GMPV1.4 | Data driven discovery in mineralogy and geochemistry: Data resources, analytics, and visualization
EDI
Data driven discovery in mineralogy and geochemistry: Data resources, analytics, and visualization
Co-sponsored by IAMG
Convener: Behnam SadeghiECSECS | Co-conveners: Shaunna Morrison, Anirudh PrabhuECSECS, Xiaogang Ma
Orals
| Thu, 27 Apr, 08:30–10:10 (CEST)
 
Room 0.15
Posters on site
| Attendance Thu, 27 Apr, 14:00–15:45 (CEST)
 
Hall X2
Posters virtual
| Attendance Thu, 27 Apr, 14:00–15:45 (CEST)
 
vHall GMPV/G/GD/SM
Orals |
Thu, 08:30
Thu, 14:00
Thu, 14:00
Data-driven discovery, including data analytics and visualization, has the potential for wide application and advancement in Earth and planetary sciences. Recent work has led to new directions in geosciences including geostatistics, mathematical geosciences, mineral informatics, geospatial and spatio-temporal data analysis, mineral prospectivity mapping and GIS, and machine-learning algorithms in 2D to 5D considering frequency, space, time, uncertainty, and any possible dimensions of the datasets. These methods increase the efficiency of scientific exploration and provide a great depth of understanding and interpretation of geo- and planetary systems. In this session, we welcome abstracts from (1) scientific results related to the application of any data analytics and visualization methods in mineralogy and geochemistry on Earth or other planetary bodies, (2) related methods and/or (3) data resources and infrastructure development that enables scientific exploration in mineralogy or geochemistry in Earth and planetary systems.

Orals: Thu, 27 Apr | Room 0.15

Chairpersons: Holly Stein, Norbert Toth
08:30–08:40
|
EGU23-2189
|
ECS
|
Highlight
|
On-site presentation
Ardiansyah Koeshidayatullah and Ivan Ferreira

Mineralogical analysis is critical for understanding the origins and properties of various rock types. Recent advancements in artificial intelligence technologies, particularly supervised deep learning, have transformed qualitative and quantitative mineral analysis. However, current deep-learning approaches require high-quality annotated datasets to acquire and identify different mineralogical characteristics and properties. This is exacerbated by the time-consuming and error-prone labeling processes for the datasets. With self-supervised architectures matching supervised approaches in many computer vision tasks, it is timely to investigate the potential of Self-Supervised Learning (SSL) models in the geosciences. As a result, we use a self-supervised semantic segmentation model to identify and characterize minerals in thin sections, with the model attempting to obtain categories of interest from images without the need for human intervention in annotating the minerals. In this study, we adopted a Self-Supervised Transformer architecture and proposed SelfMin to automatically segment out pyrite minerals from other background gangue minerals in the thin section. Our proposed method achieved 80% in the mean Intersection over Union (mIoU) metric, indicating the model's ability to accurately segment minerals that were not labeled during the annotation process. This work describes the first use of self-supervised deep learning in mineralogical analysis. Further application of this proposed method would allow a robust and efficient advanced qualitative and quantitative mineralogical analysis. It also demonstrates how this technique can be implemented to avoid the need for a large volume of high-quality labeled datasets in other image-based deep learning geosciences analyses.

How to cite: Koeshidayatullah, A. and Ferreira, I.: SelfMin: Self-Supervised Deep Learning for Advanced Mineralogical Analysis, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-2189, https://doi.org/10.5194/egusphere-egu23-2189, 2023.

08:40–08:50
|
EGU23-8924
|
ECS
|
Highlight
|
On-site presentation
Marko Bermanec, Noa Vidović, Liubomyr Gavryliv, Robert M. Hazen, Daniel R. Hummer, Shaunna M. Morrison, Anirudh Prabhu, and Jason R. Williams

Characterizing the types of crystalline structures that form in different environments helps us to better interpret the geologic record and deepens our understanding of mineral stability. To this end, the Dolivo – Dobrovol’sky symmetry index provides a convenient way to quantify the statistical trends in the symmetry of minerals over time (Bermanec et al. 2022). Behavior of the Dolivo - Dobrovol’sky symmetry index was investigated for different paragenetic modes of minerals (Hazen and Morrison 2022). Two datasets were used and compared (code and datasets are available on https://github.com/NoaVidovic/pgm-mineral-pairs-pg). The first one used only minerals, and each mineral was considered just once. In contrast, in the mineral–paragenetic mode pair dataset, minerals were counted once for each of the paragenetic modes in which they occurred.

The paragenetic mode dataset incorporates a number of properties associated with each of more than 60 modes of formation, including relative age and order of that mode’s first appearance, estimated minimum and maximum temperature and pressure of formation, and duration. Paragenetic mode order does not substantially affect the symmetry index of minerals. However, some trends are evident when inspecting the properties of given paragenetic modes. The symmetry indices show a strong correlation with the maximum temperature, maximum pressure, and minimum pressure of paragenetic modes they belong to (Hazen et al. 2022) with correlation coefficients of 69%, 84% and 95%, respectively when using the mineral dataset. These trends show that minerals formed at higher temperature display higher overall symmetry. Trends for pressure are enigmatic: correlations show that minerals formed at higher minimum pressure tend to favor lower symmetry, whereas minerals formed at higher maximum pressure tend to favor higher symmetry.

When using the mineral–paragenetic mode dataset, the correlation coefficients are significantly lower at 42%, 30% and 89% for maximum temperature, maximum pressure, and minimum pressure, respectively. The lower correlation coefficients obtained using the mineral–paragenetic mode pairs might indicate that the paragenetic mode is not as important in terms of trends in symmetry as initially thought. On the other hand, considering a much higher correlation coefficient for the mineral dataset, perhaps there is a more dominant effect where certain P-T conditions tend to favor certain types of symmetry at equilibrium.

How to cite: Bermanec, M., Vidović, N., Gavryliv, L., M. Hazen, R., R. Hummer, D., M. Morrison, S., Prabhu, A., and R. Williams, J.: Symmetry statistics of mineral – paragenetic mode pairs, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-8924, https://doi.org/10.5194/egusphere-egu23-8924, 2023.

08:50–09:00
|
EGU23-15285
|
ECS
|
On-site presentation
Hans van Melick and Oliver Plümper

Recent technological advances allow geoscientists to generate high-resolution (HR) imagery using a variety of different beam-forming mechanisms (e.g. visible light, X-Rays, or charged particles such as electrons and ions). One of the main limitations in producing HR data is the required acquisition time at high magnifications. For example, back-scattered electron (BSE) mapping of a standard petrographic thin section at a resolution of 50nm/pixel takes approximately 60 days and is associated with a storage requirement in the order of 700 GB. Deep-learning methods have proven effective for resolution enhancement in regular photographic images, and in this work we present an integrated image registration and upscaling workflow to enhance image resolution, using real-world BSE datasets.

The proposed workflow requires the acquisition of one, or multiple, HR regions within a region that is imaged at low-resolution (LR). Next, close to pixel-accurate image registration is performed by using the successive implementation of two concepts: i) first the precise location of the HR region within the LR region is determined by using a Fast Fourier Transform algorithm (Lewis, 2005), and ii) final image registration is achieved by iteratively calculating a deformation matrix that, using Newton’s method of optimization, is aiming to minimize an error function describing the differences between both images (Tudisco et al., 2017).

Subsequently, matching HR and LR image pairs are fed into a Generative Adversarial Network (GAN) that learns to produce HR images from the LR counterparts. A GAN consists of two neural networks, a generator and a discriminator. The generator produces synthetic HR data based on LR input, and the discriminator attempts to classify the data as either real HR or synthetic HR. The two networks are trained together in an adversarial process, with the goal of the generator producing synthetic data that the discriminator cannot distinguish from real data.

We demonstrate our method on a variety of large real-world datasets and show that it effectively increases the resolution of full-size BSE maps up to a factor of four, while being able to resolve important features. The upscaling of BSE data, with a factor of four, is associated with a 90% reduction in beamtime and a factor 16 reduction in storage requirements. Image registration, preprocessing, and model training on a high-performance workstation takes 12-24 hours. Having a trained model, inference can be done using a regular laptop.

[1] Lewis, J. P. "Fast normalized cross-correlation, Industrial Light and Magic." unpublished (2005).

[2] Tudisco, Erika, et al. "An extension of digital volume correlation for multimodality image registration." Measurement Science and Technology 28.9 (2017): 095401

How to cite: van Melick, H. and Plümper, O.: Resolution enhancement using deep learning methods: an integrated workflow applied to real-world Back-Scattered Electron (BSE) data, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-15285, https://doi.org/10.5194/egusphere-egu23-15285, 2023.

09:00–09:10
|
EGU23-16338
|
ECS
|
Highlight
|
On-site presentation
Alexander Prent, Lesley Wyborn, Marthe Klöcking, Kerstin Lehnert, Kirsten Elger, Dominik Hezel, Lucia Profeta, Geertje ter Maat, Rebecca Farrington, and Tim Rawling

As geochemical data enable understanding of the Earth system and help to address critical societal issues the organisation thereof is important. Questions asked about processes affecting our environment and geological past become more complex and interdisciplinary in nature as well as multidimensional. To help answer these questions within the geochemistry research capabilities and data compilations are required to be comprehensive and both human and machine readable. Various international organisations are building infrastructure to capture and distribute geochemical data in a consistent manner adhering to the FAIR principles. 

Since May 2021 the OneGeochemistry initiative has officially started efforts towards aligning these organisations’ data frameworks in order to standardise how geochemical data is reported around the globe. In November 2022 the OneGeochemistry initiative applied and was granted to become the OneGeochemistry CODATA Working Group as part of the International Science Councils Committee on Data. The initiative has now also been endorsed by the Geochemical Society, the European Association of Geochemistry and the Working Group has been endorsed by the IUGS Commission on Global Geochemical Baselines. Coordination of the OneGeochemistry initiative is funded through the WorldFAIR project where it is one of the work packages in the larger ‘WorldFAIR: Global cooperation on FAIR data policy and practice’ project. A FAIR Implementation Profile analyses of the geochemistry communities of Australia (AusGeochem), USA (EarthChem, AstroMat) and Europe (GEOROC-DIGIS, EPOS-MSL, NFDI4EARTH) resulted in recognition of the need for common vocabularies for geochemistry data reporting as one of the most important actions to undertake towards international geochemistry data interoperability. A task adopted by EarthChem-DIGIS(GEOROC)-GFZ(DataSystems) collaboration and Research Vocabularies Australia.

Here we will present an overview of the current OneGeochemistry initiative and its preliminary outcomes with regards to FAIR Implementation Profiles and processes that will help enable geochemical data interoperability between various stakeholders.

How to cite: Prent, A., Wyborn, L., Klöcking, M., Lehnert, K., Elger, K., Hezel, D., Profeta, L., ter Maat, G., Farrington, R., and Rawling, T.: The OneGeochemistry initiative as a CODATA Working Group; bringing together international geochemical data systems for easy data discovery, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-16338, https://doi.org/10.5194/egusphere-egu23-16338, 2023.

09:10–09:20
|
EGU23-16683
|
On-site presentation
|
Kerstin Lehnert, Marthe Klöcking, Dominik Hezel, Lucia Profeta, Peng Ji, and Adrian Sturm

Global geochemical datasets are increasingly valuable for solving research questions in geochemistry, volcanology and beyond. To support new research, open sharing and access of geochemical data needs to be easy for researchers so they can take full advantage of the rapidly growing volume of data generated in laboratories across the globe, and to comply with the principles of Open Science. Instead, the fragmented landscape of geochemical data systems makes it difficult for researchers to find, access, and contribute their data: Geochemical data are curated and published in a range of thematic, institutional, and programmatic data systems that differ in architecture, metadata schemas, terminology, and data output formats. Researchers have to figure out where to obtain the data they need; learn to use different search applications; retrieve data from multiple databases and painstakingly reformat the datasets they obtained from different systems to integrate them. They need to select an appropriate repository for their data, and potentially work with different submission systems and templates. Collaboration among geochemical data systems is a critical step to overcome this fragmentation and facilitate geochemical data management and access for the research community by coordinating, aligning, and integrating their systems. Through collaboration, data repositories and databases can also leverage each other’s expertise and resources to operate their services more effectively and efficiently.

We here report about new collaborative efforts among four geochemical data systems that aim to harmonize and integrate their data holdings and software ecosystem for the benefit of the research community and to improve their sustainability: EarthChem (https://earthchem.org/), GEOROC (https://georoc.eu/), MetBase (https://metbase.org/), and the Astromaterials Data System (https://www.astromat.org/).  Building on the long-term collaboration between EarthChem and GEOROC, this collaboration leverages the new development of the Astromaterials Data System with modern technology and two new projects funded to overhaul the infrastructure of the GEOROC and MetBase databases as an opportunity to jointly develop a more resilient, sustainable platform for data exchange. Results of the collaboration so far include: a) alignment of the Astronaut and MetBase data models b) migration of the MetBase data holdings into the Astromat synthesis database; c) alignment of the EarthChem and GEOROC data models; d) new automated synchronization process of GEOROC data to the ECP; e) harmonized vocabularies for chemical variables, analytical methods (Others are in development in alignment with emerging efforts of the OneGeochemstry initiative); f) design of the future shared architecture of EarthChem and GEOROC that includes plans for a joint data entry tool for curators and a single data submission platform for researchers to contribute their data to the affiliated domain repositories. 

The ultimate goal of this harmonization between EarthChem, Astromat, GEOROC and MetBase is to make it easier for researchers to access and contribute data. We hope to integrate further systems in the future, building on ongoing collaborations with the Australian Geochemistry Network, the US Geological Survey, SAMIS (Sample Analysis Microinformation System), the GFZ Data Services, and the Sparrow software.

How to cite: Lehnert, K., Klöcking, M., Hezel, D., Profeta, L., Ji, P., and Sturm, A.: Overcoming Fragmentation of Geochemical Data Resources: Collaboration between EarthChem, Astromat, GEOROC, and MetBase, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-16683, https://doi.org/10.5194/egusphere-egu23-16683, 2023.

09:20–09:30
|
EGU23-10228
|
ECS
|
Highlight
|
Virtual presentation
Yu Wang, Kunfeng Qiu, Alexandru Telea, Zhaoliang Hou, and Haocheng Yu

Machine learning has been shown to be a highly effective method for classifying geochemistry data, such as mineral forming environments and rock tectonics. However, it can be difficult to understand the decision-making processes of these models. To address this issue, we propose the use of Decision Boundary Maps (DBMs) as a visualization tool for interpreting machine learning models. These maps project high-dimensional geochemistry data onto a 2D plane and depict the decision boundaries in the projected space, providing a visual representation of the algorithm's decision-making processes. In addition, DBMs can reveal trends, correlations, and outliers in the data, helping to interpret the results obtained from machine learning-based geochemistry data classification. Seeing the positions of data points, rather than just class labels, is especially valuable because samples in geological categories often follow a sequence, such as a magmatic to hydrothermal transition. Observing the positions of data points allows for the identification of trends from one class to an adjacent class.

How to cite: Wang, Y., Qiu, K., Telea, A., Hou, Z., and Yu, H.: Interpreting Machine Learning Models for Geochemistry Data Classification using Decision Boundary Maps, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-10228, https://doi.org/10.5194/egusphere-egu23-10228, 2023.

09:30–09:40
|
EGU23-4857
|
ECS
|
Virtual presentation
Tong Zhou, Kunfeng Qiu, and Yu Wang

The diverse suite of trace elements incorporated into apatite in ore-forming systems has important applications in petrogenesis studies of mineral deposits. Trace element variations in apatite can be used to distinguish between different types of rocks as well as discriminating between deposit types, and thus have potential as mineral exploration tools. Such classification approaches commonly employ two-variable scatterplots of apatite trace element compositional data. While such diagrams offer easy and convenient visualization of compositional trends, they often struggle to effectively distinguish deposit types because they do not employ all the high-dimensional (i.e. multi-element) information accessible from high-quality apatite trace element analysis. To address this issue, we employ, for the first time, a supervised machine learning-based approach (eXtreme Gradient Boosting, XGBoost) to correlate apatite compositions with ore deposit type, utilizing high-dimensional information. We evaluated 8629 apatite trace element data from five deposit types (porphyry, skarn, orogenic Au, iron oxide copper gold, and iron oxide-apatite) along with unmineralized apatite to discriminate between apatite in mineralized vs unmineralized systems. We could show that the XGBoost classifier efficiently and accurately classifies high-dimensional apatite trace element data according to the ore deposit type (overall accuracy: 94% and F1 score: 89%). Interpretation of the model using the SHAPley Additive exPlanations tool (SHAP) shows that Th, U, Eu and Nd are the most indicative elements for classifying deposit types using apatite trace element chemistry. Our approach has broad implications for the understanding of the sources, chemistry and evolution of melts and hydrothermal fluids resulting in ore deposit formation.

Keywords: Machine learning; apatite; Trace elements; Ore deposit type; XGBoost

How to cite: Zhou, T., Qiu, K., and Wang, Y.: From Trace Elements to Petrogenesis: A Machine Learning Approach to Determine Ore Deposit Type from Trace Elements Analysis of Apatite, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-4857, https://doi.org/10.5194/egusphere-egu23-4857, 2023.

09:40–09:50
|
EGU23-14683
|
On-site presentation
Andrea Schito, Natalia Amanda Vergara Sassarini, Marta Gasparrini, Pauline Michel, and Sveva Corrado

In the last decades, the use of Raman spectroscopy on dispersed carbonaceous material in rocks has become a promising tool for geothermometry and thermal maturity assessment. In diagenesis the main problem is linked to organofacies composition and the need of time-consuming optical classification (Henry et al., 2019, Sanders et al., 2022). In this work, three different methods of clustering analysis on Raman spectra were tested as a potential approach to recognize the three main organofacies (amorphous organic matter, translucid and opaque phytoclasts) that characterize a set of 27 organic-rich samples from the Lower Toarcian source rock interval (Schistes Carton) of the Paris Basin (France).

Raman analyses were performed on concentrated organic matter obtained by acid attacks, with around 60 counts for each sample. Principal Component Analysis (PCA) was applied to reduce the dimensionality of each dataset on a 2-D score-plot. Unsupervised clustering was then performed by using three different clustering algorithms: k-means, Gaussian Mixture Models (GMM), and Density-Based Spatial Clustering for Applications with Noise (DBSCAN). The main task of these algorithms is to correctly assign the number of clusters, their size, orientation, and distribution in the score-plot that related to the heterogeneities in organofacies composition.

Results show the best performances are achieved through the application of GMM clustering that can successfully determine cluster’s geometry and optimal numbers with an accuracy mostly higher than 80% for the translucid phytoclasts group, that is the target for thermal maturity assessment.  This is a preliminary attempt showing promising application for unsupervised learning techniques coupled with Raman spectroscopy that could be applied in industrial routinely organic matter characterization or in the analysis of big dataset in both Earth and planetary sciences.

 

Henry, D. G., Jarvis, I., Gillmore, G., & Stephenson, M., 2019. Raman spectroscopy as a tool to determine the thermal maturity of organic matter: Application to sedimentary, metamorphic and structural geology. Earth-Science Reviews 198, 102936.

Sanders, M. M., Jubb, A. M., Hackley, P. C., & Peters, K. E., 2022. Molecular mechanisms of solid bitumen and vitrinite reflectance suppression explored using hydrous pyrolysis of artificial source rock. Organic Geochemistry 165, 104371.

How to cite: Schito, A., Vergara Sassarini, N. A., Gasparrini, M., Michel, P., and Corrado, S.: Unsupervised Clustering applied on Raman spectra of dispersed carbonaceous material: a case history from the Paris Basin (France), EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-14683, https://doi.org/10.5194/egusphere-egu23-14683, 2023.

09:50–10:00
|
EGU23-15241
|
ECS
|
On-site presentation
Hannah Vogel, Hamed Amiri, Austin Arias, Oliver Plümper, and Markus Ohl

Many macroscopic transport properties and physical processes, such as the flow of fluids through a porous medium, are directly controlled by its microstructure, specifically the presence and connectivity of individual pore spaces at micron and submicron scales. Reconstructing and evaluating the material properties of porous media plays a key role across many engineering disciplines from subsurface storage (e.g., CO2 and hydrogen) to geothermal energy and reservoir characterization. As such, the rapid and reliable characterization, evaluation, and simulation of complex pore microstructures is required not only to enhance our understanding of the fundamental processes occurring at the pore scale, but to also better estimate their material behavior on a larger scale.

These material behaviors are inherently volumetric and therefore cannot be accurately modelled using two-dimensional (2D) data alone. As a result, the accuracy of reconstruction techniques used to extract these morphological properties and spatial distributions is in part determined by the quality of available three-dimensional (3D) microstructural datasets. However, in comparison to their 3D counterparts, 2D imaging techniques are typically more cost efficient, easier to collect, and higher resolution. Our goal of generating statistically accurate 3D reconstructions of complex pore microstructural distributions based on high resolution 2D datasets is essential to bridging this dimensionality gap.

Newly explored 2D-to-3D reconstruction techniques based on deep-learning (DL) algorithms offer an alternative means of generating robust and statistically representative digital 3D rock reconstructions by measuring some spatial morphological properties and statistical microstructural descriptors (SMDs) of porous media samples from high-resolution 2D datasets. These DL models are highly flexible and capable of capturing a variety of complex microstructural features given representative 2D training datasets. In this paper, we implement a newly developed deep Generative Adversarial Network (GAN), known as SliceGAN, to synthesize novel binary digital 3D reconstructions using high-resolution 2D back-scattered electron (BSE) images obtained from thin-sections oriented in the x-, y- & z-direction.

Our trained model is capable of accurately reconstructing complex 3D microstructural features of porous media through capturing the underlying (micro-)structural and morphological properties contained in the original sample (2D) thin-sections. To demonstrate the effectiveness of our trained model, we conducted a comparative analysis between the generated 3D reconstructions and real sample datasets by evaluating morphological properties (volume fraction, surface area, equivalent diameter, pore orientations, etc.) as well as the widely popular SMD the two-point correlation function (S2 (r) ). The resulting reconstructions are virtually indistinguishable, both visually and statistically, from the real sample. Our research paves the way for quickly and accurately describing complex heterogenous media for the prediction of transport processes, for example, carbon and hydrogen storage and extraction.

How to cite: Vogel, H., Amiri, H., Arias, A., Plümper, O., and Ohl, M.: 3-D Reconstructions of Porous Media from 2-D input via Generative Adversarial Networks (GANs), EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-15241, https://doi.org/10.5194/egusphere-egu23-15241, 2023.

10:00–10:10
|
EGU23-4648
|
ECS
|
Virtual presentation
Chuntao Liu, C. Brenhin Keller, Xiaoming Liu, and Zhou Zhang

Reconstructing the emergence of the modern continental crust is crucial to understand the evolution of the crust, the onset of plate tectonics, elemental cycling, and long-term climate. However, it remains highly contentious about when and how the major subaerial continental crust emerged over time. Here, we used a machine learning (ML) model (XGBoost) to reveal the exposed history of continental crust over the last 3.8 billion years ago (Ga). First, we compiled ~10,000 modern subaerial or submarine basalts with major and trace elements to train the ML model. Then, the trained ML model (with resampling) was utilized to predict and calculate the mean proportions of subaerially erupted continental basaltic rocks since 3.8 Ga. The result suggested that the subaerial proportion only reached about 50% at ~2.5 Ga, indicating the exposure of the continental crust was far from the present-day level at the end of the Archean era. On the other hand, since ~1.8 Ga, the subaerial proportion of the continental crust exhibited a dynamic balance between ~60% and 80%, reaching the present-day level.

How to cite: Liu, C., Keller, C. B., Liu, X., and Zhang, Z.: The emergence of Continental Crust Revealed by Machine Learning, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-4648, https://doi.org/10.5194/egusphere-egu23-4648, 2023.

Posters on site: Thu, 27 Apr, 14:00–15:45 | Hall X2

Chairpersons: Holly Stein, Norbert Toth
X2.167
|
EGU23-5863
|
ECS
Bartosz Puzio and Maciej Manecki

The standard absolute entropies of many minerals and mineral-based inorganic materials are unknown, thereby precluding a complete insight into their thermodynamic stability. This includes many apatites. The Apatite supergroup is one of the largest groups of minerals. Consequently, they are an incomparable testing ground for finding regularities in the variation of their thermodynamic function of state, e.g., standard entropy (S°). In the early 2000’s Jenkins and Glasser [1] showed that the formula unit volume alone, Vm, can be used to estimate the standard entropy for any inorganic compound.

It was recently indicated that in terms of their thermodynamic properties, the apatite supergroup splits into distinct subgroups (populations) [2]. These subgroups are formed by Me10(AO4)6X2 with the same Me2+ cations (e.g., Pb2+, Cd2+, Ca2+, Ba2+, Sr2+) and tetrahedral AO43- anions (e.g., A=P, As, V), but with different anions at the X position (e.g., F-, Cl-, Br-, I-, OH-). We found strong linear relationships between of apatites and their Vm observed within these subgroups. A system of linear relationships (calibrated with existing experimental data) indicating high positive correlations within selected subgroups of apatites is presented in Fig. 1.

Fig. 1 Standard entropy (S°) vs. formula unit volume (Vm)for selected apatite subgroups. Errors bars are within the marker.

Table 1. Selected estimated standard entropies (S°) and calculated formation entropies (ΔS°f, el)of iodine apatites.

Apatite

Estimated S° (J/mol·K)

ΔS°f, el (J/mol·K)

Ca10(PO4)6I2

840.7

-2412.8

Sr10(PO4)6I2

1117.2

-2264.2

Pb10(PO4)6I2

1201.1

-2271.4

Ca10(AsO4)6I2

1016.1

-2205.0

Pb10(AsO4)6I2

1364.5

-2075.5

Pb10(VO4)6I2

1359.6

-2040.0

 

Using the new estimated with high accuracy values, it is possible to calculate the Gibbs energy of formation and plot stability fields for apatites for which this has not been possible so far. Financial support for the research was provided to B.P. by the Polish National Science Centre (NCN) grant No. 2017/27/N/ST10/00776.

References:

[1] Jenkins, H. D. B., & Glasser, L. (2003). Standard absolute entropy, values from volume or density. 1. inorganic materials. Inorganic Chemistry42(26), 8702-8708.

[2] Puzio, B., & Manecki, M. (2022). The prediction method for standard enthalpies of apatites using the molar volume, lattice energy, and linear correlations from existing experimental data. Contributions to Mineralogy and Petrology177(11), 1-34.

[3] Wang, J. (2015). Incorporation of iodine into apatite structure: a crystal chemistry approach using Artificial Neural Network. Frontiers in Earth Science3, 20.

 

How to cite: Puzio, B. and Manecki, M.: Estimation of missing third-law standard entropy of apatites using the optimized Volume-based Thermodynamics, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-5863, https://doi.org/10.5194/egusphere-egu23-5863, 2023.

X2.168
|
EGU23-2439
|
ECS
Xiangyu Zhao, Zhitong Xiong, and Xiaoxiang Zhu

Soil parameters are relevant and valuable for various applications such as agriculture production, scientific research, and policy making. Since acquiring such physical or chemical information could be cost-consuming by traditional methods, remote sensing and data analysis have become exciting research fields for soil parameter prediction tasks.   Many papers show that minerals and chemical materials correlate with the corresponding spectral reflectance. Based on this characteristic, there are many works using different data analysis methods such as machine learning and deep learning to predict soil properties, especially from multi- and hyper-spectral images. However, limited by the small data size, many models suffer from the overfitting problem and could not extrapolate to unseen data. Moreover, the currently existing methods only generate predictions with no consideration of the correlation among different target parameters. In this work, we propose and implement a deep learning based multitask method to predict multiple chemical properties simultaneously from hyperspectral images. To initialize the model, we use the pre-trained weights from ImageNet. To make better use of the correlation among different parameters, our model consists of shared layers and task-specific branches where each customized branch generates the prediction for one target property. Our method is implemented on the dataset from the Hyperview challenge organized by KP Labs and ESA. In this dataset, 1732 hyperspectral patches are available now and each patch has 4 soil parameters including K, P205, Mg, and pH. After comprehensive experiments, our method achieves the highest score of 0.87, which shows superior performance in this regression task.

How to cite: Zhao, X., Xiong, Z., and Zhu, X.: Soil Parameters Prediction from Hyperspectral Images via Multitask Learning, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-2439, https://doi.org/10.5194/egusphere-egu23-2439, 2023.

X2.169
|
EGU23-3925
Liubomyr Gavryliv, Vitaliy Ponomar, and Marián Putiš

An Application Programming Interface (API) is a secured, documented and accessible web service and an entry point to any database—both relational and non-relational. As a rule, it exposes the data in different formats and allows filtering of the data by utilizing the query parameters. Accordingly, it allows the developers and data scientists to retrieve and query data through HTTP or WebSocket protocols using command-line HTTP clients or language-specific ones (e.g., axios, requests). The most complicated and essential aspects of developing an API are choosing the stack, structuring the codebase and optimizing the application's performance. 

A general rule of thumb is to develop an API to be (1) platform-independent and (2) support the versioning and evolution of the service by adding new functionalities while supporting the previous versions. Other features of a robust and reliable API are documentation according to OpenAPI Specification (OAS), scalability, caching, development and production environments portability, concurrency and more.

mineralogy.rocks API for mineralogical and related data is currently a work in progress with open-source code. It follows RESTful architectural concepts, best practices of clean codebase development and the twelve-factor methodology. The application is developed in Django—a Python web framework and utilizes PostgreSQL 13 database under the hood. The APIs' design is organized around the resources, e.g. the endpoints' naming conventions are predictable, standard and follow the same patterns. 

The codebase structure deviates from the standard out-of-the-box structure provided by the Django framework to isolate database-, server- and application-specific utilities. The local environment of the application is set up using Docker and docker-compose containerization technology for the efficiency of the development. 

The CI/CD integration has zero downtime—it is organized around GitHub Actions that allow for building the application, deploying the isolated container to a cloud, and updating the Kubernetes cluster application accordingly. 

The mineralogy.rocks API supports open science and promotes the innovation, quality, and public impact of mineralogy. Our open science activities are implemented to make the results produced and used in research publicly available and their metadata quickly and widely available for reuse.

This project, No. 3007/01/01, has received funding from the European Union’s Horizon 2020 research and innovation Programme based on a grant agreement under the Marie Skłodowska-Curie scheme No. 945478 and was supported by the Slovak Research and Development Agency (contract APVV-19-0065).

How to cite: Gavryliv, L., Ponomar, V., and Putiš, M.: Designing an API for a mineralogical database, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-3925, https://doi.org/10.5194/egusphere-egu23-3925, 2023.

Posters virtual: Thu, 27 Apr, 14:00–15:45 | vHall GMPV/G/GD/SM

Chairpersons: Holly Stein, Norbert Toth
vGGGS.13
|
EGU23-1585
|
ECS
|
Highlight
Behnam Sadeghi and David Cohen

A key task in the analysis of exploration geochemical data is the selection and application of efficient classification models to discriminate mineralization-related signals from other processes affecting variation in element concentrations. Similarly in environmental or urban geochemistry one objective is to separate geochemical patterns associated with anthropogenic contamination from geogenic processes. To classify geochemical maps into background or anomalous samples or regions, a variety of mathematical and statistical models have been developed. In this study various fractal modelling has been applied to centered logratio transformed Cu, Ba, Mn, Pb, Zn, In, As, Au, and Ag contents of soil samples from the Geochemical Atlas of Cyprus. Areas with contamination have previously been shown not to display normal fractal behavior for values exceeding lithology-dependent background populations. Therefore, two new fractal methods – concentration-concentration (C-C) and concentration-distance from centroid-points (C-DC) – were applied to discriminate anthropogenic from geogenic anomalies. One of the strongest indicators of proximity to major Cu mineralization is In. The C-C model displays broad similarity between the Cu-In pairing and the raw Cu, and between its reverse in the In-Cu pairing and raw In. Of the five populations that emerge from the Cu-In fractal model, the first two (regional background and weakly anomalous) are largely restricted to the Circum-Troodos Sedimentary Succession units. The moderately anomalous population extends across all the basalts and north from the Troodos Ophiolite (TO) across the fanglomerates and more recent alluvium-colluvium that contains material shedding north off the TO. It is noted that the strongest anomalies are at the boundary between the sheeted dyke complex and basalts and on one of the major NE-trending structures that cut across the TO, but where there are only a small number of minor Cu mineralization occurrences. In the C-DC model, the centroids used to model the spatial variation of the soil geochemistry were the known mineral deposits. The Cu C-DC model delivers just two populations that are lithologically-controlled. The first spans the ultramafic TO core and the Pakhna Formation carbonates (the two extremes in the raw data geochemical compositions), and all other units, including the TO mafics, Mamonia Terrain, and the fanglomerates and alluvium-colluvium areas in the second population. The In C-DC model is somewhat similar to the In-Cu C-C model, but the second major population is more restricted to the sections of the basalts containing known Cu mineralization as well as a restricted zone in the sheeted dykes in western TO. Applying the C-DC model to the transformed scores, there are three main populations evident. The highest one contains all the known Cu mines and mineral deposits, as well as a number of NE-trending zones that cut across the sheeted dykes on the western and the eastern sides of the TO, and which also appear to follow the major sinistral faults that transect the TO.

How to cite: Sadeghi, B. and Cohen, D.: Discrimination of anthropogenic contamination and the effects of mineralization in soils from background patterns using multifractal modelling: Cyprus case study, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-1585, https://doi.org/10.5194/egusphere-egu23-1585, 2023.

vGGGS.14
|
EGU23-5095
|
ECS
Yiwei Cai, Kunfeng Qiu, and Zhaoliang Hou

Analysis of optical microscopic image data is crucial for identifications of mineral phases, and thus directly relevant to the subsequent methodology selections of the further detailed petrological exploration. So far, large-dimensional image analyses are dominantly based on digital image datasets, and the automatic identification of the optical microscopic data is still poorly examined. Here, by testing the Swin Transformer, a deep learning algorithm on different metal mineral phases, we proposed a well-behaved mineral recognizer with high accuracy of 92.8% and strong global ability. In addition, we apply Class Activation Mapping (CAM) is introduced for the first time in mineral identification tasks and reveals the interpretability of the models, allowing us to more intuitively observe that mineral edges are the most effective model identification features. The results demonstrated that optical microscope data can not only rely on pixel information, and machine learning can accurately extract all available attributes, which reveals the potential to assist in data exploration and provides an opportunity to carry out spatial quantization at a large scale (cm-mm).

Keywords: Metal mineral; Microscope images; Deep learning; Swin Transformer; Class Activation Mapping

How to cite: Cai, Y., Qiu, K., and Hou, Z.: Metal mineral classification under microscope images using deep learning, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-5095, https://doi.org/10.5194/egusphere-egu23-5095, 2023.

vGGGS.15
|
EGU23-782
|
ECS
|
Hamidreza Gholizadeh, Elizaveta Krasnova, and Ahmadreza Rabbani

Coastal Fars is the main gas-bearing region in Iran, where the reservoir units are dedicated to the Paleozoic hydrocarbon system. Geochemical explorations in this region indicate that natural gas is commonly associated with elevated non-hydrocarbon components, especially hydrogen sulfide and carbon dioxide. Previously it was shown that the Thermochemical Sulfate Reduction (TSR) is the most probable mechanism, accounting for H2S occurrence in Permo-Triassic reservoirs in this region; however, its effect on the accumulated gas’s chemistry transformation has not been studied thoroughly. In this study, the molecular and isotopic composition of 12 gas samples in addition to the previously-published results of integrated analyses on rock and condensate, were utilized to trace potential alterations caused by the given phenomenon exhaustively. A slight increase in aromatic to saturate hydrocarbon components ratio with the extent of TSR and the presence of reported sulfur-rich pyrobitumen (Saberi, et al., 2014) indicate liquid hydrocarbon involvement in the primary stage of the sulfate reduction process. Further, the differential increase of δ13C of gas components, decrease of δ13C (methane) - δ13C (ethane) (from -4.3 to -13.1‰), and increase in carbon-dioxide concentration with the increase of hydrogen sulfide along with gas dryness (from 91 to 96%) show the dominancy of C2-C4 hydrocarbon gas components in the second stage of TSR. Comparative low reservoir temperature (~90°C) does not correspond to the contribution of methane into the given phenomenon; however, a noticeable increase in δ13C (methane) (from -41.7 to -34.7‰) with the increase of hydrogen sulfide was seen. Thermochemical Sulfate Reduction impact on studied parameters is analogous to thermal maturation, but the process from heavy-hydrocarbon-dominated TSR to methane-dominated TSR presents different trends of δ13C (methane) - δ13C (ethane), ln(C1/C2) from those of maturation (Hao, et al., 2008). Simultaneous carbon-dioxide content increase and decrease in its isotopic composition with the extent of TSR indicate its presence relevancy to the given phenomenon; however, carbon isotope values of CO2 (from -5.92 to -13.93‰) are too heavy to verify this idea. According to Dai et.al (Dai, et al., 1996) it can be concluded that carbonate's dissolution has contributed to carbon-dioxide gas. Hence, a series of TSR corresponding to condensate, wet gas, and dry gas stages, respectively, has led to higher aromatic/saturate ratios, heavier hydrocarbon components, lighter carbon dioxide molecules, and relative gas dryness in the studied fields.

 Bibliography

  • Dai, J. X., Song, Y., Dai, C. S. & Wang, D. R., 1996. Geochemistry and Accumulation of Carbon Dioxide Gases in China. AAPG Bulletin, 80(10), pp. 1615-1626.
  • Hao, F. et al., 2008. Evidence for multiple stages of oil cracking and thermochemical sulfate reduction in the Puguang gas field, Sichuan Basin, China. AAPG Bulletin, 92(5), pp. 611-637.
  • Saberi, M. H., Rabbani, A. & Ahmadabadi, K. A., 2014. The Age and Facies Characteristics of Persian Gulf Source Rocks. Petroleum Science and Technology, Volume 32, pp. 371-378.

 

How to cite: Gholizadeh, H., Krasnova, E., and Rabbani, A.: Assessment of natural gas chemistry alteration by extent of H2S production and evidences for multiple stages of TSR in two gas fields in Gavbandi-High, Iran, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-782, https://doi.org/10.5194/egusphere-egu23-782, 2023.

vGGGS.16
|
EGU23-6284
|
ECS
Ziyi Zhu, Kunfeng Qiu, Fei Zhou, Yu Wang, and Tong Zhou

Zircon, a stable paragenetic mineral in various geological environments, has been recognized as a great tool to study the ages of primary rocks. Trace elements of zircons thus can record the geological evolution processes. Zircon-associated trace elements have been long studied for zircon classification and formation traditionally using binary diagram technique, classical examples including Th-U and LaN-(Sm/La)N diagrams. However, with the massive increase of zircon research, the traditional binary diagrams currently cannot precisely classify zircon types because the binary plot cannot demonstrate the higher dimensional information. It therefore significantly restricts a clear understanding of zircon formation. To address the research gap, we performed the machine-learning-based approaches on 3498 zircon trace-element data of different zircon genetic types, producing high-dimensional zircon-classification diagram plots. We applied and tested four machine learning methods (random forest, support vector machine, artificial neural network, and k-nearest neighbor) and proposed that support vector machine can best contribute to zircon genetic classification study, with an 86.8% accuracy in the prediction of zircon type and formation. In addition to the high-dimensional zircon classification diagram, this work massively improves the accuracy of zircon formation analyses by trace elements, which benefit future studies in zircons. Using the machine learning approach on zircon trace element big data is an effective multidisciplinary exploration of the modern data science technique in the geochemistry study.

How to cite: Zhu, Z., Qiu, K., Zhou, F., Wang, Y., and Zhou, T.: Machine learning based approach for zircon classification and origin, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-6284, https://doi.org/10.5194/egusphere-egu23-6284, 2023.