Machine learning and tectonic setting determination: Bridging the gap between Earth scientists and data scientists

Abstract

Technological progress and the rapid increase in geochemical data often create bottlenecks in many studies, because current methods are designed using limited number of data and cannot handle large datasets. In geoscience, tectonic discrimination illustrates this issue, using geochemical analyses to define tectonic settings when most of the geological record is missing, which is the case for most of the older portion of the Earth’s crust. Basalts are the primary target for tectonic discrimination because they are volcanic rocks found within all tectonic settings, and their chemical compositions can be an effective way to understand tectonics-related mantle processes. However, the classical geochemical discriminant methods have limitations as they are based on a limited number of 2 or 3-dimensional diagrams and need successive and subjective steps that often offers non-unique solutions. Also, weathering, erosion, and orogenic processes can modify the chemical composition of basalts and eliminate or obscure other complementary geotectonic records. To address those limitations, supervised machine learning techniques (a part of artificial intelligence) are being utilized more often as a tool to analyze multidimensional datasets and statistically process data to tackle big data challenges. This contribution starts by reviewing the current state of tectonic discrimination methods using supervised machine learning. Deep learning, especially Convolutional Neural Network (CNN) is the most accurate approach. However, it requires a large dataset and considerable processing time, and the gain of accuracy can be at the expense of interpretability. Therefore, this study designed guidelines for data pre-processing, tectonic setting classification and objectively evaluating the model performance. We also identify research gaps and propose potential directions for the application of supervised machine learning to tectonic discrimination research, aimed at closing the divide between earth scientists and data scientists.

Keywords

Machine learning / Artificial intelligence / Geochemistry / Igneous petrology / Basalts / Tectonic settings

References

[1] Agrawal S., Guevara M., Verma S.P., 2008. Tectonic discrimination of basic and ultrabasic volcanic rocks through log-transformed ratios of immobile trace elements. International Geology Review 50, 1057-1079.

[2] Agterberg F.P., 1966. Markov schemes for multivariate well data. 2 2, 1-181966.

[3] Alzubaidi L., Zhang J., Humaidi A.J., Al-Dujaili A., Duan Y., Al-Shamma O., Santamaría J., Fadhel M.A., Al-Amidie M., Farhan L., 2021. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8, 53-53.

[4] Bach S., Binder A., Montavon G., Klauschen F., Müller K.-R., Samek W., 2015. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one 10, e0130140.

[5] Bishop C.M., Nasrabadi N.M., 2006. Pattern recognition and machine learning. Springer.

[6] Breiman L., 2001. Random forests. Machine learning 45, 5-32.

[7] Butler J.C., Woronow A., 1986. Discrimination among tectonic settings using trace element abundances of basalts. Journal of Geophysical Research: Solid Earth 91, 10289-10300.

[8] Buuren S.v., Groothuis-Oudshoorn K., 2010. mice: Multivariate imputation by chained equations in R. Journal of statistical software, 1-68.

[9] Cocks L., Torsvik T., 2002. Earth geography from 500 to 400 million years ago: a faunal and palaeomagnetic review. Journal of the Geological Society 159, 631-644.

[10] Cortes C., Vapnik V., Saitta L., 1995. Support-vector networks. Machine Learning 20, 273-297.

[11] Cover T., Hart P., 1967. Nearest neighbor pattern classification. IEEE transactions on information theory 13, 21-27.

[12] Deng J., Dong W., Socher R., Li L.-J., Kai L., Li F.-F., 2010. ImageNet: A large-scale hierarchical image database. In:2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, pp. 248-255, https://doi.org/10.1109/CVPR.2009.5206848.

[13] Doucet L.S., Li Z.-X., Ernst R.E., Kirscher U., Gamaleldien H., Mitchell R.N., 2020. Coupled supercontinent-mantle plume events evidenced by oceanic plume record. Geology 48.2, 159-163.

[14] Doucet L.S., Gamaleldien H., Li Z.-X., 2022a. Pitfalls in using the geochronological information from the EarthChem Portal for Precambrian time-series analysis. Precambrian Research 369, 106514.

[15] Doucet L.S., Tetley M.G., Li Z.-X., Liu Y., Gamaleldien H., 2022b. Geochemical fingerprinting of continental and oceanic basalts: A machine learning approach. Earth-Science Reviews 233, 104192-104192.

[16] Dowla F.U., Taylor S.R., Anderson R.W., 1990. Seismic discrimination with artificial neural networks: Preliminary results with regional spectral data. Bulletin of the Seismological Society of America 80, 1346-1373.

[17] Dramsch J.S., 2020. 70 years of machine learning in geoscience in review, Advances in Geophysics. Academic Press Inc., pp. 1-55.

[18] Evans D.A.D., 2009. The palaeomagnetically viable, long-lived and all-inclusive Rodinia supercontinent reconstruction. Geological Society Special Publication 327, 371-404.

[19] Freund Y., Schapire R.E., 1997. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences 55, 119-139.

[20] Frisch W., Meschede M., Blakey R., 2011. Plate Tectonics, 2011 ed. Springer, Heidelberg Dordrecht London New York.

[21] Frisch W., Meschede M., Blakey R., 2011. In: In: Plate Tectonics. 2011 ed. SpringerPlate Tectonics-Continental Drift and Mountain Building, Heidelberg Dordrecht London New YorkSpringer, 212 pp.

[22] Ge C., Fangyue W., Hai’ou G., Huaifeng G., Xiuyu L., Feng Y., 2019. Tectonic discrimination based on convolution neural network and big data of volcanic rocks. Earth Sci. Front. 26, 22 (in Chinese with English abstract).

[23] Ge C., Huo J., Gu H.O., Wang F., Sun H., Li X., Li W., Yuan F., 2021. Tectonic discrimination and application based on convolution neural network and incomplete big data. Journal of Geochemical Exploration 220.

[24] Guidotti R., Monreale A., Ruggieri S., Turini F., Giannotti F., Pedreschi D., 2018. A survey of methods for explaining black box models. ACM computing surveys (CSUR) 51, 1-42.

[25] Han S., Li M., Ren Q., 2019. Discriminating among tectonic settings of spinel based on multiple machine learning algorithms. Big Earth Data 3, 67-82.

[26] Hastie T., Tibshirani R., Friedman J.H., Friedman J.H., 2009. The elements of statistical learning: data mining, inference, and prediction (2nd Ed.). Springer.

[27] Healey J., 2020. Artificial intelligence.

[28] Ho T.K., 1995. Random decision forests. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR 1, 278-282.

[29] Hochreiter S., Schmidhuber J., 1997. Long Short-Term Memory. Neural Computation 9, 1735-1780.

[30] Hollocher K., Robinson P., Walsh E., Roberts D., 2012. Geochemistry of amphibolite-facies volcanics and gabbros of the Støren Nappe in extensions west and southwest of Trondheim, western gneiss region, Norway: A key to correlations and paleotectonic settings. American Journal of Science 312, 357-416.

[31] Hastie T., Tibshirani R., Friedman J.H., Friedman J.H., 2009. The elements of statistical learning: data mining, inference, and predictionThe Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd Ed.). Springer, New York. Springer.http://dx.doi.org/10.1007/978-0-387-84858-7.

[32] Jain A.K., Murty M.N., Flynn P.J., 1999. Data clustering: a review. ACM computing surveys (CSUR) 31, 264-323.

[33] Keller C.B., Schoene B., 2012. Statistical geochemistry reveals disruption in secular lithospheric evolution about 2.5 Gyr ago. Nature 485, 490.

[34] Krige D.G., 1951. A statistical approach to some basic mine valuation problems on the Witwatersrand. Journal of the Southern African Institute of Mining and Metallurgy 52, 119-139.

[35] LeCun Y., Bengio Y., Hinton G., 2015. Deep learning. nature 521, 436-444.

[36] Lehnert K., Su Y., Langmuir C.H., Sarbas B., Nohl U., 2000. A global geochemical database structure for rocks. Geochemistry, Geophysics, Geosystems 1, 1012. doi, https://doi.org/10.1029/1999GC000026.

[37] Li C., Arndt N.T., Tang Q., Ripley E.M., 2015. Trace element indiscrimination diagrams. Lithos 232, 76-83.

[38] Li Z.X., Bogdanova S.V., Collins A.S., Davidson A., De Waele B., Ernst R.E., Fitzsimons I.C.W., Fuck R.A., Gladkochub D.P., Jacobs J., Karlstrom K.E., Lu S., Natapov L.M., Pease V., Pisarevsky S.A., Thrane K., Vernikovsky V., 2008. Assembly, configuration, and break-up history of Rodinia: A synthesis. Precambrian Research 160, 179-210.

[39] Li Z.-X., Liu Y., Ernst R., 2023. A dynamic 2000-540 Ma Earth history: From cratonic amalgamation to the age of supercontinent cycle. Earth-Science Reviews, 104336.

[40] Little R.J., Rubin D.B., 2019. Statistical analysis with missing data. John Wiley & Sons.

[41] Liu K., Liu W., 2017. Machine Learning and Identification of the Tectonic Environment of Basalt in the Continental Plate. Engineering Technology & Management 1, 188-191.

[42] Lundberg S.M., Lee S.-I., 2017. A unified approach to interpreting model predictions. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.

[43] Matalas N.C., 1967. Mathematical assessment of synthetic hydrology. Water Resources Research 3, 937-945.

[44] McLachlan G.J., Lee S.X., Rathnayake S.I., 2019. Finite Mixture Models. Annual Review of Statistics and Its Application 6, 355-378.

[45] Merdith A.S., Collins A.S., Williams S.E., Pisarevsky S., Foden J.D., Archibald D.B., Blades M.L., Alessio B.L., Armistead S., Plavsa D., 2017. A full-plate global reconstruction of the Neoproterozoic. Gondwana Research 50, 84-134.

[46] Merdith A.S., Williams S.E., Collins A.S., Tetley M.G., Mulder J.A., Blades M.L., Young A., Armistead S.E., Cannon J., Zahirovic S., 2021. Extending full-plate tectonic models into deep time: Linking the Neoproterozoic and the Phanerozoic. Earth-Science Reviews 214, 103477.

[47] Nesvijevskaia A., Ouillade S., Guilmin P., Zucker J.-D., 2021. The accuracy versus interpretability trade-off in fraud detection model. Data & Policy 3, e12.

[48] Newendorp P.D., 1976. Decision analysis for petroleum exploration. Penn Well Books,Tulsa, OK.

[49] Pearce J.A., 2008. Geochemical fingerprinting of oceanic basalts with applications to ophiolite classification and the search for Archean oceanic crust. Lithos 100, 14-48.

[50] Pearce J.A., Cann J.R., 1971. Ophiolite origin investigated by discriminant analysis using Ti, Zr and Y. Earth and Planetary Science Letters 12, 339-349.

[51] Pearce J.A., Cann J.R., 1973. Tectonic setting of basic volcanic rocks determined using trace element analyses. Earth and planetary science letters 19, 290-300.

[52] Pearce J.A., Ernewein M., Bloomer S.H., Parson L.M., Murton B.J., Johnson L.E., 1994. Geochemistry of Lau Basin volcanic rocks: Influence of ridge segmentation and arc proximity. Geological Society Special Publication 81, 53-75.

[53] Pearce J.A., Ernst R.E., Peate D.W., Rogers C., 2021. LIP printing: Use of immobile element proxies to characterize Large Igneous Provinces in the geologic record. Lithos 392, 106068.

[54] Pearce J.A., Norry M.J., 1979. Petrogenetic implications of Ti, Zr, Y, and Nb variations in volcanic rocks. Contrib Mineral Petrol 69, 33-47.

[55] Petrelli M., Perugini D., 2016. Solving petrological problems through machine learning: the study case of tectonic discrimination using geochemical and isotopic data. Contrib Mineral Petrol 171.

[56] Preston F.W., Henderson J., 1964. Fourier series characterization of cyclic sediments for stratigraphic correlation.

[57] Quinlan J.R., 1986. Induction of decision trees. Machine learning 1, 81-106.

[58] Ren Z.-Y., Hanyu T., Miyazaki T., Chang Q., Kawabata H., Takahashi T., Hirahara Y., Nichols A.R.L., Tatsumi Y., 2009. Geochemical Differences of the Hawaiian Shield Lavas: Implications for Melting Process in the Heterogeneous Hawaiian Plume. J Petrol 50, 1553-1573.

[59] Ren Q., Li M., Han S., Zhang Y., Zhang Q., Shi J., 2019. Basalt tectonic discrimination using combined machine learning approach. Minerals 9.

[60] Ribeiro M.T., Singh S., Guestrin C., 2016. “ Why should i trust you?” Explaining the predictions of any classifier, Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1135-1144.

[61] Rollinson H., Pease V., 2021. Using Geochemical Data to Identify Tectonic Environments, in: Rollinson, H., Pease, V. (Eds.), Using Geochemical Data: To Understand Geological Processes, 2 ed. Cambridge University Press, Cambridge, pp. 157-177.

[62] Rosenblatt F., 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review 65, 386.

[63] Rumelhart D.E., Hinton G.E., Williams R.J., 1986. Learning representations by back-propagating errors. nature 323, 533-536.

[64] Saccani E., 2015. A new method of discriminating different types of post-Archean ophiolitic basalts and their tectonic significance using Th-Nb and Ce-Dy-Yb systematics. Geoscience Frontiers 6, 481-501.

[65] Samuel A.L., 1959. Some Studies in Machine Learning Using the Game of Checkers. IBM Journal of Research and Development 3, 210-229.

[66] Sarbas B., Nohl U., 2009. The GEOROC database - a decade of “online geochemistry”. Geochim. Cosmochim. Acta 73, A1158-A1158.

[67] Sarker I.H., 2021. Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. 2, 420-420.

[68] Tetley M.G., Li Z.-X., Matthews K.J., Williams S.E., Müller R.D., 2020. Decoding earth's plate tectonic history using sparse geochemical data. Geoscience Frontiers 11, 265-276.

[69] Torsvik T.H., Müller R.D., Van der Voo R., Steinberger B., Gaina C., 2008. Global plate motion frames: toward a unified model. Reviews of geophysics 46.

[70] Turing A.M., 1950. Mind. Mind 59, 433-460.

[71] Ueki K., Hino H., Kuwatani T., 2018. Geochemical discrimination and characteristics of magmatic tectonic settings: A machine‐learning‐based approach. Geochemistry, Geophysics, Geosystems 19, 1327-1347.

[72] Ueki K., Hino H., Kuwatani T., 2022. Extracting the geochemical characteristics of magmas in different global tectono-magmatic settings using sparse modeling. Frontiers in Earth Science 10.

[73] Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser Ł., Polosukhin I., 2017. Attention is all you need. Advances in neural information processing systems 30.

[74] Verma S.P., 2010. Statistical evaluation of bivariate, ternary and discriminant function tectonomagmatic discrimination diagrams. Turkish Journal of Earth Sciences 19, 185-238.

[75] Vermeesch P., 2006b. Tectonic discrimination of basalts with classification trees. Geochim. Cosmochim. Acta 70, 1839-1848.

[76] Vermeesch P., 2006a. Tectonic discrimination diagrams revisited. Geochemistry, Geophysics, Geosystems 7, Q06017. https://doi.org/10.1029/2005GC001092.

[77] Wang J., Long X., Chen G., Wu Z., Chen Z., Ding E., Vis B., 2022. U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction.

[78] Wickman F.E., 1968. Repose period patterns of volcanoes. V. General discussion and a tentative stochastic model. Arkiv for Mineralogi och Geologi 4, 351-351.

[79] Wilkinson M.D., Dumontier M., Aalbersberg I.J., Appleton G., Axton M., Baak A., Blomberg N., Boiten J.-W., da Silva Santos L.B., Bourne P.E., 2016. The FAIR Guiding Principles for scientific data management and stewardship. Scientific data 3, 1-9.

[80] Wilson M., 1989. Igneous Petrogenesis A Global Tectonic Approach. Springer Netherlands.

[81] Wood D.A., Joron J.-L., Treuil M., 1979. A re-appraisal of the use of trace elements to classify and discriminate between magma series erupted in different tectonic settings. Earth Planet. Sci. Lett. 45, 326-336.

[82] Xia L., Li X., 2019. Basalt geochemistry as a diagnostic indicator of tectonic setting. Gondwana Research 65, 43-67.

[83] Zeiler M.D., Fergus R., 2014. Visualizing and understanding convolutional networks, Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13. Springer, pp. 818-833.

[84] Zhang R., Cheng Z., Zhang Z., Chen Z., Ernst R., Santosh M., 2023. Formation of Tarim Large Igneous Province and Strengthened Lithosphere Revealed Through Machine Learning. Journal of Geophysical Research: Solid Earth 128, e2022JB025772.

[85] Zhao X., Mendel J.M., 1998. Minimum-variance deconvolution using artificial neural networks. SEG Technical Program Expanded Abstracts, 738-741.

[86] Zhong R., Deng Y., Yu C., 2021. Multi-layer perceptron-based tectonic discrimination of basaltic rocks and an application on the Paleoproterozoic Xiong'er volcanic province in the North China Craton. Computers and Geosciences 149.