The Goldeneye project has implemented a unique combination of remote sensing and positioning technologies, exploiting Earth observation and Earth GNSS data, together with data fusion and processing powered by data analytics and machine-learning algorithms. The platform allows satellites, drones and in-situ sensors to collect high-resolution data, which can be processed and converted into actionable intelligence for safety, environmental monitoring and overall productivity, allowing more efficient exploration, extraction and closure. These tools have been demonstrated in 5 field trials in Germany, Bulgaria, Romania, Kosovo and Finland, and the initial results show significant time and cost savings, even up to 80%, for example, in exploration and mine safety, environmental and operations reporting. The project has a duration of 3,5 years and an EC funding of €8.36M. The multidisciplinary consortium includes industrial partners, SMEs, academic/research centres and end-users.

The project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No [869398].

How to cite: Paavola, M.: Goldeneye –a multisource AI-enabled earth observation platform for mining applications, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-17075, https://doi.org/10.5194/egusphere-egu23-17075, 2023.

To accomplish strategic objectives on zero-pollution, the entire mining life cycle (exploration, extraction, closure, mine- site rehabilitation) needs to develop minimal impact exploration and monitoring technologies and applications which are open to the broadest groups of stakeholders. In this respect Earth Observation (EO), Drone & Proximal Sensing and relevant in-situ data bring significant contribution for both, sustainable management of mineral resources and efficient multi-scale monitoring of mining impacts. In this sense, the purpose of the GEOMIN activity, part of the Group on Earth Observations (GEO) Work Programme [1] [2], is to increase awareness and use of state-of-the-art EO data and methods which represent a novel means for sustainable monitoring and management of mineral resources and efficient multi-scale monitoring mining impacts. 

How is GoldenEye project through AI-driven tools and applications enhances the GEOMIN community?

In the scope of the GoldenEye project, OPT/NET delivered the next generation of AI exploitation system: a hybrid platform which combines the processing & automation capabilities of AI with the natural problem-solving abilities of humans. We have developed dedicated applications with our novel approach based on the Artificial Intelligence Knowledge Packs (AI KPs), integrated in GOLDENAI Engine, to rapidly interpret the geographical patterns and environmental impacts caused by the mining activity.

What is the role of the GEO Knowledge Hub (GKH) as the Digital portal in promoting the replicability and re-usability of AI KP in the mining sector and how it relates to Goldeneye ?

The GEO Knowledge Hub (GKH) is a central cloud-based digital library providing access to Earth Observations applications developed by GEO. The GEO Knowledge Hub is part of the GEOSS Infrastructure and helps the  GEO to advance Open Knowledge. The scope of the GKH is to promote the replicability and re-usability of EO Applications by sharing with the end users, all the Knowledge Resources essential to fully understand and re-use them. All the Knowledge Resources are directly shared, curated and organized by the Knowledge Provider to ensure replicability with proper documentation.

Therefore, several Knowledge Packages (KPs) related to the technological solutions of the GoldenEye project can be found in the GKH. In this paper, the KP related to the GOLDENAI platform will be presented, including the description of the integrated AIKPs, such as:

• AI KP for mineral mapping - Band-ratios based on WorldView-3 
• AI KP for mineral mapping - SPCA based on WorldView-3
• AI KP for UML clustering based on Copernicus Satellite imagery (Sentinel-1 SLC)

The paper has been prepared in the frame of the Horizon 2020 co-funded project GOLDENEYE, which has received funds through the GA 869398.

References:

[1] GEO (2023a). GEO Work Programme 2023-2025. Access 09 Jan. 2023. url:

 https://earthobservations.org/geo_wp_23_25.php 

[2] GEO (2023b). GEO WEEK 2022. Access 09 Jan. 2023. url: https://earthobservations.org 

How to cite: Gutierres, F., Matselyukh, T., Paavola, M., Franziskakis, F., De Salvo, P., and Carlos, F.: Discover the new approach to applications development with ‘Artificial Intelligence Knowledge Packs (AI KPs)’ in the GEO Knowledge Hub: Towards the Open and Reproducible Knowledge application for mine site monitoring, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-9595, https://doi.org/10.5194/egusphere-egu23-9595, 2023.

The sulfidic sulfur contained in the host rocks and mining waste leads to strong acid mine drainage processes in the mining landscapes of Trepca, Kosovo and Pyhasalmi, Finnland. In the present, the water quality is usually monitored by discrete sampling and analysis of dissolved metal particles and other chemical parameters. Not only is this a cost- and time-consuming process, but the assessment takes place only on discrete locations.

The main aim of this application is to elaborate the suitability of multispectral remote sensing (R/S) data from different sensors for area-wide identification and quantitative mapping of Acid Mine Drainage (AMD) constituents such as dissolved iron concentration (Fe³⁺), pH value etc. in water bodies. The potential for mining waste to be subject to AMD processes is also being investigated through area-wide quantitative mapping of the sulfate content (SO₄^2-) in solid ground.

In this framework, water and solid ground samples were collected to calibrate and validate the supervised machine learning algorithm of Artificial Neural networks (ANN), used for the identification of dependencies between the multispectral R/S data and the ground measurements. The ANNs of multilayer perceptron type (MLP) is implemented in the advangeo® 2D Prediction software from Beak Consultants GmbH (www.advangeo.com). The modelling and prediction software analyses complex non-linear relationships between a wide variety of spatial controlling parameters and natural complex processes or occurrences, by using methods of artificial intelligence within a Geographic Information System (GIS) environment.

In the mining landscapes of Artana 1 & 2 and Kelmend, AKG has allocated and analysed about 20 water samples and 15 soil samples between May – August 2022 in two field campaigns, whereas low pH values (3 – 4), dissolved iron concentrations up to 25 mg/L and sulfate contents up to 28474 mg/kg have been recorded. Because of the small-scale features in the mining landscapes, high-resolution multispectral images from Worldview-3 and time-series of drone-based acquisitions are used as controlling parameters for the modelling process.

In the tailing pond of Pyhasalmi and the surrounding water environment, the Oulu University has allocated and analysed about 60 water samples between June – October 2022 in two field campaigns. Low pH values (3 – 4), dissolved iron concentrations up to 1800 mg/L and sulfate contents up to 2200 mg/l have been recorded. In this case, medium-resolution multispectral images from Sentinel-2 (Level-1C TOA and Level-2A BOA products) and high-resolution images from Worldview-3 are used as controlling parameters for the modelling process.

In all scenarios, the imagery was acquired during similar time frames as the sampling, to ensure that the measured water / soil grounds parameters correspond to the surface reflectance information.

In the study, advantages and limitations of different multispectral imaging sensors are elaborated. The newly established dependencies from the ANN models can be used to perform area-wide monitoring of AMD processes in time-series, drastically reducing the need for terrestrial measurements in the future.

The paper has been prepared in the frame of the Horizon 2020 co-funded project GOLDENEYE, which has received funds through the Grant Agreement 869398.

How to cite: Hanelli, D., Knobloch, A., Joutsenvaara, J., Puputti, J., Kotavaara, O., Tmava, K., Rexhaj, A., and Bautista Gascuena, A.: AMD Monitoring using multispectral imaging from Worldview-3, Sentinel-2 and drone-based data, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-2597, https://doi.org/10.5194/egusphere-egu23-2597, 2023.

Interferometric Synthetic Aperture Radar (InSAR) has been applied using SAR images from the European Space Agency (ESA) Sentinel-1 constellation, in descending orbit, to obtain the terrain displacement by means of the Coherent Pixel Technique (CPT). This Persistent Scatter Interferometry (PSI) technique was developed in 2002 by the Remote Sensing Laboratory (RSLab) of the Universitat Politècnica de Catalunya, UPC (Lanari et al., 2004; Mora et al. 2002), and recently updated by the Dares Technology team.

ESA Sentinel-1 satellite constellation images were used with Single Look Complex (SLC) images and Interferometric Wide Swath (IW) acquisition mode to detect terrain displacements at Vlaykov Vruh and Tsar Assen porphyry-copper deposits (PCD) in the southern part of Panagyurishte ore district in Bulgaria.

The detected displacement magnitude in Vlaykov Vruh was from 500 to 4,000 m² while for Tsar Assen PCD it ranges from 500 to 2,500 m² where several spots of displacement were detected.

We conclude that in the waste pile area east of the Vlaykov Vruh slope instabilities occurred with a displacement of 3.5 cm. Due to a landslide along the fault structure, a slope displacement of about 4.0 cm for Tsar Assen PCD was detected.

The study is supported by the Horizon 2020 co-funded GOLDENEYE project, which has received funds through Grant Agreement 869398.

References:

Lanari, R.; Mora, O.; Manunta, M.; Mallorqui, J.J.; Berardino, P.; Sansosti, E. 2004. A small-baseline approach for investigating deformations on full-resolution differential SAR interferograms.’ IEEE Trans. Geosci. Remote Sens., 42, 1377–1386.

Mora, O.; Mallorqui, J.J.; Duro, J. 2002.Generation of deformation maps at low resolution using differential interferometric SAR data.’ Proceedings of 2002 IEEE International Geoscience and Remote Sensing Symposium, IGARSS ’02, Toronto, ON, Canada.

How to cite: Domenech, G., Bogdanov, K., Nieto-Yll, D., and Faridi, A.: Interferometric Synthetic Aperture Radar (InSAR) mapping in Vlaykov Vruh and Tsar Assen Cu-porphyry deposits, Panagyurishte ore region, Bulgaria, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-8364, https://doi.org/10.5194/egusphere-egu23-8364, 2023.

Remote sensing UAV based technology combined with modern alteration mapping tools (SWIR, XRD Raman and XRF) for mineral detection has experienced great advances in the Cu-Au epithermal exploration targeting. We demonstrate quick and cost-efficient approach for epithermal gold exploration mapping and evaluation on examples of high-sulphidation epithermal Cu-Au deposits and prospects in the Panagyurishte ore district, Bulgaria.

The Panagyurishte ore district is part of the global Tethyan-Eurasian Cu-Au belt that developed during the Mesozoic as a copper-rich, andesite-dominated magmatic arc system characterized by obvious affiliation of porphyry-copper (PCD) and epithermal Cu-Au ore deposits with granodiorite and andesite dominated magmatic complexes. The target mapping has lacked high-resolution data to identify and prove the geometry of the alteration mineral assemblages and ore controlling fault structures. When distal sensing is combined with field mapping and proximal modern mineral detection methods such as SWIR (1300-2500nm) and Raman spectroscopy, XRD and ore petrography is more efficient tool for detection of hydrothermally altered minerals and zones by their diagnostic spectral signatures.

Drone based photogrammetry approach was applied for hydrothermal alterations mapping and targeting for Cu-Au epithermal deposits exploration in the Panagyurishte ore district, Bulgaria. Mineral alterations maps for Pesovets, Petelovo and Krassen Au-epithermal deposits was assembled using orthophoto model and TIR- 3D mapping to utilize the time and cost efficiency of the subsequent geological exploration field work. For classification and verification of drone orthophoto mosaic geological mapping and rock sampling was carried out in addition to XRF and XRD mapping and stream sediments sampling. UAV- based mapping with selected light bands was used to recognize different hydrothermal alterations styles such as advanced argillic (AAA), argillic (AA) propylitic (Prop) and phyllic (Phy) alteration styles that are overprinting andesitic volcanic sequences in the central part of Panagyurishte ore district. Radial and concentric fault structures and regional strike-slip fault zones have also been proved by UAV-based mapping. Domains of proximal hypogene AAA and AA and more distal propylitic halo as possible host of HS gold mineralization were clearly outlined. XRF mapping of the Pesovets lithocap indicate increasing of As (20-50ppm) and Ti (570-2400ppm) concentrations when approaching AA and AAA alteration domains and could also provide effective vectoring tool for targeting of epithermal Cu-Au mineralization.

 The recent study demonstrates UAV-based mineral mapping approach that will help to improve the exploration targeting and decision making in and eestimation of the Cu-Au mineral potential in cost-efficient manner.

The study is supported by the Horizon 2020 co-funded GOLDENEYE project, which has received funds through the Grant Agreement 869398.

How to cite: Bogdanov, K., Velev, S., and Krumov, I.: Remote-sensing applications for Au-epithermal deposits mapping and exploration targeting in Panagyurishte ore district, Bulgaria, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-2669, https://doi.org/10.5194/egusphere-egu23-2669, 2023.

The Goldeneye project combines remote sensing and positioning technologies with proximal sensing to produce reference calibrated mineralogical maps through data fusion. The project brings together optical satellite sensor data, drone sensor aerial data both optical and electromagnetic as well as spectral ground sensor data. Satellite data can offer spectral signatures of large areas but suffers from limited spatial resolution and blind spots where the higher resolution satellite data is not available. Drone data can offer more variety in spectral wavelengths with higher resolution but there are some drawbacks as well. Namely, NIR vibrational spectroscopy requires background information for successful mineralogical analysis. In addition, the most interesting SWIR range is challenging due to large and very expensive sensors. To cope with these challenges of aerial data, proximal sensing can be applied in locations where satellite imagery is not available, and it can also produce reference information for the calibration of the spaceborne and airborne instruments. The conventionally used analyses for producing mineralogical information from field collected samples are the mineral liberation analysis (MLA) and X-Ray diffraction (XRD) which require extensive sample preparations and are laborious and slow. Goldeneye-project has studied the use of time-gated Raman for easier and more practical production of reference data at the field sites as well as from field collected rock samples. The benefit of Raman is an accurate characteristic spectral fingerprint and an ability to distinguish small mineralogical features as the detection spot is in the range of hundreds of microns. There are continuous wave Raman spectrometers, which are already field deployable. However, conventional Raman suffers from the auto-fluorescence emission triggered by the laser illumination, especially in light-colored rock samples. Time-gated (TG) Raman has the benefit of time-resolved sensing, where the Raman scattering is recorded before the fluorescence signal is over-powering the weaker scattered signal. TG-Raman can thus offer information from a wider variety of geological specimen than the conventional Raman. In Goldeneye-project, TG-Raman spectra were collected with custom sampling solution from mineral samples and drill cores from Erzgebirge exploration site in Germany. The data was analysed together with pXRF reference data to assess the benefit of the data fusion.

The paper has been prepared in the frame of the Horizon 2020 co-funded project GOLDENEYE, which has received funds through the Grant Agreement 869398.

How to cite: Havisto, J., Köhler, M., Uusitalo, S., Paavola, M., Knobloch, A., and Rahkamaa-Tolonen, K.: Development of time-gated Raman proximal sensing for an earth observation platform, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-4901, https://doi.org/10.5194/egusphere-egu23-4901, 2023.

During the last few years, the number of applications utilizing unoccupied aerial vehicles (UAVs), or drones, has increased rapidly in geophysics. The main benefits of airborne surveys are the ability to avoid terrain obstacles such as lakes, rivers, swamps, and ravines and the ability to collect evenly sampled data over large areas quickly. Drone surveys are safer and more cost-effective than ground surveys, especially in rough terrain. Compared to manned aircrafts, drones are cheaper to acquire and to operate. Drones are also versatile, fast to deploy, and ecologically more friendly.

Presently, drones are commonly used for magnetic surveying, and in addition to normal photogrammetry, drones are also used for multispectral and thermal imaging. Electromagnetic (EM), radiometric and gravity applications have been scarce, because the instruments are heavy compared to the modest payload of reasonable priced drones. Special adaptation or completely new instrumentation is needed to enable more drone applications.

Radai is a private Finnish company specialized in drone-based geophysical and environmental surveys. For the last five years Radai have been developing Louhi – a frequency-domain electro­magnetic (EM) system that is lightweight enough to be operated by drones. Presently, Louhi is operated using a large (Ø 100 m) ground loop as the EM source and a standalone 3-component EM receiver is towed by a VTOL (vertical take-off and landing) drone. Radai also develops a fully airborne system where a smaller transmitter loop (Ø 1 m) is fixed to the drone and receiver is towed either by the same drone or by a second drone that flies in tandem with the first one. The applications of the new EM system include geological mapping, mineral exploration, groundwater and geotechnical investigations and environmental monitoring. This paper gives details of the drone-based Louhi EM system and shows results from the first environmental survey made over a tailings pond dam of closed Pyhäsalmi Zn-Cu mine in Finland. The work is made as a part of EU Horizon 2020 funded Goldeneye project.

How to cite: Pirttijärvi, M. and Korkeakangas, P.: Drone-based electromagnetic survey system for environmental applications, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-11469, https://doi.org/10.5194/egusphere-egu23-11469, 2023.

How to cite: Magyar, M., Puputti, J., Kotavaara, O., Joutsenvaara, J., Ariel, E., and Koivurova, T.: Piloting Simulated GNSS in Underground Spaces, EGU General Assembly 2023, Vienna, Austria, 23–28 Apr 2023, EGU23-11816, https://doi.org/10.5194/egusphere-egu23-11816, 2023.