Use of artificial intelligence to assess mineral substance criticality in the French market: the example of cobalt

  • Fenintsoa AndriamasinoroEmail author
  • Raphael Danino-Perraud
Original Paper


The French public and commercial stakeholders need prospective tools to follow how mineral substances criticality change in the French market. After arguing that such tools should necessarily tackle criticality at a complex level, in particular on multiple scales (e.g., France and the EU), we present the first thematic and methodological discussions of our results from the ongoing design of a methodologically based simulation model on two subfields of artificial intelligence: agent-based computational economics (ACE) and machine learning (ML). In applying this to cobalt, our model aims to assess a supply shortage in France for prospective purposes. More precisely, we model a first individual agent (which is already complex by itself) acting at a country level: France. This model is not yet an ACE model per se since only one agent is designed. Nonetheless, we include ACE in the discussions since the work is a premise of such an end. The discussions also include how well the field accepts the methodology. At a thematic level, our preliminary prospective conclusion is a French cobalt supply shortage, should the case arise, would not be due to the variation of price from the UK, the transit leader of cobalt export to France. At a methodological level, we think the idea of methodologically coupling ML and ACE is necessary. ML is well-known in this field, but mainly for the study of mineral prospectivity in mining. Conversely, ACE covers the value chain but is not yet well known in the field and as such is still not trusted.


Mineral raw material criticality Cobalt Machine learning Agent-based computational economics 


C63 C82 E17 F10 


Authors’ contributions

R. Danino-Perraud is a PhD student in economics. His research interest is the analysis of mineral raw materials criticality and in particular cobalt criticality at European and France scales, by using Material Flow Analysis approach (MFA). This work was however not a part of his thesis work. It was a parallel work in which his contribution and expertise were requested.

F. Andriamasinoro is a research scientist in mineral commodities market modeling and simulation by using AI approach (agent-based computational Economics, Machine learning).

All authors contributed to the description of the section “Introduction and background” of the paper (context and current state) based on their respective competences. Model description, implementation and analysis were carried out by F. Andriamasinoro under a control of R. Danino-Perraud regarding the thematic consistency of the model. All discussions related to the AI methodology in the paper were written by F. Andriamasinoro. The MFA sub-section of the discussion section was written by R. Danino-Perraud. R. Danino-Perraud also critically revised the whole work according to his knowledge of mineral raw material criticality issues. All authors read and approved the final manuscript.

Compliance with ethical standards

Competing interests

The authors declare that they have no competing interests.


  1. Andriamasinoro F, Ahne H (2013) Prospective analysis of the world lithium market: contribution to the evaluation of supply shortage periods. Int Bus Econ Res J 12(3):359–372. ISSN: 2157-9393. CrossRefGoogle Scholar
  2. Andriamasinoro F, Angel J-M (2012) Artisanal and small-scale gold mining in Burkina Faso: suggestion of multi-agent methodology as a complementary support in elaborating a policy. Resour Policy 37(3):385–396. ISSN: 0301-4207. CrossRefGoogle Scholar
  3. Andriamasinoro F, Cassard D, Martel-Jantin B (2010) ISATEM: An Integration of Socioeconomic and Spatial Models for Mineral Resources Exploitation. In D Taniar et al., eds. Computational Science and Its Applications - ICCSA 2010. Fukuoka, Japan: ICCSA 2010, part I, LNCS 6016, Springer, Heidelberg. pp.476-90. March 23-26. ISBN: 9783642121555. CrossRefGoogle Scholar
  4. Audion A, Hocquard C, Labbé J (2014) Panorama 2013 du marché du cobalt. BRGM/RP-63626-FR, 155 p., 45 fig., 33 tabl. Accessed Mar 2019
  5. Ayres RU, Kneese AV (1969) Production, Consumption & Externalities. Am Econ Rev 59(3):282–297Google Scholar
  6. Beylot A, Villeneuve J (2015) Assessing the national economic importance of metals: An Input–Output approach to the case of copper in France. Resour Policy 44(C):161–165CrossRefGoogle Scholar
  7. BIO by Deloitte (2015) Study on Data for a Raw Material System Analysis: Roadmap and Test of the Fully Operational MSA for Raw Materials. Report prepared for the European Commission, DG GROW, 179 pGoogle Scholar
  8. Biolab (n.d.) Orange Visual Programming. Accessed Mar 2019
  9. Boehm B (1988) A Spiral Model of Software Development and Enhancement. IEEE Computer 21(5):61–72 INSPEC Accession Number: 3200192CrossRefGoogle Scholar
  10. Bonnet C, Carcanague S, Hache E, Seck GS, Simoën M (2019) Critical raw materials and transportation sector electrification : A detailed bottom-up analysis in world transport. Working Paper 2019-3. IFPEN (Institut Français du pétrole et des énergies nouvelles) and IRIS (Institut de relations internationales et stratégiques). 53 p. Accessed Sept 2019
  11. Bradley R (2018) 16 Examples of Artificial Intelligence (AI) in Your Everyday Life. Accessed Mar 2019
  12. Breiman L (2001) Random forests. Machine Learning 45 (1), October, pp.5-32 ISSN: 0885-6125. Springer. Accessed Mar 2019CrossRefGoogle Scholar
  13. Brownlee J (2013) A Gentle Introduction to k-fold Cross-Validation. [Accessed 2019].
  14. Brunner PH, Rechberger H (2004) Practical Handbook of Material Flow Analysis. Londres: Lewis Publisher. 318 p. Accessed Sept 2019
  15. Buijs B, Sievers H, Tercero Espinoza L (2012) Limits to the critical raw material approach. Waste and Resource Management 165:201–208Google Scholar
  16. Caté A, Perozzi L, Gloaguen E, Blouin M (2017) Machine learning as a tool for geologists. The Leading Edge 36(3):215–219CrossRefGoogle Scholar
  17. Chamaret A, Reichel V, O'Connor M (2010) Les avenirs de la Boucle de Moisson. Un projet de réflexion participative pour un développement territorial soutenable. Rapport de Recherche REEDS - Université de Versailles Saint-Quentin-en-Yvelines, RRR n° 2010-06. Rambouillet. 119 p.Google Scholar
  18. Chen W-Q, Graedel TE (2012) Anthropogenic Cycles of the Elements: A Critical Review. Environmental Science & Technology 46(16):8574–8586CrossRefGoogle Scholar
  19. Chen Z, Zhang L, Xu Z (2019) Tracking and quantifying the cobalt flows in mainland China during 1994–2016: Insights into use, trade and prospective demand. Sci Total Environ:752–762 Accessed Sept 2019CrossRefGoogle Scholar
  20. Crit_BRGM (2015) Fiches de criticité. [Accessed 2019].
  21. Critic_FR (2018) Point de vue français sur la criticité des métaux. Accessed Sept 2019
  22. Daw G, Labbé J-F (2012) Panorama 2011 du marché du lithium. BRGM/RP-60460-FR. 157p., 51 fig., 30 tab. 157 p.Google Scholar
  23. DGCIS (2012) Outil d'analyse de la vulnérabilité des entreprises aux approvisionnements de matières critiques non énergétiques. Accessed Mar 2019
  24. Douguet JM, O’Connor M, Van Der Sluijs JP (2009) Tools to assess uncertainty in a deliberative perspective. A Catalogue. Science for Policy: Opportunities and Challenges Oxford University Press, India.Google Scholar
  25. Douguet JM, Morlat C, Lanceleur P, Andriamasinoro F (2019) Subjective evaluation of aggregate supply scenarios in the Ile-de-France region with a view to a circular economy: the ANR AGREGA research project. Int J Sustain Dev (in press)Google Scholar
  26. EcCRM (2017) Study on the review of the list of Critical Raw Materials in EU. Final Report. Luxembourg: Publications Office of the European Union. 92 p., ISBN: 978-92-79-47937-3. Accessed Mar 2019
  27. Epstein JM (2008) Why Model? J Artif Soc Soc Simul 11(412)
  28. Erdman L, Graedel TE (2011) Criticality of non-fuel minerals: a review of major approaches and analyses. Environ Sci Technol 45(18):7620–7630CrossRefGoogle Scholar
  29. Farmer JD, Foley D (2009) The economy needs agent-based modelling. Nature 460(7256):685–686 Accessed Mar 2019CrossRefGoogle Scholar
  30. Feitosa FF, Bao Le Q, Vlek P (2011) Multi-agent simulator for urban segregation (MASUS): A tool to explore alternatives for promoting inclusive cities Computers. Environ Urban Syst 35(2):104–115. CrossRefGoogle Scholar
  31. Freyssenet M (2018) La production automobile mondiale, des quatre continents et des principaux pays constructeurs, 1898-2017. automobile mondiale par continent et pour les principaux pays constructeurs,1898 2017.xlsx.
  32. Fromm J (2004) The Emergence of Complexity. Kassel university press, p 200 978-3-89958-069-3Google Scholar
  33. Gomez J (2019) Stochastic global optimization algorithms: A systematic formal approach. Inf Sci 472:53–76 Accessed Sept 2019CrossRefGoogle Scholar
  34. Gourcerol B, Gloaguen E, Melleton J, Tuduri J, Galiegue X (2019) Re-assessing the European lithium resource potential – A review of hard-rock resources and metallogeny. Ore Geo Rev 109:494–519 Accessed Sept 2019CrossRefGoogle Scholar
  35. Graedel TE, Chandler C, Barr R, Chase T, Choi J, Christoffersen L, Friedlander E, Henly C et al (2012) Methodology of Metal Criticality Determination. Environ Sci Technol 46(2):1063–1070CrossRefGoogle Scholar
  36. Grimm V, Berger U, DeAngelis DL, Polhill JG, Giske J, Railsback SF (2010) The ODD protocol: A review and first update. Ecol Model 221:2760–2768CrossRefGoogle Scholar
  37. Gruber PW, Medina PA, Keoleian GA, Kesler SE, Everson MP, Wallington TJ (2011) Global Lithium Availability: A Constraint for Electric Vehicles? Ind Ecol 15(5):760–775. CrossRefGoogle Scholar
  38. Guyonnet D, Planchon M, Rollat A, Escalon V, Tuduri J, Charles N, Vaxelaire S, Dubois D et al (2015) Material flow analysis applied to rare earth elements in Europe. J Clean Prod 107:215–228. CrossRefGoogle Scholar
  39. Harper EM, Graedel TE (2008) Illuminating Tungsten’s Life Cycle in the United States: 1975−2000. Environ Sci Technol 42(10):3835–3842. CrossRefGoogle Scholar
  40. Harper EM, Kavlak G, Graedel TE (2012) Tracking the Metal of the Goblins: Cobalt’s Cycle of Use. Environ Sci Technol 46(2):1079–1086CrossRefGoogle Scholar
  41. Helbig C, Bradshaw AM, Wietschel L, Thorenz A, Tuma A (2018) Supply risks associated with lithium-ion battery materials. J Clean Prod 172:274–286 Accessed Sept 2019CrossRefGoogle Scholar
  42. INN (2018) Cobalt Market Forecast and Cobalt Stocks to Buy. 25 p. Accessed Mar 2019
  43. INSEEPIB (2018) Évolution du produit intérieur brut et de ses composantes jusqu’au quatrième trimestre 2018. Accessed Mar 2019
  44. INSEEPopu (2018) Bilan démographique 2018.
  45. Kirman AP, Vriend NJ (2001) Evolving market structure: An ACE model of price dispersion and loyalty. J Econ Dyn Control 25(3-4):459–502 [Accessed 2019CrossRefGoogle Scholar
  46. Knoeri C, Wäger PA, Stamp A, Althaus WM (2013) Towards a dynamic assessment of raw materials criticality: Linking agent-based demand with material flow supply modelling approaches. Sci Total Environ 461:808–812CrossRefGoogle Scholar
  47. Korinek J, Kim J (2013) Export restrictions on strategic raw Materials and their impact on trade and global supply. Working Papers, n° 95. OECD Publishing (Paris, France)Google Scholar
  48. Kushnir D, Sandén BA (2012) The time dimension and lithium resource constraints for electric vehicles. Res Policy 37(1):93–103. CrossRefGoogle Scholar
  49. Lefebvre G, Andriamasinoro F (2016) Mining economist opinions on using multi-agent methodology to simulate metal markets. Int J Trade Glob Markets 9(1):83–102. CrossRefGoogle Scholar
  50. Lengnick M (2013) Agent-based macroeconomics: A baseline model. J Econ Behav Organ 86:102–120. CrossRefGoogle Scholar
  51. LesEchos (2015) Emmanuel Macron : « Il y a une richesse sous le territoire français, notamment de l'or ». [Accessed 9 septembre 2015].
  52. Moyaux T, Chaib-Draa B, D’Amours S (2006) Supply Chain Management and Multiagent Systems: An Overview. In: Chaib-draa B, Müller JP (eds) Supply Chain Management and Multiagent Systems, SCI edn. Springer-Verlag, pp 1–27 10: 3-540-33875-6. Accessed Mar 2019
  53. Müller B, Bohn F, Dreßler G, Groeneveld J, Klassert C, Martin R, Schlüter M, Schulze J et al (2013) Describing human decisions in agent-based models – ODD + D, an extension of the ODD protocol. Environ Model Softw 48:37–48 Accessed Mar 2019CrossRefGoogle Scholar
  54. Nakajima K, Daigo I, Nansai K, Matsubae K, Takayanagi W, Tomita M, Matsuno Y (2018) Global distribution of material consumption: Nickel, copper, and iron. Resour, Conserv Recycl 133:369–374 Accessed Sept 2019CrossRefGoogle Scholar
  55. Nansai K, Nakajima K, Kagawa S, Kondo Y, Suh S, Shigetomi Y, Oshita Y (2014) Global Flows of Critical Metals Necessary for Low-Carbon Technologies: The Case of Neodymium, Cobalt, and Platinum. Environ Sci Technol 48(3):1391–1400CrossRefGoogle Scholar
  56. Nuss P, Blengini GA (2018) Towards better monitoring of technology critical elements in Europe: Coupling of natural and anthropogenic cycles. Sci Total Environ 613:569–578 Accessed Sept 2019CrossRefGoogle Scholar
  57. Panousi S, Harper EM, Nuss P, Eckelman MJ, Hakimian A, Graedel TE (2015) Criticality of Seven Specialty Metals. J Ind Ecol. CrossRefGoogle Scholar
  58. Ponte S, Sturgeon T (2014) Explaining governance in global value chains: A modular theory-building effort. Rev Int Polit Econ 21(1):195–223. CrossRefGoogle Scholar
  59. Railsback SF, Grimm V (2019) Agent-based and Individual-based Modeling: A Practical Introduction, 2nd edn, p 360 9780691190822Google Scholar
  60. Riddle M, Macal CM, Conzelmann G, Combs TE, Bauer D, Fields F (2015) Global critical materials markets: An agent-based modeling approach. Res Policy 45:307–321. CrossRefGoogle Scholar
  61. Robnik-Šikonja M, Kononenko I (1997) An adaptation of Relief for attribute estimation in regression. In: Machine Learning: Proceedings of the Fourteenth International Conference (ICML’97)., pp.296-304.Google Scholar
  62. Rodriguez-Galiano V, Sanchez-Castillo M, Chica-Olmo M, Chica-Rivas M (2015) Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geol Rev 71:804–818 Accessed Sept 2019CrossRefGoogle Scholar
  63. Roskill (2009) The Economics of Lithium, 11th edn. Roskill Information Services Ltd., London, p 324Google Scholar
  64. Roskill (2017) Cobalt: Global Industry, Markets and Outlook to 2026. Roskill Information Services Ltd., p 328 978 1 910922 26 2Google Scholar
  65. Rossignol J-Y (2018) Complexité: Fondamentaux à l'usage des étudiants et des professionnels. 1st ed. EDP Sciences - Collection : PROfil. 262 p. EAN13: 9782759821945.Google Scholar
  66. SharpLearning (n.d.) SharpLearning: Machine learning for C#.Net. [Accessed 2019].
  67. Sherwood J, Ditta A, Haney B, Haarsma L, Carbajales-Dale M (2017) Resource Criticality in Modern Economies: Agent-Based Model Demonstrates Vulnerabilities from Technological Interdependence. Biophys Econ Resour Qual 2(9):1–22. Accessed Mar 2019
  68. Speirs J, Houari Y, Gross R (2013) Materials Availability: Comparison of material criticality studies - methodologies and results. UKERC Report, Working paper III. UKERC/WP/TPA/2013/002. 30 p.Google Scholar
  69. Tesfatsion L (2006) Agent-based computational economics: A constructive approach to economic theory. In: Tesfatsion L, Judd K (eds) Handbook of Computational Economics, vol 16. Elsevier. Ch., pp 831–880 978-0-444-51253-6Google Scholar
  70. The Economist (2010) Agents of change: Conventional economic models failed to foresee the financial crisis. Could agent-based modelling do better? Accessed Mar 2019
  71. TradeMap (2018) Trade statistics for international business development. Accessed Mar 2019
  72. USGSCo (2019) Cobalt Statistics and Information. Accessed Mar 2019
  73. Wooldridge M (2009) An Introduction To Multiagent Systems. 2nd ed. John Wiley & Sons. 499 p. ISBN-10: 0470519460. ISBN-13: 978-0470519462.Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.BRGMOrléans Cedex 2France
  2. 2.University of Orléans/Laboratoire Économique d’Orléans (LEO)Orléans Cedex 2France

Personalised recommendations