Preview view of the dashboard. Sign in with the credentials provided to you to access your assigned area.

Sign in to your dashboard

Use the credentials provided to you. You will see the area assigned to your account.

Your gold targeting dashboard

Find gold faster,
without losing more pits.

AI-powered targeting for your licensed gold concession. Every assay you log sharpens tomorrow's recommendations. Real satellite imagery, 3D terrain, offline-capable tablets. Your area, your data, your dashboard.

Real satellite imagery 3D terrain 24-hour learning cycle
📍 Demo location · illustrative
🛰️ Sentinel-2 + ASTER + DEM
Targets ranked
15
Pits logged
12
Hit rate
55%
What's inside
Real satellite imagery (Esri + Sentinel-2) 3D terrain visualisation 60-day operator timeline Per-pit Bayesian learning Offline tablet sync Your own private tenancy
The product

A loop, not a list. Every pit feeds the next recommendation.

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.

01
📍

Recommend

The model ranks your AOI by expected gold-per-dollar — geology, drive distance from camp, dig cost, and offtake readiness all factor in.

02
⛏️

Dig

Foreman pulls up the next pit on the offline tablet. GPS, depth target, expected grade, and cost all pre-populated.

03
📋

Log

Tablet captures geology, photos, voice notes, and the assay when it returns from the lab. Syncs nightly via camp Starlink.

04
🔁

Learn

Bayesian update on surrounding cells overnight. By morning the tablet shows refreshed next-pit recommendations.

Preview

Explore the dashboard. Click any point.

This is the same interface you get after signing in — just with preview data. Toggle map layers, switch basemaps, click any target to see the AI's reasoning, click any pit to see the assay. Press play in the next section to watch the model learn over 60 days.

Loading map and data...
What's real on this dashboard

Real data, real sources, real citations.

The Mait–Erigavo 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.

94 documented occurrences

Real mineral occurrences and prospects in Somaliland from USGS MRDS (86), USGS Africa Mineral Sites (7), and Wikidata (1). Each carries a clickable USGS deposit ID URL — verifiable by the buyer's team in seconds.

Source: mrdata.usgs.gov · public domain

332 earthquakes M≥3

Full USGS earthquake catalogue for the Horn of Africa, 1990–2026. Active-tectonics evidence — most M5+ events trace the Gulf of Aden / Afar / Somali plate boundary. Max recorded: M6.2.

Source: USGS FDSN web services · public domain

17 settlements + 7 regions

Major Somaliland settlements (Hargeisa, Berbera, Borama, Erigavo, Mait, Las Anod, etc.) with population data and Wikipedia verification links. Admin regions include the disputed Sool zone.

Source: Wikipedia (CC BY-SA), UN OCHA admin boundaries (CC BY)

8 analog deposits — Horn of Africa

Lega Dembi (Ethiopia, 3.6 Moz Au), Tulu Kapi (KEFI, 1.7 Moz), Bisha (Eritrea VMS), Sukari (Centamin, 15 Moz resource), Hassai, Block 14, Yemen basement. Used for transfer-learning the geological prior.

Source: operator NI 43-101 disclosures · public

EMAG2 v3 — global magnetic anomaly

NOAA's 228 MB global magnetic anomaly grid at 2 arc-minute resolution. Clips to any AOI for regional structural framework. Already in the data layer; the pipeline that turns it into per-cell features ships with the system.

Source: NOAA EMAG2 v3 · public domain

📚

40+ verifiable references

Curated bibliography across Somaliland geology, East African Orogen tectonics, analog deposits, ASTER alteration mapping, machine learning for prospectivity, and conflict-minerals due diligence. All findable on Google Scholar.

Categories: framework, tectonics, analogs, remote sensing, machine learning

The convincer

Watch the system learn over 60 days.

This is what makes the system different from a static map. Drag the timeline or press play to replay the first 60 days of synthetic operator data. The map shows pits as they were dug; the chart shows the operator's hit rate climbing past the baseline as the model learns from each new assay.

Day 60 / 60

2026-05-20 · synthetic operator timeline (1-day = 1 frame at 0.3s)

Day 1 · 2026-03-22 Day 60 · 2026-05-20
Cumulative hit rate
AI-targeted Baseline (blind controls)
Pits at this point
— productive
AI hit rate
vs 18% blind-control baseline
Lift over baseline
Statistical significance: (lower is better; conservative external claims only when p < 0.05)

Reading the chart: the gold line is the operator's cumulative hit rate on AI-recommended pits. The dashed grey line is the 18% baseline measured from blind-control pits — cells the model would not have recommended. The system is genuinely predictive when the gold line is consistently above the dashed line with low p-value. Honest signal, not a vanity metric.

Expected accuracy

Satellite + XRF: from belt to bench.

The system targets in two stages. Stage 1 uses satellite, geophysics, and historical data to compress your concession down to priority hectares. Stage 2 fuses handheld XRF readings on those priority hectares into a refined posterior, getting you to bench-level targets. Each new assay you log keeps sharpening it.

Stage 1

Satellite + AI (no field data)

65–75%
at 1-hectare cells (100m × 100m)

Compresses a 200 km² concession to 20–30 priority hectares using Sentinel-2 multispectral, ASTER alteration mapping, DEM-derived structure, and the published-occurrence prior.

Stage 2

+ Handheld XRF readings

70–75%
at 100m × 100m sub-cells

50–100 XRF readings per priority hectare on an AI-designed sampling grid pick up gold and pathfinder elements (Cu, Zn, Pb, As, Sb). Fused with the satellite prior into a tighter posterior.

Stage 3

+ 6 months of pit-log feedback

70–80%
at 50m × 50m bench cells

Every pit you log feeds the Bayesian update. After six months of operator data, the model is calibrated to your geology and reaches bench-level precision.

Baseline for comparison: random pitting in equivalent ground returns roughly 18% productive cells. The system's lift is measured against this in your own data — not against generic benchmarks.
Honest framing: these are internal target performance figures from spatial-block cross-validation against blind controls, not guarantees. Actual precision depends on your geology, XRF instrument calibration, pit throughput, and assay quality. Performance is reported back to you monthly with the operator-specific blind-control hit rate — so you see real numbers, not promises.
Your private dashboard

Your area. Your data. Your dashboard.

Sign in with the credentials provided to you. The dashboard loads your assigned area, your pit log, and your recommendations. No one else sees them.

🔑

Your own login

Each account has its own credentials and is scoped to a specific area. Provided directly — no self-signup, no shared accounts.

📍

Your assigned area

The dashboard loads what's relevant to you — your AOI, your pit log, your recommendations. Other users see only their own.

🔒

Private by default

Your data lives in your own encrypted tenancy on Cloudflare. Nothing shared, nothing indexed, nothing public. You can export at any time.

Capabilities

What you actually get.

Nine capabilities tuned to a real Somaliland operator's day — not a research pipeline.

🎯

Per-pit Bayesian update

Each assay shifts the posterior on a 1.5–3 km Gaussian kernel and re-ranks candidate pits within 10 km. Cycle time from new assay to updated recommendation: under 24 hours.

💰

Cost-aware ranking

Recommendations maximise expected gold per dollar — not raw probability. Cost is a model input, calibrated as your pit log grows.

📡

Offline-first tablets

QField + custom pit-log layer. MBTiles cached locally. Nightly camp Starlink sync. Works for weeks without connectivity.

🗺️

Operator overlays

Clan / xeer / diya zones, recent security incidents, surface water (NDWI), paved roads, Berbera distance, Puntland border buffer — all baked into the ranking.

💎

Market-readiness score

Each target carries a logistics score alongside its geology score — distance to market, transport practicality, downstream feasibility. A high-grade target with no route to market is ranked lower than a moderate target you can actually sell.

📷

Field-buddy VLM

Photograph an outcrop on the tablet. Get back: "Looks like shear-zone iron-oxide alteration. Similar to your pits #027 and #041 (2.3 and 1.8 g/t). Recommend panning 50 m N-NE."

🔒

Confidentiality engineering

Operator AOI never leaves your tenancy. End-to-end encrypted sync. Audit-trail exports are per-target signed CSVs — share only what the financier needs.

📜

Append-only audit trail

Every recommendation hashed, timestamped, GPS-locked, and chain-linked. The basis of the royalty calculation and your defence in any future audit.

🧪

Blind controls 10–15%

Monthly target lists include low-probability cells the model would not otherwise recommend. Honest validation that the system is genuinely predictive, not confirming pre-existing intuition.

FAQ

Quick answers.

How do I sign in?+
Use the credentials provided to you. Click Sign in at the top right, enter your username and password, and your assigned area loads automatically. There is no self-signup — accounts are issued directly.
What will I see after I sign in?+
Your assigned area on real satellite imagery with 3D terrain, the AI-recommended targets ranked by expected return, your pit log, and the 60-day timeline showing how the model is learning from your assays. The capabilities you see on this preview are what you get inside — applied to your real area.
How does the system learn?+
Every assay you log feeds a Bayesian update on the surrounding cells. Productive assays raise the probability of nearby cells; barren assays lower it. The cycle from new assay to refreshed recommendation is under 24 hours. The "Watch it learn" section shows the hit rate climbing past the baseline as more data accumulates.
Can I see another user's area?+
No. Each account is scoped to its own assigned area. You cannot see, search, or browse any other user's AOI, pit log, or recommendations. Other accounts cannot see yours.
Where is my data stored?+
In an encrypted Cloudflare tenancy scoped to your account. Your data is not indexed, not shared, not published anywhere. You can export your pit log and audit trail at any time.
Does it work without internet at site?+
Yes. The field tablets cache the map and recommendations locally. Pit logs are entered offline, then sync the next time the tablet sees camp WiFi or Starlink — typically nightly. Days without connectivity are handled cleanly.
Can I download my targets?+
Yes. Targets, pit log, and audit trail are exportable as CSV or GeoJSON from within your dashboard. Use them in QGIS, Excel, or any other tool you prefer.
How do I get help?+
Use the contact details that came with your account. Account holders get direct support — typically a same-day response.

Ready when you are.

Sign in with the credentials provided to you. Your dashboard, your area, your data.

Sign in →