Frontend demo only — unlocks richer reasoning and removes coordinate obfuscation on synthetic data.
test / test./operator/* route.
Closed-loop AI targeting for licensed north Sudan gold operators on Pan-African basement. Every pit you dig sharpens the next recommendation within 24 hours. Offline-first tablets. Append-only audit trail. OECD Annex II-aware offtake routing.
The Hassai/Ariab demo data (targets, pits, controls) is synthetic and clearly labelled. Everything else on this page comes from authoritative, free, citable sources. Click any reference layer in the demo map to verify against the original source.
Real mineral occurrences and prospects in north Sudan from USGS MRDS, USGS Africa Mineral Sites, Wikidata, and the peer-reviewed Maus 2022 global mine extents. Each carries a clickable source URL.
Source: USGS MRDS · public domain
USGS earthquake catalogue for north Sudan 1990–2026. Active-tectonics evidence along the Red Sea rift margin. Max recorded: M5.7.
Source: USGS FDSN web services · public domain
Major north Sudan settlements (Khartoum, Port Sudan, Wadi Halfa, Karima, Atbara, etc.) with population data and Wikipedia verification. Admin regions cover the four Pan-African gold belts.
Source: Wikipedia (CC BY-SA), UN OCHA admin boundaries (CC BY)
Hassai (Sudan, direct neighbour), Sukari (Egypt, 15 Moz Centamin), Bisha (Eritrea VMS), Block 14 (Sudan Managem), Lega Dembi (Ethiopia, 3.6 Moz MIDROC), Mahd adh Dhahab (Saudi Ma'aden), Tulu Kapi (KEFI), Kefi Hawiah. Used for transfer-learning the geological prior.
Source: operator NI 43-101 disclosures · public
NOAA's 228 MB global magnetic anomaly grid at 2 arc-minute resolution. Clips to any AOI for regional structural framework. Ships with the system.
Source: NOAA EMAG2 v3 · public domain
Curated bibliography across north Sudan geology, ANS tectonics, analog deposits, ASTER alteration mapping, ML for prospectivity, and OECD due diligence.
All findable on Google Scholar / DOI
Most targeting tools deliver a static map and walk away. This one closes the loop — every assay updates the model overnight, and the next morning's recommendations reflect what you just learned in the field.
The model ranks your AOI by expected gold-per-dollar — geology, drive distance from camp, dig cost, and offtake readiness all factor in.
Foreman pulls up the next pit on the offline tablet. GPS, depth target, expected grade, and cost all pre-populated.
Tablet captures geology, photos, voice notes, and the assay when it returns from the lab.
Bayesian update on surrounding cells overnight. By morning the tablet shows refreshed next-pit recommendations.
Same dashboard your geologist would see. Data is a learning-mode placeholder over the Hassai/Ariab gold belt in Sudan's Red Sea Hills. Toggle layers, click a target for AI reasoning, click a pit for the assay.
Drag the timeline or press play. The map shows pits as they were dug; the chart shows the operator's hit rate climbing past baseline as the model learns from each new assay.
2026-05-20 · synthetic operator timeline
Three tiers. Public view obfuscates coordinates ±1.5 km on synthetic data — same model applied to real data. Real operator data only behind authenticated access.
What you're looking at now.
test / test. For prospective operators evaluating the UX.
Real operator data. Per-operator tenancy.
/operator/*Each assay shifts the posterior on a 1.5–3 km Gaussian kernel and re-ranks candidate pits within 10 km. Under 24 hours from assay to refreshed recommendation.
Maximises expected gold per dollar — not raw probability. Cost calibrated as the pit log grows.
QField + custom pit-log layer. MBTiles cached locally. Works for weeks without connectivity.
Tribal stakeholders, security incidents, water (NDWI), paved roads, Port Sudan distance — baked into ranking.
LBMA refinery acceptance, OECD Annex II path, customs route, disclosure burden — alongside the geology score.
Photograph an outcrop on the tablet. AI returns: "Looks like VMS gossan. Similar to your pits P-099 (3.21 g/t) and P-104 (4.05 g/t). Pan 50 m SE."
Operator AOI never leaves your tenancy. End-to-end encrypted sync. Signed CSV exports for financier reporting.
Every recommendation hashed, timestamped, GPS-locked, chain-linked. Basis of royalty calculation.
Monthly target lists include low-probability cells. Honest validation that the system is genuinely predictive.
30-minute call. Bring your SGRA licence area, your current process, and your offtake setup. We'll tell you honestly whether the system would lift your hit rate and what the binding compliance constraint looks like for your specific situation.