Overview
Advanced Settings in DORA give you additional control over how your Prediction Map is generated. They are available in Step 4: Select Input Features and are optional. In most cases, the default configuration is appropriate.
There are two Advanced Settings:
Prediction Tendency controls how selective the Prediction Map is. It determines how closely new areas must resemble your positive Learning Data to receive a high VPS. You can choose between Conservative (fewer, higher-confidence targets), Balanced (default), or Aggressive (broader coverage, more targets).
Resolution defines the spatial scale at which the model evaluates your data across the AOI. DORA sets this automatically based on your input rasters. Manual adjustment is available when spatial scale is a variable you want to test.
Use Advanced Settings when you want to refine target selectivity or test different modelling scenarios.
Prediction Tendency
Prediction Tendency controls how selective the final Prediction Map will be.
It determines how closely new areas must resemble your positive Learning Data to be highlighted as prospective. In practical terms, this setting controls the balance between:
Higher confidence, fewer targets
Broader coverage, more targets
The default Balanced setting is suitable for most use cases. The other two settings can be valuable in certain use cases.
Conservative Setting
The Conservative setting focuses on areas that closely match known mineralization. It produces fewer, higher-confidence targets, while reducing noise and false positives.
This setting could be used when:
Drill budgets are limited
You need to prioritize high-confidence targets
You are refining targets for follow-up work
Aggressive Setting
The Aggressive setting expands the range of highlighted areas. It includes targets that are less similar to known mineralization and increases overall coverage.
This setting could be used when you’re:
Working in early-stage exploration
Screening large or underexplored areas
Looking for new or unconventional targets
Resolution
Resolution defines the spatial scale at which the model evaluates your data across the selected AOI.
By default, DORA automatically determines resolution based on the most common resolution among your selected rasters. This ensures minimal distortion or resampling and consistent alignment across input layers
In most cases, manual adjustment is not required.
You may consider adjusting resolution when:
Running highly targeted experiments (e.g., geology-only models)
Working with very high-resolution local datasets
Testing how spatial scale impacts results
If you manually adjust resolution, DORA 2.0 re-runs the experiment and all input rasters are re-evaluated at the new scale. This means that input feature scores and recommendations are updated.
Resolution affects how data is sampled and aligned, so changing it can significantly impact results.
Learn More
Still Have Questions?
Reach out to your dedicated DORA contact or email support@vrify.com for more information.