Overview

After completing Step 4: Select Input Features and generating a Prediction Map, you can use Create Target Groups to organize high VRIFY Prospectivity Score (VPS) areas into discrete exploration targets.

This step helps convert a continuous VPS surface into clusters that are easier to interpret and evaluate:

Groups high-prospectivity areas into clusters
Generates Feature Importance (SHAP) for each group
Helps you assess what is driving predictions in different areas

This step is optional and does not change the underlying VPS. You can still use the Surface and Sub-surface VPS threshold slider (bottom left) to adjust how VPS is visualized

Understanding Target Groups

After running a prediction, DORA generates a continuous VPS surface across your AOI.

Target Groups apply a filter and grouping process. The VPS threshold defines which areas are considered targets, then grouping settings determine how those areas are clustered:

Step 1: Filter → The VPS threshold selects the areas to include
Step 2: Group → The other two sliders define how targets are formed

All three settings work together and should be adjusted iteratively.

Adjust Target Group Settings

Parameter	What it does	How to adjust
VPS Threshold	Controls which areas are considered targets.	Lower values → broader coverage, more potential targets (more noise) Higher values → fewer, higher-confidence targets
Minimum Group Size	Controls how spatially connected areas are grouped.	Higher values → merge nearby zones into larger groups Lower values → create smaller, more fragmented groups
Minimum Points in Group	Controls how many data points are required to form a target.	Higher values → removes small or weak clusters Lower values → allows smaller groups (may introduce noise)

Why the Create Target Groups Step Matters

Geoscience Perspective

Target clustering enables you to group predictions into geologically meaningful exploration zones. Since different areas may be influenced by different mineralization controls, this step allows you to apply domain knowledge and evaluate whether the generated targets align with known geological patterns.

AI Perspective

This step turns your model results into clear exploration targets. By adjusting threshold and clustering settings, you control how targets are grouped, filtering out noise and preventing the output from breaking into too many small, disconnected zones.

Step by Step Instructions

Run the Prediction Model
- Complete Step 4: Select Input Features.
- Click Run Prediction.
- Wait for the Prediction Map and VPS to generate.
Create Target Groups
- In the top middle navigation, click Create Targets.
- Start with the default parameters, then adjust them based on your geological understanding of the AOI:
- Click Update Target Groups to confirm your selections.
Review Feature Importance by Group
- Open the Prediction Results panel on the right.
- Use the dropdown menu to select a specific target group.
- Review the corresponding Feature Importance (SHAP) label for that group:
- You can modify Target Groups as many times as needed. Each update generates new Feature Importance labels.