Overview
This article explains how to interpret the Depth Accuracy gauge and R² Valid scatter plot on your Prediction Map. These outputs help you evaluate how well the model predicts the vertical position of mineralized targets, and what to do if results are not reliable.
Depth Accuracy Gauge
When you first open your results, you’ll see a Depth Accuracy display in the form of a circular gauge, or odometer, showing:
Accuracy Score – A percentage representing how closely predicted depths match actual depths
Label – A qualitative indicator of model performance
A higher percentage indicates better alignment between predicted and actual depths. Lower scores may suggest the model is struggling to learn vertical patterns from your data.
Ideally, you want to see the High label.
To explore the results further, click the arrow in the upper right to view detailed model outputs.
What is the R² Valid Scatter Plot?
Below the gauge, you’ll find the R² Valid graph. The R² Valid is a scatter plot that compares predicted depth values with actual depth values from your validation dataset, typically sourced from drill holes.
The X-axis shows the true depth from drilling, often negative because it represents depth below surface.
The Y-axis shows the predicted depth from the model.
A red diagonal line (1:1 line) is drawn across the plot. This line represents perfect predictions, where predicted and actual depths are equal.
Each blue dot represents a learning point (i.e., a location where both prediction and actual depth are known). A point on the red line indicates a perfect prediction. The farther a point is from the red line, the less accurate the model’s prediction.
This graph is essential because it links classification outputs (e.g., the probability of mineralization) with predicted depth, a critical factor for drill targeting. While classification tells you where mineralization is likely, the depth model tells you how deep to drill. The R² Valid graph helps assess whether those depth predictions are reliable.
How to Interpret
The R² Valid scatter plot provides a quick visual indicator of prediction performance:
A tight cluster of blue dots along the diagonal means the model is performing well, accurately predicting depths across the range.
If the dots are spread widely above or below the diagonal, the model is either over- or under-predicting:
Dots above the diagonal: The model is predicting the depth to be deeper than it actually is.
Dots below the diagonal: The model is predicting the depth to be shallower than it actually is.
A pattern of horizontal alignment, where dots form a flat band regardless of actual depth, suggests the model is defaulting to average depth values. This indicates the model is not learning from your input features and is performing poorly.
If only a few dots appear in the scatter plot, the model may have had too few learning points. This limits its ability to accurately learn and predict depth.
Replacing underperforming features with more geologically relevant inputs can significantly improve model accuracy.
What to Do if Results Aren’t Optimal
If the R² Valid scatter plot shows a weak or inconsistent pattern, your model may not be effectively predicting depth. Try the following adjustments:
Lower the classification threshold
In Step 3: Set Up Learning Data, reduce the value used to define mineralized points. A high threshold can result in too few positive samples, limiting valid training data for depth modeling.
Review your input features
In Step 2: Select Input Features, assess whether the rasters you’ve selected are suitable for predicting depth. Remove features with little vertical variation or excessive noise, and experiment with different raster combinations. Replacing underperforming features with more geologically relevant inputs can significantly improve model accuracy.
Adjust model training parameters
In Step 4: Embed Input Features, increase the number of epochs to allow more training cycles. In Step 5: Build Predictive Model, refine cluster settings (e.g. cluster size or minimum points) to better capture subsurface patterns.
Learn More
Interpret other DORA’s Result Graphs:
Create a DORA Prediction Map:
Still Have Questions?
Reach out to your dedicated DORA contact or email support@VRIFY.com for more information.