Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Spain

Research and Innovation Action · Running

GAIA-TSF Geospatial Artificial Intelligence Analysis for Tailings Storage Facilities

Coordinator
Cluster Para La Mineria Sostenible Y Servicios Asociados De La Peninsula Iberica - Iberian Sustainable Mining Cluster, Spain
Runs
1 November 2024 to 28 February 2027
Status
Running
EU funding
€998k
Total cost
—
Partners
7 organisations in 6 countries
Type
Research and Innovation Action
Grant agreement
101180263

What the project is doing

In the project's own words, from its summary on CORDIS.

The Geospatial Artificial Intelligence Analysis for Tailings Storage Facilities (GAIA-TSF) aims to design and develop the prototype of a system based on satellite earth observation and machine learning algorithms to achieve continuous multi-level/multi-scale characterisation and monitoring of Tailings Storage Facilities (TSFs). To achieve this goal, GAIA-TSF consortium will engage in interdisciplinary and international collaborative research and development, integrating the fields of geoscience, Earth Observation (EO), and Machine Learning (ML) Science as well as five countries (Spain, Portugal, Netherlands, Czech Republic, Zambia and South Africa).

The project will focus on establishing strong interactions with user communities (mining authorities and mining industry) involved in TSF operational activities with the aim of defining clear customer-specific functional and technical requirements. These requirements will lay down Key Variables (KV) that could be used as parameters to monitor TSF as well as precise performance objectives for the GAIA-TSF prototype. On this foundation, the cooperative work between scientists and the mining operational communities will lead to explore how three technical disciplines, namely satellite earth observation, geo-engineering and machine learning, can be integrated into the design of a prototype supporting the automatic detection of anomalies and risks in TSFs.

Based on the designed variables and structured training datasets, different machine and deep learning algorithms will be tested and evaluated to design and develop a prototype supporting the automatic detection and prediction of anomalies and risks in TSFs.

Topics

Who is involved

OrganisationCityCountryRole
Cluster Para La Mineria Sostenible Y Servicios Asociados De La Peninsula Iberica - Iberian Sustainable Mining ClusterLeonSpainCoordinator
Ceske Vysoke Uceni Technicke V PrazePrahaCzechiaParticipant
Univerzita KarlovaPraha 1CzechiaParticipant
Technische Universiteit DelftDelftNetherlandsParticipant
Cybele Lawgical LtdLisboaPortugalParticipant
University of the Witwatersrand JohannesburgJohannesburgSouth AfricaParticipant
Copperbelt UniversityKitweZMParticipant

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI