Bhārata Strata · Maharashtra · Nandurbar · morphological twins
Places like cell 4860001921
The MH-36 locality cells most similar to this Nandurbar cell across terrain, built form, land cover, climate dynamics and connectivity — ranked by a GUM-confidence-weighted (R24) distance, with the temporal block down-weighted. Each twin is a real cell with its own witnessed dossier.
Twins found
18
across 3 distinct districts
Index confidence
0.92
GUM mean confidence of the anchor (R24)
Dimensions compared
45
morphology-v2 feature dimensions
Closest twin distance
0.218
lower = more alike (weighted)
The twins, closest first
#1 · Nandurbarcell 4860001700
distance 0.218
#2 · Nandurbarcell 4860002052
distance 0.264
#3 · Nandurbarcell 4860001772
distance 0.3
#4 · Nandurbarcell 4860002106
distance 0.307
#5 · Nandurbarcell 4860001410
distance 0.308
#6 · Nandurbarcell 4860001587
distance 0.317
#7 · Nandurbarcell 4860001918
distance 0.325
#8 · Nandurbarcell 4860002449
distance 0.328
#9 · Nandurbarcell 4860001591
distance 0.344
#10 · Nandurbarcell 4860001922
distance 0.344
#11 · Nandurbarcell 4860001768
distance 0.349
#12 · Nashikcell 4870008517
distance 0.363 · cross-district
#13 · Nandurbarcell 4860000889
distance 0.363
#14 · Nandurbarcell 4860001697
distance 0.365
#15 · Dhulecell 4740005108
distance 0.369 · cross-district
#16 · Dhulecell 4740005478
distance 0.371 · cross-district
#17 · Nandurbarcell 4860001247
distance 0.372
#18 · Nashikcell 4870001377
distance 0.373 · cross-district
witness: find_twins — morphology-twin-index-v2 (R24, GUM-confidence-weighted, magnitude-aware, temporal block down-weighted). Distance is the weighted feature distance; lower is more alike. Cross-district twins are the discriminative signal.
Re-witness these twins
curl -s https://api.gridrock.ai/mcp -H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"find_twins",
"arguments":{"admin_code":486,"cluster_id":4860001921}}}'Scope: the live MH-36 cube. Twins are computed from the sha-verified morphology-v2 vector; the engine supplies no goodness/suitability ranking — only morphological similarity.