Integrated Object-Based Image Analysis for semi-automated geological lineament detection in southwest England

Yeomans, Chris; Middleton, Maarit; Shail, RK; Grebby, Stephen; Lusty, Paul

doi:10.1016/j.cageo.2018.11.005

Cited by 37 publications

(42 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Willis-Richards and Jackson (1989). Black lines represent regional lineaments derived by Yeomans et al (2019) from Tellus South West airborne geophysical data. Figure 2: Schematic illustrations of the kinematics and structures generated during .…”

Section: Discussionmentioning

confidence: 99%

“…Geochemical datasets include soil and stream-sediment data from the G-BASE survey (British Geological Survey, 2016), Tellus South West airborne geophysical surveys (Beamish et al, 2014;Ferraccioli et al, 2014) and lineament data (Yeomans et al, 2019).…”

Section: Conceptual Tungsten Deposit Modelmentioning

confidence: 99%

“…Structural information was also included, based on observations by Shail et al (2017), using regional lineament data derived from the airborne geophysics by Yeomans et al (2019). A proximity-to structures layer using a Euclidean distance algorithm was prepared based on NW-SE lineaments with lengths > 1200 m; these lineaments are interpreted to be primarily fault-controlled.…”

Section: Geological Evidence Layersmentioning

confidence: 99%

See 2 more Smart Citations

A machine learning approach to tungsten prospectivity modelling using knowledge-driven feature extraction and model confidence

Yeomans¹,

Shail²,

Grebby³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Novel mineral prospectivity modelling presented here applies knowledge-driven feature extraction to a data-driven machine learning approach for tungsten mineralisation. The method emphasises the importance of appropriate model evaluation and develops a new Confidence Metric to generate spatially refined and robust exploration targets. The data-driven Random Forest™ algorithm is employed to model tungsten mineralisation in SW England using a range of geological, geochemical and geophysical evidence layers which include a depth to granite evidence layer. Two models are presented, one using standardised input variables and a second that implements fuzzy set theory as part of an augmented feature extraction step. The use of fuzzy data transformations mean feature extraction can incorporate some user-knowledge about the mineralisation into the model. The typically subjective approach is guided using the Receiver Operating Characteristics (ROC) curve tool where transformed data are compared to known training samples. The modelling is conducted using 34 known true positive samples with 10 sets of randomly generated true negative samples to test the random effect on the model. The two models have similar accuracy but show different spatial distributions when identifying highly prospective targets. Areal analysis shows that the fuzzy-transformed model is a better discriminator and highlights three areas of high prospectivity that were not previously known. The Confidence Metric, derived from model variance, is employed to further evaluate the models. The new metric is useful for refining exploration targets and highlighting the most robust areas for follow-up investigation. The fuzzy-transformed model is shown to contain larger areas of high model confidence compared to the model using standardised variables. Finally, legacy mining data, from drilling reports and mine descriptions, is used to further validate the fuzzy-transformed model and gauge the depth of potential deposits. Descriptions of mineralisation corroborate that the targets generated in these models could be undercover at depths of less than 300 m. In summary, the modelling workflow presented herein provides a novel integration of knowledge-driven feature extraction with data-driven machine learning modelling, while the newly derived Confidence Metric generates reliable mineral exploration targets.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Conceptual Tungsten Deposit Modelmentioning

confidence: 99%

Section: Geological Evidence Layersmentioning

confidence: 99%

See 1 more Smart Citation

A machine learning approach to tungsten prospectivity modelling using knowledge-driven feature extraction and model confidence

Yeomans¹,

Shail²,

Grebby³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The ability to semi-automate lineament extraction and loop through a range of azimuths has meant that more objective lineament maps can be created compared to manual methods (e.g. Rahnama and Gloaguen, 2014;Middleton et al, 2015;ilhav˝et al, 2016;Yeomans et al, 2019). Therefore, a semi-automated lineament detection method can be desirable and increase the objectivity of the analysis.…”

Section: Introductionmentioning

confidence: 99%

“…However, many studies still implement the use of directional filters as a first pass for lineament mapping (Mallast et al, 2011;Sedrette and Rebaï, 2016). The study uses bathymetric data from SW England over a classic area of o shore NW Devon, illustrated in Figure 1 and utilises a state-of-the-art Object-based Image Analysis (OBIA) lineament detection method designed by Yeomans et al (2019). A small subset of the study area over the platform edge is highlighted; full analyses are included in the Supplementary Information.…”

Section: Introductionmentioning

confidence: 99%

Application of the tilt derivative transform to bathymetric data for structural lineament mapping

Yeomans

Head

Lindsay

2021

Journal of Structural Geology

Self Cite

View full text Add to dashboard Cite

High-resolution bathymetry surveys provide an opportunity to analyse local geological structure where onshore areas a ord limited exposure. Semi-automated lineament detection methods are necessary for areas of large coverage where a manual analysis would be subjective and timeconsuming. However, semi-automated approaches are dependent on e ective feature extraction methods to identify genuine lineaments. This study o ers solutions to common problems that can impede processing methods where sharp steps in the seafloor (e.g. palaeocoastlines) are present. Directional gradient, Sobel and Laplacian filters are explored as well as the hillshade and tilt derivative transform for feature extraction prior to applying an object-based image analysis lineament detection approach. The filtered datasets generally perform poorly with a marked improvement when using the hillshade transform. However, we find the azimuth-invariant tilt derivative, which incorporates a convolved vertical derivative, to be the most successful, identifying lineaments in a range of orientations and across a sharp step in the seafloor.

show abstract

Geological mapping and structural interpretation of the Dschang‐Santchou‐escarpment (West, Cameroon), using Landsat 8 OLI/TIRS sensors/SRTM and field observations

et al. 2022

View full text Add to dashboard Cite

Geological mapping of the Dschang‐Santchou‐escarpment rocks in the Western Cameroon region was done using a combination of Landsat 8 OLI/TIRS, SRTM images acquired by satellites on January 21, 2021, and field observations. Lineaments were pre‐processing and processing, performed with Envi 5.1. The different methods of digital processing applied, such as the principal component analysis, the coloured compositions and the combination of bands, show a lithological differentiation of the geological formations of the study area. Lineament maps were obtained by applying Sobel directional filters where 496 lineaments were manually extracted. These lineaments display two main trending directions: the NW–SE trend corresponding to the S2 metamorphic foliation direction and the NE–SW trend corresponding to the S3 magmatic foliation direction. The set of these lineaments represents the fracture network in the area. The field observations as well as the lineaments mapping obtained, allowed us to confirm with the help of the fracture network that we are indeed in an escarped environment. Remote sensing data constitute thus a useful tool for geological mapping and structural reconstitutions in the escarped environment.

show abstract

Integrated Object-Based Image Analysis for semi-automated geological lineament detection in southwest England

Cited by 37 publications

References 28 publications

A machine learning approach to tungsten prospectivity modelling using knowledge-driven feature extraction and model confidence

A machine learning approach to tungsten prospectivity modelling using knowledge-driven feature extraction and model confidence

Application of the tilt derivative transform to bathymetric data for structural lineament mapping

Geological mapping and structural interpretation of the Dschang‐Santchou‐escarpment (West, Cameroon), using Landsat 8 OLI/TIRS sensors/SRTM and field observations

Contact Info

Product

Resources

About