Our Solution

ENERZAi provides a machine learning solution that can be used in the early exploration stages
of mineral discovery and mine development


Can narrow down prospective areas
for exploration

Used in both greenfield and
brownfield explorations

Can be applied to wide
variety of mineral types

How it works

Survey Data Input

ENERZAi’s AI Model

AI based Prospectivity Map

Target region is divided into grids and accessible data is processed and utilized for each grid with available label information

ENERZAi’s machine learning model is
trained based on given dataset
and its labelled output

ENERZAi’s model predicts the prospectivity of the existence of minerals for each grid


High Predictability

Our AI solution shows high performance in mapping
the prospectivity of each site for possibility of deposits,
leading to increased rate of success in discoveries

Explainable AI

We use a machine learning techniques to trace the learning process of the AI, and therefore can explain how the AI deducts prospectivity for each site

Combining Data of Difference Scales and Dimensions

We use machine learning techniques to deal with the challenging problem
of combining data that exists in different forms

Consistency with Geological Interpretation

The AI solution’s outcomes are consistent with analysis done by geologists, therefore compatible and complementary with current methods

Process for Application


Workflow Description

Gawler region prediction

Predict areas of potential mineralisation within the Gawler region.

– Process the geoscientific data as ready-to-use machine learning models.
– Taking various approaches to increase the probability and merge through ensemble model.
– Feature importance explains why this result came from.