Overview
Data Augmentation transforms raw geological, geochemical, and geophysical data into continuous grids (rasters) that support exploration analysis and modelling, including DORA.
This article explains the output of each Data Augmentation Module, helping you understand what each Module represents, what data goes in, and how the processing works.
Outputs
Module | Simple Overview | Functional Summary | Technical Breakdown |
Distance Maps | Shows how close each cell is to things like roads, faults, or boundaries. | Rasterizes vector features (points, lines, polygons) into distance-to-feature rasters for spatial modelling. | Input: Vector data (.SHP) Output: Raster Key Parameters: Grid resolution, AOI, Vector category, Desired category Processing: Converts vector features into distance-to-feature raster. One grid raster per feature type if categories are specified. |
Data Density Maps
| Highlights areas where you have lots of information vs. little to none. | Creates a raster that reflects how many data layers are present per pixel, highlighting data-rich areas. | Input: Vector Data (.SHP), Raw Raster Output: Raster Key Parameters: Grid resolution, AOI Processing: Counts the number of layers informing each pixel to highlight data density. |
Structural Domain Maps | Creates a map of which way rock layers are tilted or folded underground. | Convert orientation measurements (strike/dip) into interpolated structural grids, vector fields. | Input: Measurement points (.SHP) Output: Raster Key Parameters: Grid resolution, AOI, Structure types, Strike, Dip, Right hand rule Processing: Converts structural measurements into interpolated strike field maps using transformation rules. |
Fault Disturbance Maps | Maps how the volume of rock is affected by a fault. | Model spatial influence and disturbance zones around fault lines with customizable decay. | Input: Line vectors (.SHP) Output: Raster Key Parameters: Grid resolution, AOI, Faults, Wavelength, Disturbance level, Decay Processing: Models wave-based disturbance zones around faults with decay scaling away from fault trace. |
Computer Vision Maps | Pulls out hidden patterns in the data using image recognition techniques. | Apply deep learning filters (feature extraction) to raster inputs to extract high-level spatial features. | Input: Raster Output: Raster Key Parameters: Grid resolution, AOI, Number of filters Processing: Applies deep learning, RESNET-50, to extract spatial features from raster data. |
Texture Filter Maps | Pulls out hidden patterns in the data using Haralick filters. | Apply deep learning filters (feature extraction) to raster inputs to extract high-level spatial features. | Input: Raster Output: Raster Key Parameters: Grid resolution, AOI, Number of filters Processing: Applies Haralick filters to extract spatial features from raster data. |
Multivariate Anomaly Maps | Flags areas where the data looks strange or unexpected when layers are compared together. | Detect anomalies based on multi-layer raster analysis using an anomaly scoring algorithm. | Input: Data Rasters Output: Raster Key Parameters: Grid resolution, AOI, Target grids Processing: Analyzes multiple grids to detect anomalies across all data, using a scoring algorithm across layers. |
Lineament Maps | Traces straight-line features like fractures or boundaries that show up in the data. | Identify and extract linear features (lineaments) using edge detection and line-following algorithms. | Input: Data Raster Output: Raster Key Parameters: Grid resolution, AOI, Edge detection sensitivity, Line length, Gaps, Orientation filters Processing: Detects and traces linear features from raster data using edge and line detection techniques. |
Learn More
Still have questions?
Reach out to your dedicated DORA contact or email Support@VRIFY.com for more information.