Our explainable engine

mineBAG — see the reasons behind every target.

mineBAG scores your ground the way a geologist would: it checks seven kinds of evidence for every spot, weighs them up, and gives you a score you can question — plus a clear flag for where it's guessing.

What it is

mineBAG compares every spot on your ground against the most similar places we already know about — within the same rock type. If a spot looks like ground that hosts deposits, it scores high. If it looks like nothing we've seen, mineBAG says so instead of inventing a number. Nothing is hidden: you see exactly which evidence pushed each target up or down.

Seven kinds of evidence — the ones your geologist checks.

Each kind of evidence votes for or against, on its own. We combine them into one score — and show you how each one voted.

GEOLOGY

Host rock

rock type and age

GEOPHYSICS

Gravity & magnetics

buried structures and intrusions

GEOPHYSICS

Radiometrics

potassium, thorium, uranium

TERRAIN

Terrain shape

elevation, slope, aspect

SATELLITE

Surface texture

radar (Sentinel-1)

SATELLITE

Alteration

mineral signatures from satellite

GEOCHEM

Pathfinder chemistry

the elements that point to your commodity

One clear score

Seven votes, added up into a single score — with every vote on show.

And when there's no evidence to go on, mineBAG says so — it won't make up a number.

See exactly why a target scored.

When a target scores high, your team can see why: the right host rock, a buried intrusion on the magnetics, a clear arsenic-and-silver anomaly. It's all laid out — so you can agree with it, or push back, and take it to your board either way.

What moves a gold target — Lachlan Fold Belt (example)

The signals that push a gold target up the list. We tune these for each region and rock type.

GEOCHEM Arsenic (As)
GEOCHEM Silver (Ag)
GEOLOGY Host rock
GEOPHYSICS Gravity
GEOPHYSICS Magnetics
GEOPHYSICS Potassium (K)
TERRAIN Terrain
GEOCHEM Copper (Cu)
SATELLITE Alteration
GEOPHYSICS Thorium (Th)
DRILL TARGET
Target 7
SCORE
84/100
-32.847, 148.923 solid evidence
Points for
+
Host rock — granodiorite, a known gold–copper host
+
Magnetics — magnetic high, likely a buried intrusion
+
Alteration — clay alteration picked up from satellite
+
Chemistry — arsenic & silver anomaly
Points against
~
Surface cover — heavy vegetation, satellite less reliable here
~
Radiometrics — no clear potassium signature

Strong, consistent evidence across rock type, magnetics and chemistry. Worth following up.

The honesty signal — where not to trust the map.

Every target comes with a plain flag — how much real evidence is behind it. It's the part no other tool gives you.

Solid evidence

We've seen ground like this before. Trust the score.

Thin evidence

Not much to go on here. Treat the score as a maybe.

We're guessing

We've never seen ground like this — so we tell you straight, instead of inventing a number.

Proven on real deposits.

We tested mineBAG on known deposits it had never seen (0.5 is a coin toss, 1.0 is perfect). South Australia is proven for all six commodities.

Commodity SAQLDWAVICTASNTNSW
Gold
orogenic / intrusion-related
0.81
0.82
0.73
Copper
porphyry / IOCG
0.81
0.79
Silver
epithermal / vein
0.78
0.74
0.76
0.71
Lead-Zinc-Silver
SEDEX / VMS
0.75
0.78
0.76
Nickel-Cobalt
magmatic / laterite
0.76
0.85
0.87
Tin-Tungsten
granite-related
0.74
0.75
0.72
Strong (0.80+)
Solid (0.75–0.79)
Good (0.70–0.74)
Most data (NSW)
Not proven yet

An empty cell isn't missing coverage — it's ground we haven't proven yet, so we won't quote a number. What works for one rock type and region won't always work for another, and we'd rather tell you than guess. NSW is where we hold the most data (proven across all six) — ask us for the regional numbers.

Choose mineBAG when…

  • You need to defend every target to a board, a JV partner or an investor.
  • There isn't much local data to train a model on — mineBAG leans on analogues from across the country.
  • You want a clear flag on where the model is guessing, not just a score.

Got plenty of your own samples and want the highest accuracy? A custom ML model may suit your ground better. We'll tell you which.

Targets you can defend.

Let's run mineBAG on a pilot area so you can judge the output, not the pitch.

Scope a pilot AOI