026-05-16 → 2026-09-28); valid pixels 100% / 100%. Scenes: [object Object], [object Object], [object Object], [object Object], [object Object], [object Object]

deltaNdvi -0.16460240001431226validPctA 100validPctB 100
· eo_compare v1.0 · s2-ndvi-median-bra-12-77-1-2026-05-16..2026-09-28

Context

0.72×
AOI vs its 25 km neighbourhood
AOI
1263.854
Ring
1752.674
Metric
alert ha per deg²
ENSO El Niño · ONI +1.8
  • Living value (benefit transfer, order of magnitude): 1346.7 ha of tropical forest ≈ $9,047,131/yr alive (band $2,657,039–$35,050,561, 2020 USD), ≈ $904,713,100 over 100 yr ($389,916,433 NPV @ 2 %). Source: Costanza R. et al. et al. — a floor for one kind of value, not a price.
  • The watch area is 31.3 % converted land (MapBiomas 2024: pasture, crops, mosaic, urban, mining).

Publication gates

  • Evidence — 1 piece from gfw-integrated-alerts — met
  • Independent confirmation — a different sensor (sentinel-2-l2a), 2026-09-28 — met
  • Human approval — 1 of 1 needed at tier 1 — met
  • Narration — AI-drafted by claude-opus-5 — met
Published
2026-09-28 by AI model
Narrated By
AI model
Reviewed By
AI model
Policy
2026-09-26-autonomous
Note
autonomous publish: narrated by model:claude-opus-5, reviewed by model:claude-sonnet-5 (policy 2026-09-26-autonomous)

History5

  1. status changed → publishedAI model
  2. reviewed → confirmedAI model
  3. narrated → confirmedAI model
  4. confirmed → confirmedautomatic rule forest_loss v1.0
  5. created → candidateautomatic rule forest_loss v1.0

Verify

Checkpoint
earthdeck.dev/findings/v1 · 714 entries
Signed root
23ed27dda9a2…5fec16
This case
5 signed events
Leaf
#704 of 714 — this case’s latest event
Leaf hash
97517b4d5dee…91f7bf
Proof
7-hash audit path
  1. 8ec1c31277f4abe09763f7c746ffc066fc3d8af815458ff68953ad7e428a580e
  2. e11eefc9011cfc1e875e2d7a0ca31a233a983d32c16b5802e7ffb25705f8785e
  3. 1dd8b669176ba23a234c3887e513118ce5f8fd15a154b8fdd926ee02760d8174
  4. a7fdef2cf5b5a712272dd0a660098eb2cfa6428b0896d7a072066e511d831900
  5. 227a1a00b64043f08073431f63834a568f922396dea9ef77ee795cd7e34484d7
  6. 4dcd70c622d414afaa3e0c21c3cf5233386d63f463994a07fff4e5e92c390f72
  7. 5f7580b7f5a7f09ff7675565fb36c19876079a6c101f721419a5a07a7a23b1c1
Last event
72c9bb7e1fc8…9b3213
Note
Checkpoint text
earthdeck.dev/findings/v1
714
I+0n3ami2iq+Pb01ZzA9/W1AK7wHekeD5OebmHxf7BY=

— earthdeck TkCXv0OmAxDtzaj1At98wE5s0VUwWeSCBAVzEDOuLw2Ioh7cGCd8Por/k57n26y0m4mCTkkb6qIdr6CB1+b6NmG1wgc=

Re-derive every entry, signature and trust rule yourself:

npx -y earthdeck ledger verify --remote https://vitalearth.io