Państwowa służba geologiczna planuje wykorzystać sztuczną inteligencję i uczenie maszynowe do analizy danych i poszukiwania surowców krytycznych na Dolnym Śląsku

• Autorzy: Karcz Przemysław

Identyfikatory

DOI

10.7306/2025.80

Warianty tytułu

EN

The Polish Geological Service plans to use artificial intelligence and machine learning for data analysis and critical raw material exploration in Lower Silesia

• Języki publikacji: PL

Abstrakty

EN

Artificial intelligence (AI) and machine learning (ML) are becoming increasingly common tools in geological data analysis, offering new opportunities in data processing, prediction, and decision support. This article presents a proposal for implementing AI and ML solutions within the operations of the Polish Geological Sur-vey (PSG), which has collected vast geological data resources over more than 100 years. The project, initiated by the Lower Silesian Branch of PSG, aims to integrate dispersed data and use it for exArtificial intelligence (AI) and machine learning (ML) are becoming increasingly common tools in geological data analysis, offering new opportunities in data processing, prediction, and decision support. This article presents a proposal for implementing AI and ML solutions within the operations of the Polish Geological Sur-vey (PSG), which has collected vast geological data resources over more than 100 years. The project, initiated by the Lower Silesian Branch of PSG, aims to integrate dispersed data and use it for exploration purposes, including the identification of new prospective areas for resources such as critical raw materials. The article also discusses existing examples of AI applications in geology -particularly in the oil and gas sector - and highlights potential risks related to data quality, model interpretability, and acceptance within the expert community. It emphasizes that the success of AI implementation depends on close collaboration between specialists and technical teams, as well as on phased approach to deployment. The paper aligns with current trends in the digital transformation of geosciences and serves as a starting point for further research based on advanced technologies.ploration purposes, including the identification of new prospective areas for resources such as critical raw materials. The article also discusses existing examples of AI applications in geology -particularly in the oil and gas sector - and highlights potential risks related to data quality, model interpretability, and acceptance within the expert community. It emphasizes that the success of AI implementation depends on close collaboration between specialists and technical teams, as well as on phased approach to deployment. The paper aligns with current trends in the digital transformation of geosciences and serves as a starting point for further research based on advanced technologies.

Słowa kluczowe

PL

sztuczna inteligencja w geologii; zastosowania uczenia maszynowego; integracja danych geologicznych; poszukiwanie złóż mineralnych i węglowodorów; cyfrowe nauki o Ziemi

EN

artificial intelligence in geology; machine learning applications; geological data integration; mineral and hydrocarbon exploration; digital geosciences

• Wydawca: Państwowy Instytut Geologiczny - Państwowy Instytut Badawczy
• Czasopismo: Przegląd Geologiczny
• Rocznik: 2025
• Tom: Vol. 73, nr 8
• Strony: 744--745
• Opis fizyczny: Bibliogr. 6 poz., wykr.

Twórcy

autor

Karcz Przemysław

• Państwowy Instytut Geologiczny - Państwowy Instytut Badawczy, Oddział Dolnośląski, al. Jaworowa 19, 53-122 Wrocław

• https://orcid.org/0000-0002-2932-6851

Bibliografia

• 1. ALSHAMMASI L., MERIDJI J., BRADFORD CH. 2024 - Innovative Machine Learning based model to predict deep lateral log resistivity in high salinity muds. [W:] Mutti M., Al-Tawil A. (red.), Cross Regional Carbonates and Mixed Carbonate Systems Symposium. Guidebook of the Intern. Conf., 22-24 April 2024. AAPG Europe & Middle East Region, Palermo: 13.
• 2. CEDRIC M.J. 2024 - Enhancing Geological Interpretations: Leveraging Computer Vision and AI in Mixed Carbonate-Clastic Systems. [W:] Mutti M., Al-Tawil A. (red.), Cross Regional Carbonates and Mixed Carbonate Systems Symposium. Guidebook of the Intern. Conf., 22-24 April 2024. AAPG Europe & Middle East Region, Palermo: 49.
• 3. CHONGCHONG Q., KECHAO L., TAO H., QIUSONG C., ZHANG L., LIYUAN C. 2025 - Modeling spatiotemporal hotspots and impact of cobalt contamination in European soils. Environmental Technology & Innovation, 39, 104307.
• 4. FAJFER J., ROLKA M., KOSTRZ-SIKORA P. 2025 - Assessing the potential of secondary raw materials from hard coal and iron ore mining waste disposal sites using machine learning. Geological Quarterly 69,14.
• 5. MAAS M., MAAS RODRIGUES M.V., BEDLE H., CASTRO DE MATOS M. 2023 - Seismic identification of carbonate reservoir sweet spots using unsupervised machine learning: A case study from Brazil deep water Aptianpre-salt data. [W:] Ladner S., Turko M. (red.), Finding New Oil and Gas, the Old-Fashioned Way. Guidebook of the Intern. Conf., 7-10 October 2023. AAPG Midcontinent Sectional, Oklahoma City: 72.
• 6. SACREY D. 2023 - Paradise Machine Learning Technology - Understanding the Sub-surface in Detail. [W:] Ladner S., Turko M. (red.), Finding New Oil and Gas, the Old-Fashioned Way. Guidebook of the Intern. Conf., 7-10 October 2023. AAPG Midcontinent Sectional, Oklahoma City: 54.