Predictive analysis of total organic carbon (TOC) in shale targets: example from the Lower Cretaceous of the Austral Basin (Patagonia, Argentina) using machine learning on outcrop data
Keywords:
Austral Basin, dimensional reduction, machine learning, TOC prediction, unconventional reservoirsAbstract
The Río Mayer Formation (Lower Cretaceous) of the Austral Basin, Patagonia, is a key source rock for unconventional reservoirs. This study explores the potential of machine learning (ML) for predicting Total Organic Carbon (TOC) content using outcrop data, a novel approach compared to traditional subsurface data applications. Employing dimensional reduction techniques (PCA, T-SNE, UMAP), the analysis revealed clear clustering of high TOC values in feature space, supporting the feasibility of predictive modeling. Three ML models —Logistic Regression, Support Vector Classifier (SVC), and KNearest Neighbors (KNN)— were tested using a feature set derived from ANOVA F-Score rankings. Dimensionality reduction improved model performance, with SVC achieving the most robust results. Despite limited labeled samples, predictions across models were consistent, identifying a promising region for high TOC. The study highlights the importance of integrating geological variables and XRD data in TOC modeling and emphasizes the need for expanded datasets and additional sedimentary sections to enhance regional interpretations.
References
Aguirre Urreta, M.B. (2002). Invertebrados del cretácico inferior. In: Haller, M.J. (Ed.), Geología y Recursos Naturales de Santa Cruz. Relatorio del XV Congreso Geológico Argentino, 925 pp.
Arbe, H.A. (2002). Análisis estratigráfico del Cretácico de la Cuenca Austral. In: Haller, M.J. (Ed.), Geología y Recursos Naturales de Santa Cruz. Relatorio del XV Congreso Geológico Argentino, pp. 103–128.
Arbe, H.A. and Hechem, J. (1984). Estratigrafía y facies de depósitos continentales, litorales y marinos del Cretácico superior, lago Argentino. IX Congreso Geológico Argentino Actas 7:124-158.
Belotti, H., Pagan, F., Perez Mazas, A., Agüera, M., Rodriguez, J., Porras, J., Köhler, G., Weiner, G., Conforto, G., and Cagnolatti, M. (2013). Geologic Interpretation and Assessment of Early Cretaceous Shale Oil and Gas Potential in Austral Basin, Santa Cruz, Argentina, In: Unconventional Resources Technology Conference, Denver, Colorado, USA, August 2013.
Belotti, H., Rodriguez, J., Conforto, G., Pagan, F., Pérez Mazas, A., Agüera, M., Porras, J., Köhler, G., Cagnolatti, M., Weiner, G., Nigro, E., and Cangini, A. (2014). La Formación Palermo Aike como Reservorio No Convencional en la Cuenca Austral, Provincia de Santa Cruz, Argentina. IX Congreso de Exploración y Desarrollo, 1–17.
Brown, G., and Brindley, G.W. (1980). X-ray diffraction procedures for clay mineral identification. In: Brindley, G.W., Brown, G. (Eds.), Crystal structures of Clay Minerals and Their X-ray Identification. Mineralogical Society, London, pp. 305–359.
Busch, B., Spitzner, A., Adelmann, D., and Hilgers, C. (2022). The significance of outcrop analog data for reservoir quality assessment: A comparative case study of Lower Triassic Buntsandstein sandstones in the Upper Rhine Graben. Marine and Petroleum Geology 141, 105701. https://doi.org/10.1016/j.marpetgeo.2022.105701
Cuitiño, J., Varela, A., Ghiglione M., Richiano, S., and Poire, D.G. (2019). The Austral-Magallanes Basin (Southern Patagonia): A synthesis of its stratigraphy and evolution. Latin American Journal of Sedimentology and Basin Analysis 26, 155–166.
Féraud, G., Alric, V., Fornari, M., Bertrand, H., and Haller, M. (1999). 40Ar/39Ar dating of the Jurassic volcanic province of Patagonia: migrating magmatism related to Gondwana break-up and subduction. Earth and Planetary Science Letter 172, 83–98. https://doi.org/10.1016/S0012-821X(99)00190-9
Guo, J., Wang, S., Chang, L., Li, Y., Lyu, Q., and Fan, J. (2022). A Novel Method for Conventional Logging Prediction of Brittleness Index: A Case of Tight Sandstone in Western Ordos Basin. Frontiers in Energy Research 10.3389/fenrg.2022.819078.
Handhal, A., Al-Abadi, A., Chafeet, H., and Ismail, M. (2020). Prediction of total organic carbon at Rumaila oil field, Southern Iraq using conventional well logs and machine learning algorithms. Marine and Petroleum Geology 116, 104347. https://doi.org/10.1016/j.marpetgeo.2020.104347
Kraemer, P.E., and Riccardi, A.C. (1997). Estratigrafía de la región comprendida entre los lagos Argentino y Viedma (49º40’ - 50º10’ LS), Provincia de Santa Cruz. Revista de la Asociación Geológica Argentina 52, 333–360.
Melendo, F., Gargiulo, C., Garcia, N., and Jait, N. (2023). Description and Analysis of the First Two Vertical Pilot Wells Completions to the Palermo Aike Shale: A Highly Promising Unconventional Reservoir in Austral Basin, Argentina. Latin America Unconventional Resources Technology Conference (LA URTeC) https://doi.org/10.15530/urtec-2023-3969079
Milad, B., Slatt, R., and Fuge, Z. (2020). Lithology, stratigraphy, chemostratigraphy, and depositional environment of the Mississippian Sycamore rock in the SCOOP and STACK area, Oklahoma, USA: Field, lab, and machine learning studies on outcrops and subsurface wells. Marine and Petroleum Geology 115, 104278. https://doi.org/10.1016/j.marpetgeo.2020.104278
Moore, D.M., and Reynolds Jr., R.C. (1997). X-ray Diffraction and the Identification and Analysis of Clay Minerals. Oxford University Press, Oxford.
Mustafa, A., Tariq, Z., Abdulraheem, A., Mahmoud, M., Kalam, S., and Khan, R. (2022). Shale brittleness prediction using machine learning—A Middle East basin case study. AAPG Bulletin, 106 (11), 2275–2296. https://doi.org/10.1306/12162120181
Niu, D., Li, Y., Zhang, Y., Sun, P., Wu, H., Fu, H., and Wang, Z. (2022). Multi-scale classification and evaluation of shale reservoirs and ‘sweet spot’ prediction of the second and third members of the Qingshankou Formation in the Songliao Basin based on machine learning. Journal of Petroleum Science and Engineering 216, 110678. https://doi.org/10.1016/j.petrol.2022.110678
Ore, T. and Gao, D. (2023). Prediction of reservoir brittleness from geophysical logs using machine learning algorithms. Computers & Geosciences 171, 105266. https://doi.org/10.1016/j.cageo.2022.105266
Pankhurst, R.J., Riley, T.R., Fanning, C.M., and Kelley, S.P. (2000). Episodic silicic volcanism in Patagonia and Antarctic Peninsula: chronology of magmatism associated with the break-up of Gondwana. Journal of Petrology 41, 605–625.
Passey, Q., Creaney, S., Kulla, J., Moretti, F., and Stroud, J. (1990). A practical model for organic richness from porosity and resistivity logs. AAPG Bulletin 74, 1777–1794. https://doi.org/10.1306/0C9B25C9-1710-11D7-8645000102C1865D
Poiré, D., Richiano, S., Varela, A., and Sandoval, P.N. (2007). Descripción detallada de coronas, interpretación paleoambiental y logs numéricos de facies sedimentarias, Proyecto Lomitas. Informe confidencial preparado para Larriestra-Geotecnologías SA y Repsol-YPF SA. Parte I-II.
Prochnow, S., Raterman, N., Swenberg, M., Reddy, L., Smith, I., Romanyuk, M., and Fernadez, T. (2022). A subsurface machine learning approach at hydrocarbon production recovery & resource estimates for unconventional reservoir systems: Making subsurface predictions from multimensional data analysis. Journal of Petroleum Science and Engineering 215, 110598. https://doi.org/10.1016/j.petrol.2022.110598
Richiano, S. (2014). Lower cretaceous anoxic conditions in the Austral basin, south-western Gondwana, Patagonia Argentina. Journal of South American Earth Sciences 54, 37–46.
Richiano, S. (2015). Environmental factors affecting the development of the Zoophycos ichnofacies in the lower cretaceous Río Mayer Formation (Austral basin, Patagonia). Palaeogeography Palaeoclimatology, Palaeoecology https://doi.org/10.1016/j.palaeo.2015.03.029.
Richiano, S., Varela, A.N., Cereceda, A., and Poiré, D.G. (2012). Evolución paleoambiental de la Formación Río Mayer, cretácico inferior, cuenca austral, Patagonia Argentina. Latin American Journal of Sedimentology and Basin Analysis 19, 3–26.
Richiano, S., Poiré, D.G., and Varela, A.N. (2013). Icnología de la Formación Río Mayer, cretácico inferior, SO Gondwana, Patagonia, Argentina. Ameghiniana 50, 273–286.
Richiano, S., Varela, A.N., Gómez-Peral, L.E., Cereceda, A., and Poiré, D.G. (2015). Composition of the lower cretaceous black shales from the Austral basin (Patagonia, Argentina): implication for unconventional reservoirs in the southern Andes. Marine and Petroleum Geology 66, 764–790. http://dx.doi.org/10.1016/j.marpetgeo.2015.07.018
Richiano, S., Varela, A.N., and Poiré, D.G. (2016). Heterogeneous distribution of trace fossils across initial transgressive deposits in rift basins: an example from the Springhill Formation, Argentina. Lethaia 49, 524–539. https://doi.org/10.1111/let.12163
Richiano S., Gómez-Peral, L.E., Varela, A.N., Gómez Dacal, A., Cavarozzi, C., and Poiré, D.G. (2019). Geochemical characterization of black shales from the Río Mayer Formation (Early Cretaceous), Austral-Magallanes Basin, Argentina: Provenance response during Gondwana break-up. Journal of South American Earth Sciences 93, 67–83. https://doi.org/10.1016/j.jsames.2019.04.009
Rojas, C., Jait, D., Aimar, E., Rivero, M., Cevallos, M., Gargiulo, C., and Melendo, F. (2022). Formación Palermo Aike, Caracterización y potencial productivo como reservorio no convencional, Cuenca Austral, Provincia De Santa Cruz, Argentina. 11º Congreso de Exploración y Desarrollo de Hidrocarburos Exploración y Sistemas Petroleros, 73–96.
Rousseeuw, P.J. (1987). Silhouettes: a Graphical Aid to the Interpretation and Validation of Cluster Analysis”. Computational and Applied Mathematics 20, 53–65. https://doi.org/10.1016/0377-0427(87)90125-7
Saporetti, C.M., Fonseca, D.L., Olivera, L.C., Pereira, E., and Goliatt, L. (2022). Hybrid machine learning models for estimating total organic carbon from mineral constituents in core samples of shale gas fields. Marine and Petroleum Geology 143, 105783. https://doi.org/10.1016/j.marpetgeo.2022.105783
Schultz, L.G. (1964). Quantitative interpretation of mineralogical composition from X-ray and chemical data for Pierra Shale. In: U.S. Geological Survey Professional Paper, vol. 391, pp. 1–31.
Tognoli, F. M. W., Spaniol, A., de Mello, M., and de Souza, L. (2024). A machine-learning based approach to predict facies associations and improve local and regional stratigraphic correlations. Marine and Petroleum Geology 160, 106636. https://doi.org/10.1016/j.marpetgeo.2023.106636
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Sebastián M. Richiano, Federico Ares
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
