scholarly journals Resolution Enhancement for Drill-Core Hyperspectral Mineral Mapping

2021 ◽  
Vol 13 (12) ◽  
pp. 2296
Author(s):  
Isabel Cecilia Contreras Acosta ◽  
Mahdi Khodadadzadeh ◽  
Richard Gloaguen
Keyword(s):  
Mineral Exploration ◽  
Resolution Enhancement ◽  
Hyperspectral Data ◽  
Spatial Sampling ◽  
Machine Learning Techniques ◽  
Drill Core ◽  
Accurate Analysis ◽  
Operational Conditions ◽  
Mineral Mapping ◽  
Supervised Learning Algorithms

Drill-core samples are a key component in mineral exploration campaigns, and their rapid and objective analysis is becoming increasingly important. Hyperspectral imaging of drill-cores is a non-destructive technique that allows for non-invasive and fast mapping of mineral phases and alteration patterns. The use of adapted machine learning techniques such as supervised learning algorithms allows for a robust and accurate analysis of drill-core hyperspectral data. One of the remaining challenge is the spatial sampling of hyperspectral sensors in operational conditions, which does not allow us to render the textural and mineral diversity that is required to map minerals with low abundances and fine structures such as veins and faults. In this work, we propose a methodology in which we implement a resolution enhancement technique, a coupled non-negative matrix factorization, using hyperspectral, RGB images and high-resolution mineralogical data to produce mineral maps at higher spatial resolutions and to improve the mapping of minerals. The results demonstrate that the enhanced maps not only provide better details in the alteration patterns such as veins but also allow for mapping minerals that were previously hidden in the hyperspectral data due to its low spatial sampling.

A supervised technique for drill-core mineral mapping using Hyperspectral data

2020 ◽  
Author(s):  
Cecilia Contreras ◽  
Mahdi Khodadadzadeh ◽  
Laura Tusa ◽  
Richard Gloaguen
Keyword(s):  
Machine Learning ◽  
Near Infrared ◽  
Hyperspectral Data ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Drill Core ◽  
Data Set ◽  
Mineral Mapping ◽  
Core Logging ◽  
Learning Techniques

<p>Drilling is a key task in exploration campaigns to characterize mineral deposits at depth. Drillcores<br>are first logged in the field by a geologist and with regards to, e.g., mineral assemblages,<br>alteration patterns, and structural features. The core-logging information is then used to<br>locate and target the important ore accumulations and select representative samples that are<br>further analyzed by laboratory measurements (e.g., Scanning Electron Microscopy (SEM), Xray<br>diffraction (XRD), X-ray Fluorescence (XRF)). However, core-logging is a laborious task and<br>subject to the expertise of the geologist.<br>Hyperspectral imaging is a non-invasive and non-destructive technique that is increasingly<br>being used to support the geologist in the analysis of drill-core samples. Nonetheless, the<br>benefit and impact of using hyperspectral data depend on the applied methods. With this in<br>mind, machine learning techniques, which have been applied in different research fields,<br>provide useful tools for an advance and more automatic analysis of the data. Lately, machine<br>learning frameworks are also being implemented for mapping minerals in drill-core<br>hyperspectral data.<br>In this context, this work follows an approach to map minerals on drill-core hyperspectral data<br>using supervised machine learning techniques, in which SEM data, integrated with the mineral<br>liberation analysis (MLA) software, are used in training a classifier. More specifically, the highresolution<br>mineralogical data obtained by SEM-MLA analysis is resampled and co-registered<br>to the hyperspectral data to generate a training set. Due to the large difference in spatial<br>resolution between the SEM-MLA and hyperspectral images, a pre-labeling strategy is<br>required to link these two images at the hyperspectral data spatial resolution. In this study,<br>we use the SEM-MLA image to compute the abundances of minerals for each hyperspectral<br>pixel in the corresponding SEM-MLA region. We then use the abundances as features in a<br>clustering procedure to generate the training labels. In the final step, the generated training<br>set is fed into a supervised classification technique for the mineral mapping over a large area<br>of a drill-core. The experiments are carried out on a visible to near-infrared (VNIR) and shortwave<br>infrared (SWIR) hyperspectral data set and based on preliminary tests the mineral<br>mapping task improves significantly.</p>

scholarly journals The Rocklea Dome 3D Mineral Mapping Test Data Set

2020 ◽  
Author(s):  
Carsten Laukamp ◽  
Maarten Haest ◽  
Thomas Cudahy
Keyword(s):  
Remote Sensing ◽  
Case Studies ◽  
Test Data ◽  
Mineral Exploration ◽  
Hyperspectral Data ◽  
Mineral Deposits ◽  
Drill Core ◽  
Data Set ◽  
Mineral Mapping ◽  
Barren Ground

Abstract. The integration of surface and subsurface geoscience data is critical for efficient and effective mineral exploration and mining. Publicly accessible datasets to evaluate the various geoscience analytical tools and their effectiveness for characterisation of mineral assemblages and lithologies or discrimination of ore from waste are however scarce. The open access Rocklea Dome 3D Mineral Mapping Test Data Set (Laukamp, 2020; https://doi.org/10.25919/5ed83bf55be6a) provides an opportunity for evaluating proximal and remote sensing data, validated and calibrated by independent geochemical and mineralogical analyses, for exploration of channel-iron deposits (CID) through cover. We present hyperspectral airborne, surface and drill core reflectance spectra collected in the visible-near infrared and shortwave infrared wavelength ranges (VNIR-SWIR; 350 to 2500 nm), as well as whole rock geochemistry obtained by means of X-Ray fluorescence analysis and loss on ignition measurements of drill core samples. The integration of surface with subsurface hyperspectral data collected in the frame of previously published Rocklea Dome 3D Mineral Mapping case studies demonstrated that about 30 % of exploration drill holes were sunk into barren ground and could have been of better use, located elsewhere, if airborne hyperspectral imagery had been consulted for drill hole planning. The remote mapping of transported Tertiary detritals (i.e. potential hosts of channel iron ore resources) versus weathered in situ Archaean geology (i.e. barren ground) has significant implications for other areas where cover (i.e. regolith and/or sediments covering bedrock hosting mineral deposits) hinders mineral exploration. Hyperspectral remote sensing represents a cost-effective method for regolith landform mapping required for planning drilling programs. In the Rocklea Dome area, vegetation unmixing methods applied to airborne hyperspectral data, integrated with subsurface data, resulted in seamless mapping of ore zones from the weathered surface to the base of the CID – a concept that can be applied to other mineral exploration and mineral deposit studies. Furthermore, the associated, independent calibration data allowed to quantify iron oxide phases and associated mineralogy from hyperspectral data. Using the Rocklea Dome data set, novel geostatistical clustering methods were applied to the drill core data sets for ore body domaining that introduced scientific rigour to a traditionally subjective procedure, resulting in reproducible objective domains that are critical for the mining process. Beyond the already published case studies, the Rocklea Dome 3D Mineral Mapping Test Data Set has the potential to develop new methods for advanced resource characterisation and develop new applications that aid exploration for mineral deposits through cover. The here newly presented white mica and chlorite abundance maps derived from airborne hyperspectral highlight the additional applications of remote sensing for geological mapping and could help to evaluate newly launched hyper- and multispectral spaceborne systems for geoscience and mineral exploration.

scholarly journals The Rocklea Dome 3D Mineral Mapping Test Data Set

2021 ◽  
Vol 13 (3) ◽  
pp. 1371-1383
Author(s):  
Carsten Laukamp ◽  
Maarten Haest ◽  
Thomas Cudahy
Keyword(s):  
Remote Sensing ◽  
Case Studies ◽  
Test Data ◽  
Mineral Exploration ◽  
Hyperspectral Data ◽  
Mineral Deposits ◽  
Data Sets ◽  
Drill Core ◽  
Data Set ◽  
Mineral Mapping

Abstract. The integration of surface and subsurface geoscience data is critical for efficient and effective mineral exploration and mining. Publicly accessible data sets to evaluate the various geoscience analytical tools and their effectiveness for characterisation of mineral assemblages and lithologies or discrimination of ore from waste are however scarce. The open-access Rocklea Dome 3D Mineral Mapping Test Data Set (Laukamp, 2020; https://doi.org/10.25919/5ed83bf55be6a) provides an opportunity for evaluating proximal and remote sensing data, validated and calibrated by independent geochemical and mineralogical analyses, for exploration of channel iron deposits (CIDs) through cover. We present hyperspectral airborne, surface, and drill core reflectance spectra collected in the visible–near-infrared and shortwave infrared wavelength ranges (VNIR–SWIR; 350 to 2500 nm), as well as whole-rock geochemistry obtained by means of X-ray fluorescence analysis and loss-on-ignition measurements of drill core samples. The integration of surface with subsurface hyperspectral data collected in the frame of previously published Rocklea Dome 3D Mineral Mapping case studies demonstrated that about 30 % of exploration drill holes were sunk into barren ground and could have been of better use, located elsewhere, if airborne hyperspectral imagery had been consulted for drill hole planning. The remote mapping of transported Tertiary detritals (i.e. potential hosts of channel iron ore resources) versus weathered in situ Archaean bedrock (i.e. barren ground) has significant implications for other areas where “cover” (i.e. regolith and/or sediments covering bedrock hosting mineral deposits) hinders mineral exploration. Hyperspectral remote sensing represents a cost-effective method for regolith landform mapping required for planning drilling programmes. In the Rocklea Dome area, vegetation unmixing methods applied to airborne hyperspectral data, integrated with subsurface data, resulted in seamless mapping of ore zones from the weathered surface to the base of the CID – a concept that can be applied to other mineral exploration and mineral deposit studies. Furthermore, the associated, independent calibration data allowed the quantification of iron oxide phases and associated mineralogy from hyperspectral data. Using the Rocklea Dome data set, novel geostatistical clustering methods were applied to the drill core data sets for ore body domaining that introduced scientific rigour to a traditionally subjective procedure, resulting in reproducible objective domains that are critical for the mining process. Beyond the previously published case studies, the Rocklea Dome 3D Mineral Mapping Test Data Set has the potential to develop new methods for advanced resource characterisation and develop new applications that aid exploration for mineral deposits through cover. The white mica and chlorite abundance maps derived from airborne hyperspectral, presented here for the first time, highlight the additional applications of remote sensing for geological mapping and could help to evaluate newly launched hyper- and multispectral spaceborne systems for geoscience and mineral exploration.

scholarly journals Mineral Mapping and Vein Detection in Hyperspectral Drill-Core Scans: Application to Porphyry-Type Mineralization

Minerals ◽  
2019 ◽  
Vol 9 (2) ◽  
pp. 122 ◽  
Author(s):  
Laura Tusa ◽  
Louis Andreani ◽  
Mahdi Khodadadzadeh ◽  
Cecilia Contreras ◽  
Paul Ivascanu ◽  
...  
Keyword(s):  
Mineral Exploration ◽  
Mining Industry ◽  
Structural Data ◽  
Short Wave ◽  
Variable Density ◽  
Drill Core ◽  
Distribution Maps ◽  
Mineral Mapping ◽  
Core Logging ◽  
Core Mapping

The rapid mapping and characterization of specific porphyry vein types in geological samples represent a challenge for the mineral exploration and mining industry. In this paper, a methodology to integrate mineralogical and structural data extracted from hyperspectral drill-core scans is proposed. The workflow allows for the identification of vein types based on minerals having significant absorption features in the short-wave infrared. The method not only targets alteration halos of known compositions but also allows for the identification of any vein-like structure. The results consist of vein distribution maps, quantified vein abundances, and their azimuths. Three drill-cores from the Bolcana porphyry system hosting veins of variable density, composition, orientation, and thickness are analysed for this purpose. The results are validated using high-resolution scanning electron microscopy-based mineral mapping techniques. We demonstrate that the use of hyperspectral scanning allows for faster, non-invasive and more efficient drill-core mapping, providing a useful tool for complementing core-logging performed by on-site geologists.

Geochemical And Hyperspectral Data Fusion For Drill-Core Mineral Mapping

2019 ◽  
Author(s):  
Cecilia Contreras ◽  
Mahdi Khodadadzadeh ◽  
Laura Tusa ◽  
Christina Loidolt ◽  
Raimon Tolosana-Delgado ◽  
...  
Keyword(s):  
Data Fusion ◽  
Hyperspectral Data ◽  
Drill Core ◽  
Mineral Mapping

scholarly journals MULTI-LABEL CLASSIFICATION FOR DRILL-CORE HYPERSPECTRAL MINERAL MAPPING

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 383-388
Author(s):  
I. C. Contreras ◽  
M. Khodadadzadeh ◽  
R. Gloaguen
Keyword(s):  
Near Infrared ◽  
Short Wave ◽  
Hyperspectral Data ◽  
Training Data ◽  
Electromagnetic Spectrum ◽  
Drill Core ◽  
Data Set ◽  
Mineral Mapping ◽  
Mapping Task ◽  
Liberation Analysis

Abstract. A multi-label classification concept is introduced for the mineral mapping task in drill-core hyperspectral data analysis. As opposed to traditional classification methods, this approach has the advantage of considering the different mineral mixtures present in each pixel. For the multi-label classification, the well-known Classifier Chain method (CC) is implemented using the Random Forest (RF) algorithm as the base classifier. High-resolution mineralogical data obtained from Scanning Electron Microscopy (SEM) instrument equipped with the Mineral Liberation Analysis (MLA) software are used for generating the training data set. The drill-core hyperspectral data used in this paper cover the visible-near infrared (VNIR) and the short-wave infrared (SWIR) range of the electromagnetic spectrum. The quantitative and qualitative analysis of the obtained results shows that the multi-label classification approach provides meaningful and descriptive mineral maps and outperforms the single-label RF classification for the mineral mapping task.

scholarly journals Heart disease prediction using machine learning techniques : a survey

2018 ◽  
Vol 7 (2.8) ◽  
pp. 684 ◽  
Author(s):  
V V. Ramalingam ◽  
Ayantan Dandapath ◽  
M Karthik Raja
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Complex Data ◽  
Learning Techniques ◽  
Vector Machines ◽  
Supervised Learning Algorithms ◽  
Life Threatening

Heart related diseases or Cardiovascular Diseases (CVDs) are the main reason for a huge number of death in the world over the last few decades and has emerged as the most life-threatening disease, not only in India but in the whole world. So, there is a need of reliable, accurate and feasible system to diagnose such diseases in time for proper treatment. Machine Learning algorithms and techniques have been applied to various medical datasets to automate the analysis of large and complex data. Many researchers, in recent times, have been using several machine learning techniques to help the health care industry and the professionals in the diagnosis of heart related diseases. This paper presents a survey of various models based on such algorithms and techniques andanalyze their performance. Models based on supervised learning algorithms such as Support Vector Machines (SVM), K-Nearest Neighbour (KNN), NaïveBayes, Decision Trees (DT), Random Forest (RF) and ensemble models are found very popular among the researchers.

scholarly journals IDENTIFICATION OF A ROBUST LICHEN INDEX FOR THE DECONVOLUTION OF LICHEN AND ROCK MIXTURES USING PATTERN SEARCH ALGORITHM (CASE STUDY: GREENLAND)

2016 ◽  
Vol XLI-B7 ◽  
pp. 973-979
Author(s):  
S. Salehi ◽  
M. Karami ◽  
R. Fensholt
Keyword(s):  
Search Algorithm ◽  
Mineral Exploration ◽  
Optimization Procedure ◽  
Hyperspectral Data ◽  
Pattern Search ◽  
Rock Outcrops ◽  
Bare Rock ◽  
Mixed Pixel ◽  
Mixing Ratios ◽  
Linear Mixtures

Lichens are the dominant autotrophs of polar and subpolar ecosystems commonly encrust the rock outcrops. Spectral mixing of lichens and bare rock can shift diagnostic spectral features of materials of interest thus leading to misinterpretation and false positives if mapping is done based on perfect spectral matching methodologies. Therefore, the ability to distinguish the lichen coverage from rock and decomposing a mixed pixel into a collection of pure reflectance spectra, can improve the applicability of hyperspectral methods for mineral exploration. The objective of this study is to propose a robust lichen index that can be used to estimate lichen coverage, regardless of the mineral composition of the underlying rocks. The performance of three index structures of ratio, normalized ratio and subtraction have been investigated using synthetic linear mixtures of pure rock and lichen spectra with prescribed mixing ratios. Laboratory spectroscopic data are obtained from lichen covered samples collected from Karrat, Liverpool Land, and Sisimiut regions in Greenland. The spectra are then resampled to Hyperspectral Mapper (HyMAP) resolution, in order to further investigate the functionality of the indices for the airborne platform. In both resolutions, a Pattern Search (PS) algorithm is used to identify the optimal band wavelengths and bandwidths for the lichen index. The results of our band optimization procedure revealed that the ratio between R<sub>894-1246</sub> and R<sub>1110</sub> explains most of the variability in the hyperspectral data at the original laboratory resolution (R<sup>2</sup>=0.769). However, the normalized index incorporating R<sub>1106-1121</sub> and R<sub>904-1251</sub> yields the best results for the HyMAP resolution (R<sup>2</sup>=0.765).

Sign in / Sign up

Export Citation Format

Share Document