S34I 2025 Abstracts

Area 1 - S34I - From the Sky to the Soil
Full Papers Short Papers

Area 1 - S34I - From the Sky to the Soil

Full Papers
Paper Nr: 5
Title:

S34I Project: Secure and Sustainable Supply of Raw Materials for EU Industry
Authors:

Ana Cláudia Teodoro, Joana Cardoso-Fernandes, Mihaela Gheorghe, Francesco Falabella, Fabiana Calò, Antonio Pepe, Delira Hanelli, Andreas Knobloch, Roberto De La Rosa, Fahimeh Farahnakian, Georgios Periklis Georgalas, Enoc Sanz-Ablanedo, Vaughan Williams and Krištof Oštir
Abstract: The Secure and Sustainable Supply of Raw Materials for EU Industry – S34I project is researching and innovating new data-driven methods to analyze Earth Observation (EO) data, supporting systematic mineral exploration and continuous monitoring of extraction, closure, and post-closure activities to increase European autonomy regarding raw materials (RM) resources, and to use EO not only for the management of technical and environmental issues for a green transition but also to support public awareness, mining's social acceptance, and better legislation. S34I uses data from satellites, airborne, unmanned aerial vehicles, ground-based sensors, underwater hyperspectral imaging and conventional in-situ techniques/methods and fieldwork. The S34I project is supporting the technical experiments and pilot validations/demonstrations for the six pilot use cases and at different phases of the mining life-cycle to address the challenges of the topic: Onshore exploration (Aramo in Spain); Shallow water exploration (Ria de Vigo in Spain); Extraction (Gummern in Austria); and Closure/post-closure (Lausitz in Germany, Aijala and Outokumpu in Finland). The S34I project involves 19 partners from 12 European countries. The project started in January 2023 and ends in June 2025. bi cj dk el fm g
Download
Paper Nr: 7
Title:

An Ensemble Modeling Approach for Mapping Critical Mineral Distribution with LiDAR and PRISMA Data
Authors:

Fahimeh Farahnakian, Mahyar Yousefi and Ana Cláudia Teodoro
Abstract: Traditional mining exploration techniques require significant effort, including drilling and sample collection, making the process highly challenging and costly. The application of machine learning (ML) in mineral exploration has revolutionized the field by improving efficiency and accuracy in identifying critical raw materials (CRM). This study presents a novel framework that integrates Light Detection and Ranging (LiDAR) and PRISMA hyperspectral data with ML techniques to enhance mineral exploration. By leveraging an ensemble model combining Random Forest (RF) and Multi-Layer Perceptron (MLP), this approach captures complex spatial and spectral patterns, improving the prediction of cobalt, copper, and nickel concentrations. To address the challenge of limited labeled data, synthetic samples were generated using the Gaussian Copula Synthesizer (GCS), enhancing model generalization. The proposed methodology was validated at the ´Aramo mine in Asturias, Spain, demonstrating that the fusion of multispectral and topographical features significantly improves predictive accuracy. The results show that the scalability and robustness of this framework for identifying CRM in geologically significant yet underexplored regions.
Download
Paper Nr: 8
Title:

Evaluation of EnMAP Hyperspectral Data for the Identification of Placers in the Rias Baixas Region (Spain)
Authors:

Beatriz L. Araújo, Joana Cardoso-Fernandes, Antonio Azzalini, Morgana Carvalho, Alexandre Lima, Francisco J. González and Ana Cláudia Teodoro
Abstract: Critical Raw Materials are crucial to achieve the European Union’s (EU) goals of a climate-neutral economy by 2050. The high supply risk led the EU to prioritise domestic mineral exploration. This study, part of the S34I – SECURE AND SUSTAINABLE SUPPLY OF RAW MATERIALS project, utilised remote-sensing-based methods to identify and map heavy-mineral (HM) placer deposits in the Ria de Vigo, located in Galicia, Spain. Documented since the 70s, the sands of the Vigo beaches contain placers rich in Ti, Sn, Li, Rare Earth Elements (REE), Au, Fe and Cu. Mineral mapping was performed using hyperspectral EnMAP data. Band ratios were applied to identify possible mineralisation areas. Additionally, spectral unmixing was performed through the Mixture Tuned Matched Filtering (MTMF) workflow, included in ENVI 6.0 software, and two classification maps were obtained: one utilising the USGS spectral library and the other employing an HM concentrate spectral library. Band ratios were able to distinguish possible areas of hydrothermal alteration. MTMF classifications mapped most HM known to occur in the Ria, namely sillimanite, garnet, tourmaline, ilmenite, rutile, and monazite, were identified. This first approach will allow the selection of areas of interest for field validation and verification. The results will also be confronted with existing geological data.
Download
Paper Nr: 10
Title:

AMD Mapping in the Lusatian Region: From Medium to Very High-Resolution R/S Data
Authors:

Delira Hanelli, Enis Sterjo, Roberto De La Rosa and Andreas Knobloch
Abstract: The Lusatian region is undergoing an extensive landscape rehabilitation program following the closure of lignite open-pit mines. Under this programme, former open-cast lignite mines are being converted into artificial water bodies. However, the region faces significant challenges related to the acidification of surface and groundwater primarily driven by the oxidation of pyrite. Recent geochemical analyses show that, surface waters exhibit a strong variation of pH and iron concentration. This study aims to elaborate the potential of free and commercial space- and airborne- multispectral Remote Sensing (R/S) datasets (Sentinel-2, Worldview-3 and Unmanned Aerial Vehicle (UAV)) for large-scale acid mine drainage (AMD) mapping and identify the most suitable data sources and approaches for practical case studies. Additionally, cross-sensor comparisons are performed to gain more insights into the agreement between the spectra from Sentinel-2 images with those from the Worldview-3 and UAV images over surface water. The cross-sensor agreement of the images is quantified by performing regression analyses between R/S data at different wavelengths. Finally, dependencies and relationships between AMD constituents and the spectral data are investigated using artificial neural networks (ANN) of type Multi-Layer Perceptron (MLP).
Download
Paper Nr: 11
Title:

Innovative Hyperspectral Data Fusion for Enhanced Mineral Prospectivity Mapping
Authors:

Roberto De La Rosa, Michael Steffen, Ina Storch, Andreas Knobloch, Joana Cardoso-Fernandes, Morgana Carvalho, Mercedes Suárez Barrios, Juan Morales Sánchez-Migallón, Petri Nygren, Vaughan Williams and Ana Cláudia Teodoro
Abstract: To meet the European Union’s growing demand for critical raw materials in the transition to green energy, this study presents a novel, cost-effective, and non-invasive methodology for mineral prospectivity mapping. By integrating hyperspectral data from satellite, airborne, and ground-based sources with deep learning techniques, we enhance mineral exploration efficiency. We employ Bayesian Neural Networks (BNNs) to predict mineral prospective areas while providing uncertainty estimates, improving decision-making. To address the challenge of obtaining reliable negative labels for supervised learning, Self-Organizing Maps (SOMs) are used for unsupervised clustering, identifying barren areas through co-registration with known mineral occurrences. We illustrate this approach in the Aramo Unit in Spain, a geologically complex region with Cu-Co-Ni mineralized veins. Our workflow integrates local geology, mineralogy, geochemistry, and structural data with hyperspectral data from PRISMA, airborne Specim AisaFenix, LiDAR and ground-based spectroradiometry. By leveraging learning techniques and high-resolution remote sensing, we accelerate exploration, reduce costs, and minimize environmental impact. This methodology supports the EU’s S34I project by delivering high-value, unbiased datasets and promoting sustainable, cutting-edge mineral exploration technologies.
Download
Short Papers
Paper Nr: 6
Title:

Application of UAV, GNSS and InSAR Techniques in the Raw Material Supply Chain
Authors:

Tanja Grabrijan, Krištof Oštir, Klemen Kozmus Trajkovski, Dejan Grigillo, Veronika Grabrovec Horvat, Polona Pavlovčič Prešeren, Veton Hamza, Antonio Pepe, Fabiana Calò, Francesco Falabella, Enoc Sanz-Ablanedo, Mihaela Gheorghe, Teodora Selea and Ana Cláudia Teodoro
Abstract: The marble quarry, located in southern Austria produces high-quality marble, both in open-pit and underground extraction sites. Extraction, transportation and accumulation of material require close monitoring to maintain the stability of the whole area and to observe changes in waste dumps. In this study, we have shown how different methodologies can be used to support the monitoring of the entire raw material supply chain. Several unmanned aerial vehicle (UAV) surveys were performed to compute high-resolution digital elevation models (DEM) to serve as a reference for comparing stereo and tri-stereo DEMs calculated from satellite imagery. A low-cost global navigation satellite system (GNSS)-based monitoring system was set up to estimate horizontal and vertical displacements. In addition, the state-of-the-art technique of Interferometric synthetic aperture radar (InSAR) provided displacement time series for a broader area.
Download
Paper Nr: 9
Title:

Exploring and Mapping Marine Placers in Vigo Estuary Shoreline Using GIS Cartographic Tools
Authors:

Wai L. Ng-Cutipa, Ana Lobato, Francisco J. González, Georgios P. Georgalas, Irene Zananiri, Joana Cardoso-Fernandes and Ana C. Teodoro
Abstract: Marine placer deposits are accumulations of heavy minerals in coastal areas, both on beaches and in shallow water, usually consisting of ilmenite, rutile and zircon, and less commonly rare earth minerals (REEs) such as monazite and xenotime. This study investigates marine placer deposits in the Vigo Estuary (NW Spain), focusing on integrating diverse on and offshore cartographic data (geology, mineral resources, drainage, bathymetry, tides, Earth observation and others) for exploration. Six hundred two information points of marine placers have been analysed, 379 of them from shallow water, where Thiessen polygons have been spatially calculated. Our results, integrating regional cartographies in a Geographic Information System (GIS), shown great potential of placer minerals on the Santa Marta and Vao beaches (with presence of garnet, ilmenite, zircon, monazite and, locally, xenotime). This work 1) highlights the importance of collecting and analysing different previous information for marine placer exploration in integrated digital cartographies, 2) allows to program new activities to investigate local areas, 3) remark the remote sensing applications (cheap, easy and non-invasive tool), better applied to inaccessible areas, and 4) contribute to allow a sustainable resource exploration and coastal management.
Download