Geophysical research: article

REVIEW AND PROSPECTS OF APPLYING MODERN APPROACHES TO COMPREHENSIVE GEODATA ANALYSIS FOR PREDICTING THE SPATIAL DISTRIBUTION OF GEOLOGICAL AND GEOPHYSICAL PARAMETERS
A.A. Soloviev 1,2 I.A. Lisenkov 1
1 Geophysical Center, Russian Academy of Sciences 2 Schmidt Institute of Physics of the Earth, Russian Academy of Sciences
Journal: Geophysical research
Tome: 25
Number: 2
Year: 2024
Pages: 20-45
UDK: 550.34.013.4
DOI: 10.21455/gr2024.2-2
Full text
Keywords: multivariate data analysis, geospatial data, machine learning, GIS, convolutional neuron networks, decision trees, geological and geophysical data, spatial correlation of geophysical fields, Russian Arctic.
Аnnotation: This paper provides an overview of the application of modern approaches to the collection and combined anal-ysis of digital geodata in geophysical problems that involve the search for internal patterns in such data. In particular, the problems of identifying informative features when recognizing strong earthquake-prone areas, assessing attributes of potential geothermal reservoirs and minerals using indirect geodata, defining spatial correlations in geophysical fields, geological structures, and geotectonic processes etc. are considered. It is shown that such studies are quite limited to a narrow semantic formulation of the problem implying analysis of small and predefined data sets. During the analysis, types and structures of source data are determined, as well as their availability for conducting of relevant computational experiments. The concept of a generalized array of geological and geophysical information is introduced and the need to form a unified structure for storing geospatial data is substantiated. Such structure is necessary for the assessment of geological and geophysical parameters using well-established classical geoinformatics approaches and modern data analysis algorithms based on machine learning and artificial neural networks. A general statement of the problem is formulated for a comprehensive analysis of the entire variety of available geodata to assess the spatial distribution of individual geological and geophysical parameters. This statement of the problem is necessary for planning further stages of the study for collecting and processing of data. The general principles for the formation of software and hardware infrastructure for collecting and processing geodata to solve the problem are given. To demonstrate the prospects of the proposed approach within the framework of the formulated general problem, the results of applying classical machine learning algorithms on a limited sample of geodata are presented. The efficiency of the classification results in this experiment exceeds 90 %.
Bibliography: Agterberg F.P., Bonham-Carter G.F., Wright D.F., Statistical Pattern Integration for Mineral Exploration, in Com-puter Applications in Resource Estimation, Oxford, Pergamon Press, 1990, pp. 1-21. https://doi.org/10.1016/B978-0-08-037245-7.50006-8

Alekseevskaya M.A., Gabrielov A.M., Gvishiani A.D., Gelfand I.M., Rantsman E.Ya., Morphostructural zoning of mountainous countries according to formalized features, Vychislitel'naya seismologiya (Computa-tional seismology), 1977, no. 10, pp. 33-49. [In Russian].

Alekseevskaya M.A., Gabrielov A.M., Gvishiani A.D., Gelfand I.M., RanzmanE.Ya., Formal morphostructural zoning of mountain territories, Journal of Geophysics, 1977, vol. 43, pp. 227-233.

Alzubaidi L., Zhang J., Humaidi A., Al-Dujaili A., Duan Y., Al-Shamma O., Santamaría J., Fadhel M.,

Al-Amidie M., Farhan L., Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, Journal of Big Data, 2021, vol. 8, 74 p. DOI: 10.1186/s40537-021-00444-8

Amante C., Eakins B.W., ETOPO1. 1 Arc-Minute Global Relief Model: Procedures, Data Sources and Analysis. NOAA Technical Memorandum NESDIS NGDC-24, 19 pp., March 2009. URL: http://www.ngdc.noaa.gov/mgg/global/global.html. Accessed 17.04.2024.

Andrianova O.N., Guryeva I.G., Kuznetsova G.N., Lipatov A.V., Sirota Yu.N., Chistyakova T.N., Gosudarstvennaya geologicheskaya karta masshtaba 1:2 500 000 (State Geological scale map 1:2 500 000), St. Petersburg, VSEGEI, 2011. [In Russian].

Breiman L., Random forests, Machine Learning, 2001, vol. 45, pp. 5-32. DOI: 10.1023/A:1010933404324

CEIC - China Earthquake Networks. URL: http://www.ceic.ac.cn. Accessed 17.04.2024.

Cristianini N., Shawe-Taylor J., An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge, New York, Cambridge University Press, 2000, 189 p.

Dobretsov N.L., Vasilevskiy A.N., Postglacial Uplift: Record in the Gravity Field and in Neogene-Quaternary Structures, Russian Geology and Geophysics, 2019, vol. 60, no. 12, pp. 1327-1352. https://doi.org/

10.15372/RGG2019131

Dzeboev B.A., Gvishiani A.D., Agayan S.M., Belov I.O., Karapetyan J.K., Dzeranov B.V., Barykina Y.V., System-Analytical Method of Earthquake-Prone Areas Recognition, Applied Sciences, 2021, vol. 11, no. 17, 31 p. DOI: 10.3390/app11177972

European Commission - Directorate General Joint Research Centre, Institute for Environment and Sustainability. 2004. European Soil Database (v 2.0), European Soil Bureau Network and the European Commission, EUR 19945 EN, March 2004. URL: https://esdac.jrc.ec.europa.eu/content/european-soil-database-v20-vector-and-attribute-data. Accessed 17.04.2024.

Förste C., Bruinsma S.L., Shako R., Abrikosov O., Flechtner F., Marty J.-C., Lemoine J.-M., Dahle C., Neumeyer H., Barthelmes F., Biancale R., Balmino G., König R., A new release of EIGEN-6: The latest combined global gravity field model including LAGEOS, GRACE and GOCE data from the collaboration of GFZ Potsdam and GRGS Toulouse, in Geophysical Research Abstracts. EGU General Assembly. Vol. 14, Ger-many, Copernicus GmbH on behalf of the European Geosciences Union, 2012, 1 p.

Fullea J., Afonso J.C., Connolly J.A.D., Fernàndez M., García-Castellanos D., Zeyen H., LitMod3D: An interac-tive 3-D software to model the thermal, compositional, density, seismological, and rheological structure of the lithosphere and sublithospheric upper mantle, Geochemistry, Geophysics, Geosystems, 2009, vol. 10, no. 8, pp. 1-21. DOI: 10.1029/2009GC002391

GEBCO – The General Bathymetric Chart of the Oceans. URL: https://www.gebco.net/. Accessed 27.06.2023.

Gelfand I.M., Guberman S.A., Izvekova M.L., Keilis-Borok V.I., Rantsman E.Ya., On the criteria of high seis-micity, Doklady AN SSSR (Doklady Earth Sciences), 1972, vol. 202, no. 6, pp. 1317-1320. [In Russian].

Gelfand I.M., Guberman Sh., Izvekova M.L., Keilis-Borok V.I., Ranzman E.Ja., Criteria of high seismicity de-termined by pattern recognition, Tectonophysics, 1972, vol. 13, no. 1-4, pp. 415-422.

Golebiowski T., Piwakowski B., Cwiklik M., Application of Complex Geophysical Methods for the Detection of Unconsolidated Zones in Flood Dikes, Remote Sensing, 2022, vol. 14, 24 p. DOI: 10.3390/rs14030538

Goodfellow I., Bengio Y., Courville A., Deep Learning, USA, Cambridge, MIT Press, 2016, pp. 95-221.

Gorshkov A.I., Soloviev A.A., Characterization of ore-bearing nodes by pattern recognition methods, in Krupnye i superkrupnye mestorozhdeniya: zakonomernosti razmeshcheniya i usloviya obrazovaniya (Large and super-large deposits: patterns of location and conditions of formation), Moscow, IGEM RAN, 2004, pp. 381-390. [In Russian].

Gorshkov A., Kossobokov V., Soloviev A., Recognition of Earthquake-Prone Areas, in Nonlinear Dynamics of the Lithosphere and Earthquake Prediction, Berlin-Heidelberg, Springer-Verlag, 2003, pp. 239-310.

Gorshkov A.I., Soloviev A.A., Recognition of the appearance of ore deposits in the Tethys belt, in Krupnye i superkrupnye mestorozhdeniya rudnykh poleznykh iskopaemykh. T. 1. Global'nye zakonomernosti razme-shcheniya (Large and super-large deposits of ore minerals. Vol. 1. Global patterns of placement), Moscow, IGEM RAN, 2006, pp. 361-374. [In Russian].

Gvishiani A.D., Soloviev A.A., On the occurrence of epicenters of strong earthquakes at the intersection of mor-phostructural lineaments in South America, Vychislitel'naya seismologiya (Computational seismology), 1981, no. 13, pp. 46-50. [In Russian].

Gvishiani A.D., Gorshkov A.I., Rantsman E.Ya., Sisternas A., Soloviev A.A., Prognozirovanie mest zemlet-ryasenii v regionakh umerennoi seismichnosti (Forecasting earthquake sites in regions of moderate seis-micity), Moscow, Nauka, 1988, 176 p. [In Russian].

Gvishiani A.D., Agayan S.M., Dzeboev B.A., Belov I.O., Recognition of strong earthquake–prone areas with a single learning class, Doklady Earth Sciences, 2017, vol. 474, no. 1, pp. 546-551. https://doi.org/10.1134/S1028334X17050038

Gvishiani A.D., Soloviev A.A., Dzeboev B.A., Problem of Recognition of Strong-Earthquake-Prone Areas: A State-of-the-Art Review, Izvestiya, Physics of the Solid Earth, 2020, vol. 56, no. 1, pp. 1-23. https://doi.org/10.1134/S1069351320010048

Gvishiani A.D., Dobrovolsky M.N., Dzeranov B.V., Dzeboev B.A., Big Data in Geophysics and Other Earth Sci-ences, Izvestiya, Physics of the Solid Earth, 2022, vol. 58, no. 1, pp. 1-29. https://doi.org/10.1134/S1069351322010037

Gvishiani A., Dzeboev B., Dzeranov B., Kedrov E., Skorkina A., Nikitina I., Strong Earthquake-Prone Areas in the Eastern Sector of the Arctic Zone of the Russian Federation, Applied Sciences, 2022b, vol. 12, no. 23, 11990. DOI: 10.3390/app122311990

Gvishiani A., Vorobieva I., Shebalin P., Dzeboev B., Dzeranov B., Skorkina A., Integrated Earthquake Catalog of the Eastern Sector of Russian Arctic, Applied Sciences, 2022a, vol. 12, no. 10, 5010. https://doi.org/10.3390/app12105010

Ho T.K., Random decision forests, in Proceedings of 3rd International Conference on Document Analysis and Recognition. V. 1, Canada, IEEE, 1995, pp. 278-282. DOI: 10.1109/ICDAR.1995.598994

Hosseinali F., Alesheikh A., Weighting Spatial Information in GIS for Copper Mining Exploration, American Journal of Applied Sciences, 2008, vol. 5, no. 9, pp. 1187-1198.

Ibrahim M.B., Mustaffa Z., Balogun A., Indra Sati H.H., Landslide Risk Analysis Using Machine Learning Prin-ciples: A Case Study of Bukit Antrabangsa Landslide Incidence, Journal of Hunan University Natural Sciences, 2022, vol. 49, no. 5, 15 p.

IIASA. The International Institute for Applied Systems Analysis, 2002. Land Resources of Russia. URL: https://webarchive.iiasa.ac.at/Research/FOR/russia_cd/download.htm. Accessed 17.04.2024.

IIASA. The International Institute for Applied Systems Analysis, 2023. Global Forest Database. URL: https://iiasa.ac.at/models-tools-data/global-forest-database. Accessed 17.04.2024.

Jarvis A., Reuter H.I., Nelson A., Guevara E., Hole-filled seamless SRTM data V4, International Centre for Trop-ical Agriculture (CIAT), 2008. URL: http://srtm.csi.cgiar.org. Accessed 17.04.2024.

Kaban M., Sidorov R., Soloviev A., Gvishiani A., Petrunin A., Petrov O., Kashubin S., Androsov E., Milshtein E., A new Moho map for north-eastern Eurasia based on the analysis of various geophysical data, Pure and Applied Geophysics, 2022, vol. 179, pp. 3903-3916. DOI: 10.1007/s00024-021-02925-6

Kana J.D., Djongyang N., Raidandi D., Nouck P.N., Dadje A., A review of geophysical methods for geothermal exploration, Renewable and Sustainable Energy Reviews, 2015, vol. 44, pp. 87-95.

Krasnoperov R.I., Soloviev A.A., Analytical geoinformation system for complex geological and geophysical re-search in Russia, Gornyi zhurnal (Mining Journal), 2015, no. 10, pp. 89-93. [In Russian].

Krizhevsky A., Sutskever I., Hinton G., ImageNet Classification with Deep Convolutional Neural Networks, Communications of the ACM, 2017, vol. 60, no. 6, pp. 84-90. DOI: 10.1145/3065386

Koulakov I.Y., Gaina C., Dobretsov N.L., Vasilevsky A.N., Bushenkova N.A., Plate Reconstructions in the Arctic Region Based on Joint Analysis of Gravity, Magnetic, and Seismic Anomalies, Russian Geology and Ge-ophysics, 2013, vol. 54, no. 8, pp. 859-873.

Lee C., Cheang P., Moslehpour M., Predictive Analysis in Business Analytics: Application of Decision Tree, Ad-vances in Decision Sciences, 2022, vol. 26, no. 1, pp. 1-29. DOI: 10.47654/v26y2022i1p1-29

Lee S., Lee M.-J., Jung H.-S., Data Mining Approaches for Landslide Susceptibility Mapping in Umyeonsan, Seoul, South Korea, Applied Sciences, 2017, vol. 7, no. 7, 21 p. DOI: 10.3390/app7070683

Lesur V., Hamoudi M., Choi Y., Dyment J., Thebault E., Building the second version of the World Digital Mag-netic Anomaly Map (WDMAM), Earth, Planets and Space, 2016, vol. 68, no. 27, 13 p.

Li J., Cheng J., Shi J., Huang F., Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement, Advances in Computer Science and Information Engineering, 2012, vol. 2, pp. 553-558.

Liu Z., Cheng L., Review of GIS Technology and Its Applications in Different Areas, in IOP Conference Series: Materials Science and Engineering. V. 735, Bristol, England, IOP Publishing, 2020, 012066.

Liu J., Dong F., Li Z., Application of Convolutional Neural Network to GIS and Physics, Computational Intelli-gence and Neuroscience, 2022, vol. 2022, 6 p. https://doi.org/10.1155/2022/8559343

Livinsky A.I., Gorshkov A.I., Novikova O.V., Characteristic geological and geophysical features of ore-bearing nodes of the Caucasus and Altai-Sayan region, in Tezisy dokladov II Vserossiiskoi nauchnoi konferentsii s mezhdunarodnym uchastiem “Sovremennye metody otsenki seismicheskoi opasnosti i prognoza zemlet-ryasenii” (Abstracts of the II All-Russian Scientific Conference with international participation “Modern methods of seismic hazard assessment and earthquake prediction”), Moscow, ITPZ RAS, 2021, pp. 66-68. [In Russian].

Meyer B., Saltus R., Chulliat A., EMAG2: Earth Magnetic Anomaly Grid (2-arc-minute resolution) Version 3. National Centers for Environmental Information, NOAA. Model, 2017. URL: https://www.ngdc.noaa.gov/geomag/emag2.html. Accessed 17.04.2024.

Mineragenicheskaya karta Rossiiskoi Federatsii i sopredel'nykh gosudarstv (v predelakh byvshego SSSR) masshtaba 1:2 500 000 (Mineragenic map of the Russian Federation and neighboring states (within the former USSR) scale 1:2 500 000). Moscow, FGUNPP Aerogeologiya, 2009. [In Russian].

Mohan S., Giridhar M., A brief review of recent developments in the integration of deep learning with GIS, Geo-matics and Environmental Engineering, 2022, vol. 16, no. 2, pp. 21-38. https://doi.org/10.7494/geom.2022.16.2.21

Nikishin D.A., Comparison of the features of the representation of geodata in cartography and geoinformatics, Sistemy i sredstva informatiki (Computer science systems and tools), 2018, vol. 28, no. 2, pp. 60-74. [In Russian]. DOI: 10.14357/08696527180205

Pavlis N.K., Holmes S.A., Kenyon S.C., Factor J.K., An Earth Gravitational Model to Degree 2160: EGM2008, presented at the 2008 General Assembly of the European Geosciences Union, Vienna, Austria, April. 2008. URL: http://earth-info.nga.mil/GandG/wgs84/gravitymod/egm2008/egm08_wgs84.html. Accessed 27.06.2023.

Petrunin A.G., Soloviev A.A., Sidorov R.V., Gvishiani A.D., Inverse-forward method for heat flow estimation: case study for the Arctic region, Russian Journal of Earth Sciences, 2022, vol. 22, pp. 1-9.

Pradhan B., Lee S., Landslide risk analysis using artificial neural network model focusing on different training sites, International Journal of Physical Sciences, 2009, vol. 4, no. 1, pp. 001-015.

Press Gil. Cleaning Big Data: Most Time-Consuming, Least Enjoyable Data Science Task, Sur-vey Says, 2016. URL: https://www.forbes.com/sites/gilpress/2016/03/23/data-preparation-most-time-consuming-least-enjoyable-data-science-task-survey-says. Acessed: 17.04.2024.

Rabhi L., Falih N., Afraites A., Bouikhalene B., Big Data Approach and its applications in Various Fields: Re-view, Procedia Computer Science, 2019, vol. 155, pp. 599-605. DOI: 10.1016/j.procs. 2019.08.084

Rumelhart D.E., Hinton G.E., Williams R.J., Learning Internal Representations by Error Propagation, in Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations, Cambridge, MIT Press, 1987, pp. 318-362.

Sidorov R.V., Kaban M.K., Soloviev A.A., Petrunin A.G., Gvishiani A.D., Oshchenko A.A., Popov A.B., Krasnop-erov R.I., Sedimentary basins of the eastern Asia Arctic zone: new details on their structure revealed by decompensative gravity anomalies, Solid Earth, 2021, vol. 12, pp. 2773-2788. https://doi.org/10.5194/

se-12-2773-2021

Sindayigaya L., Dey A., Machine learning algorithms: A review, International Journal of Science and Research, 2022, vol. 11, iss. 8, 7 p. DOI: 10.21275/SR22815163219

Soloviev A.A., Gorshkov A.I., Soloviev A.A., Application of the Data on the Lithospheric Magnetic Anomalies in the Problem of Recognizing the Earthquake Prone Areas, Izvestiya, Physics of the Solid Earth, 2016, vol. 52, no. 6, pp. 803-809.

Soloviev A.A., Soloviev A.A., Gvishiani A.D., Nikolov B.P., Nikolova Y.I., GIS-oriented database on seismic hazard assessment for Caucasian and Crimean regions, Izvestiya, Atmospheric and Oceanic Physics, 2018, vol. 54, no. 9, pp. 1363-1373. DOI: 10.1134/S0001433818090505

Stolk W., Kaban M.K., Beekman F., Tesauro M., Mooney W.D., Cloetingh S., High resolution regional crustal models from irregularly distributed data: Application to Asia and adjacent areas, Tectonophysics, 2013, vol. 602, pp. 55-68. http://dx.doi.org/10.1016/j.tecto.2013.01.022

Sun T., Chen F., Zhong L., Liu W., Wang Y., GIS-based mineral perspectivity mapping using machine learning methods: A case study from Tongling ore district, eastern China, Ore Geology Reviews, 2019, vol. 109, pp. 26-49. https://doi.org/10.1016/j.oregeorev.2019.04.003

USGS EROS Archive - Digital Elevation - Global 30 Arc-Second Elevation (GTOPO30). URL: https://www.

usgs.gov/centers/eros/science/usgs-eros-archive-digital-elevation-global-30-arc-second-elevation-gtopo30. Acessed 17.04.2024.

Yesin E.I., Vasilevsky A.N., Bushenkova N.A., Spatial correlations of relief features, gravitational field and ve-locity anomalies of seismic waves in the central zone of the Kamchatka region, in Materialy pervoi Vse-rossiiskoi nauchnoi konferentsii “Dobretsovskie chteniya: nauka iz pervykh ruk” (Materials of the first All-Russian scientific conference “Dobretsov readings: first-hand science”), Novosibirsk, Siberian Branch of the Russian Academy of Sciences, 2022, pp. 97-100. [In Russian].

Yu S., Ma J., Deep learning for geophysics: Current and future trends, Reviews of Geophysics, 2021, vol. 59, 36 p. https://doi.org/10.1029/2021RG000742

Zavyalov A.D., Srednesrochnyi prognoz zemletryasenii. Osnovy, metodika, realizatsiya (Medium-term earth-quake forecast. Fundamentals, methodology, implementation), Moscow, Nauka, 2006, pp. 3-23. [In Russian].

Zhang Y.D., Xie Y.Y., Zhang T., Liu T., Zhang C., 2m survey method and its improved device application in Dongshan geothermal field in Xiamen in China, Environmental Earth Sciences, 2016, vol. 75, iss. 18, 1290. DOI: 10.1007/s12665-016-6048-9

Zhang Y.D., Zhang Y., Yu H., Li J., Xie Y., Lei Z., Geothermal resource potential assessment of Fujian Province, China, based on geographic information system (GIS) – supported models, Renewable Energy, 2020, vol. 153, pp. 564-579.