Enhanced View of the Mw 6.4 Petrinja (Croatia) Earthquake Sequence (2020–2022) Using Deep Learning
DOI:
https://doi.org/10.26443/seismica.v5i2.1770Keywords:
Machine learning, seismic catalogue, earthquake sequencesAbstract
Machine learning approaches have shown potential to automate the creation of seismic catalogues, but their abilities and performance are still questioned and being tested. We here present the Petrinja Earthquake Sequence Machine Learning Catalogue (PESMLC), generated using the EQTransformer seismic phase picker trained on the INSTANCE dataset, PyOcto for phase association, and NonLinLoc for event relocation. Our study focuses on the 2020 MW 6.4 Petrinja earthquake sequence in Croatia, covering the period from 28 December 2020 to 30 November 2022, during which we detected 41,989 seismic events. PESMLC achieves high matching rates — 96% for the first six months, and 85% over the complete study duration — when compared with detailed manual catalogues. The seismic network densification in January 2021 significantly enhanced event detection reliability, highlighting the importance of network configuration in efficient seismic monitoring. While our machine learning approach successfully identified previously undetected microseismicity and dramatically reduced processing time, we observed systematic limitations, including magnitude estimation biases and difficulties in accurately distinguishing closely spaced events in time. Optimisation of associator parameters remains essential, and should ideally be performed specifically for each network configuration, particularly for fully automated seismic monitoring systems. We further demonstrate that raw machine learning catalogues require quality filtering prior to seismological analysis: stricter magnitude of completeness estimators result in artificially high thresholds for unfiltered machine learning catalogues, and Omori p exponents are biased downward by low-quality detections. Both effects are resolved when analysis is restricted to a quality-filtered subset, which recovers parameters consistent with high-quality manual catalogues. Nevertheless, PESMLC overall provides a detailed, comprehensive seismic dataset aligned closely with manual catalogues, demonstrating the considerable potential of machine learning to support routine seismic monitoring, particularly in resource-limited observatories and/or for long seismic sequences and large datasets.
References
Allen, R. V. (1978). Automatic earthquake recognition and timing from single traces. Bulletin of the Seismological Society of America, 68(5), 1521–1532. https://doi.org/10.1785/bssa0680051521
Atalić, J., Demšić, M., Baniček, M., Uroš, M., Dasović, I., Prevolnik, S., Kadić, A., Novak, M. Š., & Nastev, M. (2022). The December 2020 Magnitude (Mw) 6.4 Petrinja earthquake, Croatia: Seismological aspects, emergency response and impacts. https://doi.org/10.21203/rs.3.rs-2136108/v1
Baize, S., Amoroso, S., Belić, N., Benedetti, L., Boncio, P., Budić, M., Cinti, F., Henriquet, M., Jamšek Rupnik, P., Kordić, B., & others. (2022). Environmental effects and seismogenic source characterization of the December 2020 earthquake sequence near Petrinja, Croatia. Geophysical Journal International, 230(2), 1394–1418.
Basili, R., Danciu, L., Carafa, M. M. C., Kastelic, V., Maesano, F. E., Tiberti, M. M., Vallone, R., Gracia, E., Sesetyan, K., Atanackov, J., Sket-Motnikar, B., Zupančič, P., Vanneste, K., & Vilanova, S. (2020). Insights on the European Fault-Source Model (EFSM20) as input to the 2020 update of the European Seismic Hazard Model (ESHM20). Copernicus GmbH. https://doi.org/10.5194/egusphere-egu2020-7008
Basili, R., Kastelic, V., Demircioglu, M., Garcia Moreno, D., Nemser, E. S., Petricca, P., Sboras, S. P., Besana-Ostman, G. M., Cabral, J., Camelbeeck, T., Caputo, R., Danciu, L., Domac, H., Fonseca, J., García-Mayordomo, J., Giardini, D., Glavatovic, B., Gulen, L., Ince, Y., … Wössner, J. (2013). The European Database of Seismogenic Faults (EDSF) compiled in the framework of the Project SHARE.
Becker, D., McBrearty, I. W., Beroza, G. C., & Martínez-Garzón, P. (2024). Performance of AI-Based Phase Picking and Event Association Methods after the Large 2023 Mw 7.8 and 7.6 Türkiye Doublet. Bulletin of the Seismological Society of America, 114(5), 2457–2473. https://doi.org/10.1785/0120240017
Braszus, B., Rietbrock, A., Haberland, C., & Ryberg, T. (2024). AI based 1-D P- and S-wave velocity models for the greater alpine region from local earthquake data. Geophysical Journal International, 237(2), 916–930. https://doi.org/10.1093/gji/ggae077
Cao, A., & Gao, S. S. (2002). Temporal variation of seismic b ‐values beneath northeastern Japan island arc. Geophysical Research Letters, 29(9). https://doi.org/10.1029/2001gl013775
Cianetti, S., Bruni, R., Gaviano, S., Keir, D., Piccinini, D., Saccorotti, G., & Giunchi, C. (2021). Comparison of Deep Learning Techniques for the Investigation of a Seismic Sequence: An Application to the 2019, Mw 4.5 Mugello (Italy) Earthquake. Journal of Geophysical Research: Solid Earth, 126(12). https://doi.org/10.1029/2021jb023405
Clauset, A., Shalizi, C. R., & Newman, M. E. J. (2009). Power-Law Distributions in Empirical Data. SIAM Review, 51(4), 661–703. https://doi.org/10.1137/070710111
Dasović, I., Herak, M., Herak, D., Latečki, H., Sečanj, M., Tomljenović, B., Cvijić-Amulić, S., & Stipčević, J. (2024). The Berkovići (BIH) ML= 6.0 earthquake sequence of 22 April 2022–Seismological and seismotectonic analyses. Tectonophysics, 875, 230253.
Fernandez-Prieto, L. M., García, J. E., Villaseñor, A., Sanz, V., Ammirati, J.-B., Díaz, E., & García, C. (2022). Performance of Deep Learning pickers in routine network processing applications. https://doi.org/10.5194/egusphere-egu22-7844
Fonzetti, R., Govoni, A., De Gori, P., Valoroso, L., & Chiarabba, C. (2025). Machine learning-based high-resolution data set for the 2009 L’Aquila earthquake sequence. Geophysical Journal International, 243(1). https://doi.org/10.1093/gji/ggaf286
Herak, D., & Herak, M. (2010). The Kupa Valley (Croatia) Earthquake of 8 October 1909–100 Years Later. Seismological Research Letters, 81(1), 30–36. https://doi.org/10.1785/gssrl.81.1.30
Herak, M. (2020). Conversion between the local magnitude (ML) and the moment magnitude (Mw) for earthquakes in the Croatian Earthquake Catalogue. Geofizika, 37(2), 197–211. https://doi.org/10.15233/gfz.2020.37.10
Herak, M. (2025). Croatian catalogue and database of focal mechanism solutions, characteristic mechanisms, and stress field properties in the Dinarides and the surrounding regions. Geofizika, 41(2), 79–123. https://doi.org/10.15233/gfz.2024.41.5
Herak, M., & Herak, D. (2023). Properties of the Petrinja (Croatia) earthquake sequence of 2020–2021 – Results of seismological research for the first six months of activity. Tectonophysics, 858, 229885. https://doi.org/10.1016/j.tecto.2023.229885
Herak, M., Herak, D., & Markušić, S. (1996). Revision of the earthquake catalogue and seismicity of Croatia, 1908–1992. Terra Nova, 8(1), 86–94. https://doi.org/10.1111/j.1365-3121.1996.tb00728.x
Herak, M., Herak, D., & Orlić, N. (2022). Properties of the Zagreb 22 March 2020 earthquake sequence–analyses of the full year of aftershock recording. Geofizika, 38(2), 93–116. https://doi.org/10.15233/gfz.2021.38.6
Hu, Q., Liang, H., Li, H., Shan, X., & Zhang, G. (2024). Aftershock Spatiotemporal Activity and Coseismic Slip Model of the 2022 Mw 6.7 Luding Earthquake: Fault Geometry Structures and Complex Rupture Characteristics. Remote Sensing, 17(1), 70. https://doi.org/10.3390/rs17010070
Jiang, C., Fang, L., Fan, L., & Li, B. (2021). Comparison of the earthquake detection abilities of PhaseNet and EQTransformer with the Yangbi and Maduo earthquakes. Earthquake Science, 34(5), 425–435. https://doi.org/10.29382/eqs-2021-0038
Jiang, C., Zhang, P., White, M. C. A., Pickle, R., & Miller, M. S. (2022). A detailed earthquake catalog for Banda Arc–Australian plate collision zone using machine-learning phase picker and an automated workflow. The Seismic Record, 2(1), 1–10. https://doi.org/10.1785/0320210041
Kim, A., Nakamura, Y., & Yukutake, Y. (2022). Development of high-performance seismic phase picker using deep learning in Hakone Volcanic Area. Research Square. https://doi.org/10.21203/rs.3.rs-2253946/v1
Kong, Q., Trugman, D. T., Ross, Z. E., Bianco, M. J., Meade, B. J., & Gerstoft, P. (2018). Machine Learning in Seismology: Turning Data into Insights. Seismological Research Letters, 90(1), 3–14. https://doi.org/10.1785/0220180259
Li, Z., Meier, M., Hauksson, E., Zhan, Z., & Andrews, J. (2018). Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning. Geophysical Research Letters, 45(10), 4773–4779. https://doi.org/10.1029/2018gl077870
Lomax, A., & Savvaidis, A. (2021). High-precision earthquake location using source-specific station terms and inter-event waveform similarity. ESS Open Archive. https://doi.org/10.1002/essoar.10507108.2
Lomax, A., Virieux, J., Volant, P., & Berge-Thierry, C. (2000). Probabilistic earthquake location in 3D and layered models: Introduction of a Metropolis-Gibbs method and comparison with linear locations. In Advances in Seismic Event Location (pp. 101–134). Springer Netherlands. https://doi.org/10.1007/978-94-015-9536-0_5
Majstorović, J., Giffard-Roisin, S., & Poli, P. (2022). Interpreting convolutional neural network decision for earthquake detection with feature map visualization, backward optimization and layer-wise relevance propagation methods. Geophysical Journal International, 232(2), 923–939. https://doi.org/10.1093/gji/ggac369
Markušić, S., Stanko, D., Penava, D., Ivančić, I., Bjelotomić Oršulić, O., Korbar, T., & Sarhosis, V. (2021). Destructive M6.2 Petrinja Earthquake (Croatia) in 2020—Preliminary Multidisciplinary Research. Remote Sensing, 13(6), 1095. https://doi.org/10.3390/rs13061095
Michelini, A., Cianetti, S., Gaviano, S., Giunchi, C., Jozinović, D., & Lauciani, V. (2021). INSTANCE – the Italian seismic dataset for machine learning. Earth System Science Data, 13(12), 5509–5544. https://doi.org/10.5194/essd-13-5509-2021
Mirwald, A., Schmid, N., Mizrahi, L., Han, M., Rohnacher, A., Ritz, V. A., & Wiemer, S. (2026). SeismoStats: a Python package for statistical seismology. Seismological Research Letters. https://doi.org/10.1785/0220250266
Mizrahi, L., Nandan, S., & Wiemer, S. (2021). The Effect of Declustering on the Size Distribution of Mainshocks. Seismological Research Letters, 92(4), 2333–2342. https://doi.org/10.1785/0220200231
Mohorovičić, A. (1910). Potres od 8/X 1909.(Das Beben vom 8. X. 1909). Jahrbuch Des Meteorologischen Observatoriums in Zagreb (Agram) Für Das Jahr, 1909, 1.
Mohorovičić, A. (1992). Earthquake of 8 october 1909. Geofizika, 9(1), 3–55.
Mousavi, S. M., Beroza, G. C., Mukerji, T., & Rasht-Behesht, M. (2023). Applications of deep neural networks in exploration seismology: A technical survey. Geophysics, 89(1), WA95–WA115. https://doi.org/10.1190/geo2023-0063.1
Mousavi, S. M., Ellsworth, W. L., Zhu, W., Chuang, L. Y., & Beroza, G. C. (2020). Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nature Communications, 11(1). https://doi.org/10.1038/s41467-020-17591-w
Mousavi, S. M., Sheng, Y., Zhu, W., & Beroza, G. C. (2019). STanford EArthquake Dataset (STEAD): A Global Data Set of Seismic Signals for AI. IEEE Access, 7, 179464–179476. https://doi.org/10.1109/access.2019.2947848
Münchmeyer, J. (2024). PyOcto: A high-throughput seismic phase associator. Seismica, 3(1). https://doi.org/10.26443/seismica.v3i1.1130
Niksejel, A., & Zhang, M. (2024). OBSTransformer: a deep-learning seismic phase picker for OBS data using automated labelling and transfer learning. Geophysical Journal International, 237(1), 485–505. https://doi.org/10.1093/gji/ggae049
Ogata, Y. (1983). Estimation of the parameters in the modified Omori formula for aftershock frequencies by the maximum likelihood procedure. Journal of Physics of the Earth, 31(2), 115–124. https://doi.org/10.4294/jpe1952.31.115
Pita-Sllim, O., Chamberlain, C. J., Townend, J., & Warren-Smith, E. (2023). Parametric Testing of EQTransformer’s Performance against a High-Quality, Manually Picked Catalog for Reliable and Accurate Seismic Phase Picking. The Seismic Record, 3(4), 332–341. https://doi.org/10.1785/0320230024
Pollak, D., Gulam, V., Novosel, T., Avanić, R., Tomljenović, B., Hećej, N., Terzić, J., Stipčević, J., Bačić, M., Kurečić, T., & others. (2021). The preliminary inventory of coseismic ground failures related to December 2020–January 2021 Petrinja earthquake series. Geologia Croatica, 74(2), 189–208.
Ross, Z. E., Meier, M., & Hauksson, E. (2018). P Wave Arrival Picking and First‐Motion Polarity Determination With Deep Learning. Journal of Geophysical Research: Solid Earth, 123(6), 5120–5129. https://doi.org/10.1029/2017jb015251
Ross, Z. E., Meier, M., Hauksson, E., & Heaton, T. H. (2018). Generalized Seismic Phase Detection with Deep Learning. Bulletin of the Seismological Society of America, 108(5A), 2894–2901. https://doi.org/10.1785/0120180080
Ross, Z. E., Yue, Y., Meier, M., Hauksson, E., & Heaton, T. H. (2019). PhaseLink: A Deep Learning Approach to Seismic Phase Association. Journal of Geophysical Research: Solid Earth, 124(1), 856–869. https://doi.org/10.1029/2018jb016674
Sardeli, E., Michas, G., Pavlou, K., Zaccagnino, D., & Vallianatos, F. (2024). Spatiotemporal properties of the 2020–2021 Petrinja (Croatia) earthquake sequence. Journal of Seismology, 28(4). https://doi.org/10.1007/s10950-024-10228-1
Stipčević, J., Poggi, V., Herak, M., Parolai, S., Herak, D., Dasović, I., Bertoni, M., Barnaba, C., & Pesaresi, D. (2021). First results from temporary deployment of small seismic network following the Mw=6.4 Petrinja earthquake. EGU General Assembly 2021. https://doi.org/10.5194/egusphere-egu21-16579
Suarez, E. D., Domínguez-Cerdeña, I., Villaseñor, A., Aparicio, S. S.-M., del Fresno, C., & García-Cañada, L. (2023). Unveiling the pre-eruptive seismic series of the La Palma 2021 eruption: Insights through a fully automated analysis. Journal of Volcanology and Geothermal Research, 444, 107946. https://doi.org/10.1016/j.jvolgeores.2023.107946
Sugan, M., Peruzza, L., Romano, M. A., Guidarelli, M., Moratto, L., Sandron, D., Plasencia Linares, M. P., & Romanelli, M. (2023). Machine learning versus manual earthquake location workflow: testing LOC-FLOW on an unusually productive microseismic sequence in northeastern Italy. Geomatics, Natural Hazards and Risk, 14(1). https://doi.org/10.1080/19475705.2023.2284120
Tan, Y. J., Waldhauser, F., Ellsworth, W. L., Zhang, M., Zhu, W., Michele, M., Chiaraluce, L., Beroza, G. C., & Segou, M. (2021). Machine-learning-based high-resolution earthquake catalog reveals how complex fault structures were activated during the 2016–2017 central Italy sequence. The Seismic Record, 1(1), 11–19. https://doi.org/10.1785/0320210001
Tomac, I., Kovačević Zelić, B., Perić, D., Domitrović, D., Štambuk Cvitanović, N., Vučenović, H., Parlov, J., Stipčević, J., Matešić, D., Matoš, B., & Vlahović, I. (2023). Geotechnical reconnaissance of an extensive cover-collapse sinkhole phenomena of 2020–2021 Petrinja earthquake sequence (Central Croatia). Earthquake Spectra, 39(1), 653–686. https://doi.org/10.1177/87552930221115759
Tomac, I., Vlahovic, I., Parlov, J., Matoš, B., Matešic, D., Kosovic, I., Pavicic, I., Frangen, T., Terzic, J., Pavelic, D., & others. (2021). Geotechnical Reconnaissance and Engineering Effects of the December 29, 2020, M6. 4 Petrinja, Croatia Earthquake, and Associated Seismic Sequence [Techreport]. Technical report of Geotechnical Extreme Event Reconnaissance (GEER ….
University of Zagreb. (2001a). Croatian Seismograph Network. International Federation of Digital Seismograph Networks. https://doi.org/10.7914/SN/CR
University of Zagreb. (2001b). Croatian Seismograph Network. International Federation of Digital Seismograph Networks. https://doi.org/10.7914/SN/CR
Utsu, T. (2002). Statistical features of seismicity. In International Handbook of Earthquake and Engineering Seismology (pp. 719–732). Elsevier. https://doi.org/10.1016/s0074-6142(02)80246-7
Utsu, T., Ogata, Y., S, R., & Matsu’ura. (1995). The centenary of the Omori formula for a decay law of aftershock activity. Journal of Physics of the Earth, 43(1), 1–33. https://doi.org/10.4294/jpe1952.43.1
Waldhauser, F. (2001). hypoDD-A Program to Compute Double-Difference Hypocenter Locations. In Open-File Report. US Geological Survey. https://doi.org/10.3133/ofr01113
Waldhauser, F., & Ellsworth, W. L. (2000). A double-difference earthquake location algorithm: Method and application to the northern Hayward fault, California. Bulletin of the Seismological Society of America, 90(6), 1353–1368.
Wiemer, S., & Wyss, M. (2000). Minimum Magnitude of Completeness in Earthquake Catalogs: Examples from Alaska, the Western United States, and Japan. Bulletin of the Seismological Society of America, 90(4), 859–869. https://doi.org/10.1785/0119990114
Woessner, J., & Wiemer, S. (2005). Assessing the Quality of Earthquake Catalogues: Estimating the Magnitude of Completeness and Its Uncertainty. Bulletin of the Seismological Society of America, 95(2), 684–698. https://doi.org/10.1785/0120040007
Woollam, J., Münchmeyer, J., Tilmann, F., Rietbrock, A., Lange, D., Bornstein, T., Diehl, T., Giunchi, C., Haslinger, F., Jozinović, D., & others. (2022). SeisBench—A toolbox for machine learning in seismology. Seismological Society of America, 93(3), 1695–1709.
Woollam, J., Rietbrock, A., Bueno, A., & De Angelis, S. (2019). Convolutional Neural Network for Seismic Phase Classification, Performance Demonstration over a Local Seismic Network. Seismological Research Letters, 90(2A), 491–502. https://doi.org/10.1785/0220180312
Xiong, W., Yu, P., Chen, W., Liu, G., Zhao, B., Nie, Z., & Qiao, X. (2021). The 2020Mw 6.4 Petrinja earthquake: a dextral event with large coseismic slip highlights a complex fault system in northwestern Croatia. Geophysical Journal International, 228(3), 1935–1945. https://doi.org/10.1093/gji/ggab440
Zhou, J., Pham, T.-S., & Hrvoje Tkalčić. (2024). Deep-learning phase-onset picker for deep Earth seismology: PKIKP waves. ESS Open Archive, 2024(0422). https://doi.org/10.22541/essoar.171378807.79679078/v1
Zhou, Y., Yue, H., Kong, Q., & Zhou, S. (2019). Hybrid event detection and phase-picking algorithm using convolutional and recurrent neural networks. Seismological Research Letters, 90(3), 1079–1087. https://doi.org/10.1785/0220180319
Zhu, W., & Beroza, G. C. (2018). PhaseNet: a deep-neural-network-based seismic arrival-time picking method. Geophysical Journal International. https://doi.org/10.1093/gji/ggy423
Zhu, W., Mousavi, S. M., & Beroza, G. C. (2019). Seismic Signal Denoising and Decomposition Using Deep Neural Networks. IEEE Transactions on Geoscience and Remote Sensing, 57(11), 9476–9488. https://doi.org/10.1109/tgrs.2019.2926772
Žilić, I., Causse, M., Vallée, M., & Markušić, S. (2025). High Stress Drop and Slow Rupture During the 2020 MW6.4 Intraplate Petrinja Earthquake, Croatia. ESS Open Archive. https://doi.org/10.22541/essoar.173724184.40120513/v1
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Dinko Šindija, Marija Mustać Brčić, György Hetényi, Josip Stipčević
This work is licensed under a Creative Commons Attribution 4.0 International License.
