Skip to main content

Advertisement

Springer Nature Link
Log in

Performance enhancement of deep neural network using fusional data assimilation and divide-and-conquer approach; case study: earthquake magnitude calculation

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The presence of "ill-posed samples" specifically in low-volume datasets leads to accuracy decrement in the learning procedure and the generalization of neural networks. Such samples can be caused by various reasons such as noise contamination, corrupted sensors, or even, the complex distribution of physical properties governing the problem. The peak ground acceleration (PGA) datasets are definitely among the last mentioned. Focusing on speed and accuracy, a method for calculating earthquake magnitude based on the PGA data recorded at a single station along with hypocentral information has been presented in this research. Here, after training a deep neural network, the regression errors of the training data samples are clustered into two groups, namely well and ill posed using the grey wolf optimization algorithm. Instead of being removed, the data samples with low learning rates are then modified using samples selected from the other cluster in a fusional form. Then, two separate models are used and trained independently for the clusters. Next, in addition to the routine procedure of network generalization, every new sample is first checked whether is more likely to belong to which group of the clustered data, and after processing, the corresponding trained model is used. The results of the experiments show that using the proposed method results in magnitude calculation with an error order of less than 0.212 units of moment magnitude with a probability of more than 99.7%, which is superior to the conventional methods some of which were reviewed in this research.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data and resources

The data used in this study were extracted from the strong motion data reported by Japan’s Building Research Institute (BRI) strong motion network. https://smo.kenken.go.jp/. All data processing, model training procedures, and plotting the results were coded with Python using the Google Colaboratory environment.

References

  1. Yim J, Sohn K-A (2017) ‘Enhancing the performance of convolutional neural networks on quality degraded datasets. In: 2017 international conference on digital image computing: techniques and applications (DICTA), IEEE. https://doi.org/10.1109/dicta.2017.8227427

  2. Shu Z, Sheng VS, Li J (2018) Learning from crowds with active learning and self-healing. Neural Comput Appl 30(9):2883–2894. https://doi.org/10.1007/s00521-017-2878-y

    Article  Google Scholar 

  3. Ma Z, Mei G, Piccialli F (2021) Machine learning for landslides prevention: a survey. Neural Comput Appl 33(17):10881–10907. https://doi.org/10.1007/s00521-020-05529-8

    Article  Google Scholar 

  4. Pulgar FJ et al (2017) On the impact of imbalanced data in convolutional neural networks performance. In: Lecture Notes in Computer Science. Springer, Cham (Lecture notes in computer science), pp 220–232. https://doi.org/10.1007/978-3-319-59650-1_19.

  5. Bath M (1966) Earthquake energy and magnitude. Phys Chem Earth 7:115–165. https://doi.org/10.1016/0079-1946(66)90003-6

    Article  Google Scholar 

  6. Walczak S (2001) An empirical analysis of data requirements for financial forecasting with neural networks. J Manag Inf Syst 17(4):203–222

    Article  Google Scholar 

  7. Tabatabae SM, Kimiaefar R, Hajian A, Akbari A (2022) Prediction of the peak ground acceleration for Zagros earthquakes using ANFIS and data partitioning approach. J Geogr Environ Stud 42(11):92–104

    Google Scholar 

  8. Richter CF (1935) An instrumental earthquake magnitude scale (PDF). Bull Seismol Soc Am 25:1–32

    Article  Google Scholar 

  9. Lockman A, Allen RM (2005) Single station earthquake characterization for early warning. Bull Seismol Soc Am 95:2029–2039

    Article  Google Scholar 

  10. Delouis B, Charlety J, Vallee M (2009) A method for rapid determination of moment magnitude Mw for moderate to large earthquakes from the near-field spectra of strong-motion records (MWSYNTH). Bull Seismol Soc Am 99(3):1827–1840

    Article  Google Scholar 

  11. Ochoa LH, Niño LF, Vargas CA (2018) Fast magnitude determination using a single seismological station record implementing machine learning techniques. Geod Geodyn 9(1):34–41. https://doi.org/10.1016/j.geog.2017.03.010

    Article  Google Scholar 

  12. Mousavi SM et al (2019) ‘CRED: a deep residual network of convolutional and recurrent units for earthquake signal detection. Sci Rep. https://doi.org/10.1038/s41598-019-45748-1

    Article  Google Scholar 

  13. Zhu W, Biondi E, Li J, Yin J, Ross ZE, Zhan Z (2023) Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning. Nat Commun. https://doi.org/10.21203/rs.3.rs-2597732/v1

    Article  Google Scholar 

  14. Samadi H, Kimiaefar R, Hajian A (2022) Fast earthquake relocation using ANFIS neuro-fuzzy network trained based on the double difference method. Sci Q J Geosci 32(3):93–102. https://doi.org/10.22071/gsj.2022.296260.1922

    Article  Google Scholar 

  15. Fukushima R, Kano M, Hirahara K (2023) Physics-informed neural networks for fault slip monitoring: simulation, frictional parameter estimation, and prediction on slow slip events in a spring-slider system. J Geophys Res Solid Earth 128(12):12. https://doi.org/10.1029/2023jb027384

    Article  Google Scholar 

  16. Wang X, Wang X, Zhang X, Wang L, Guo H, Li D (2023) Near real-time spatial prediction of earthquake-induced landslides: a novel interpretable self-supervised learning method. Int J Digit Earth 16(1):1885–1906. https://doi.org/10.1080/17538947.2023.2216029

    Article  Google Scholar 

  17. Tabatabaei M, Kimiaefar R, Hajian A, Akbari A (2021) Robust outlier detection in geo-spatial data based on lolimot and KNN search. Earth Sci Inform 14(2):1065–1072. https://doi.org/10.1007/s12145-021-00610-9

    Article  Google Scholar 

  18. Namdari A, Li ZS (2021) A multiscale entropy-based long short term memory model for lithium-ion battery prognostics. In: 2021 IEEE international conference on prognostics and health management (ICPHM), Detroit (Romulus), MI, USA, pp 1–6. https://doi.org/10.1109/ICPHM51084.2021.9486674

  19. Namdari Al, Asad SM, Durrani TS (2022) Lithium-ion battery prognostics through reinforcement learning based on entropy measures. Algorithms 15(11):393. https://doi.org/10.3390/a15110393

    Article  Google Scholar 

  20. Li S, Yang X, Cao A, Wang C, Liu Y, Liu Y, Niu Q (2023) Seismogram transformer: a generic deep learning backbone network for multiple earthquake monitoring tasks. arXiv preprint arXiv:2310.01037

  21. Cho H, Yoon S (2018) ‘Divide and conquer-based 1D CNN human activity recognition using test data sharpening. Sensors (Basel, Switzerland) MDPI AG 18(4):1055. https://doi.org/10.3390/s18041055

    Article  Google Scholar 

  22. Niculescu V (2022) On generalizing divide and conquer parallel programming pattern. Mathematics MDPI AG 10(21):3925. https://doi.org/10.3390/math10213925

    Article  Google Scholar 

  23. Tripathi AK, Sharma K, Bala M (2018) A novel clustering method using enhanced grey wolf optimizer and MapReduce. Big Data Res 14:93–100. https://doi.org/10.1016/j.bdr.2018.05.002

    Article  Google Scholar 

  24. Karakoyun M, Inan O, Akto İ (2019) Grey Wolf Optimizer (GWO) algorithm to solve the partitional clustering problem. Int J Intell Syst Appl Eng 7(4):201–206. https://doi.org/10.18201/ijisae.2019457231

    Article  Google Scholar 

  25. Aljarah I, Mafarja M, Heidari AA et al (2020) Clustering analysis using a novel locality-informed grey wolf-inspired clustering approach. Knowl Inf Syst 62:507–539. https://doi.org/10.1007/s10115-019-01358-x

    Article  Google Scholar 

  26. Tripathi A, Bharti KK, Ghosh M (2023) A fusion of binary grey wolf optimization algorithm with opposition and weighted positioning for feature selection. Int J Inf Tecnol 15:4469–4479. https://doi.org/10.1007/s41870-023-01481-7

    Article  Google Scholar 

  27. Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61

    Article  Google Scholar 

  28. Devore JL (2011) Probability and statistics for engineering and the sciences. Cengage Learning, Boston, MA, pp 508–510

    Google Scholar 

  29. Chicco D, Warrens MJ, Jurman G (2021) The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci. https://doi.org/10.7717/peerj-cs.623.PMC8279135

    Article  Google Scholar 

  30. Ishibashi K (2004) Status of historical seismology in Japan. Ann Geophys 47:339–368

    Google Scholar 

  31. Scordilis E (2005) ‘Globally valid relations converting Ms, mb and MJMA to Mw’, Nato Advanced Research workshop on earthquake monitoring and seismic hazard mitigation in Balkan Countries, Borovetz—Rila Mountain—Bulgaria, 11–17 September 2005. 158–161

  32. Hajian A, Nunnari G, Kimiaefar R (2023) Intelligent methods and motivations to use in volcanology and seismology. In: Intelligent methods with applications in volcanology and seismology. Springer. Cham, pp 1–17. https://doi.org/10.1007/978-3-031-15432-4_1

  33. Olsson R (1986) Analogies between electricity and mechanics with geophysical applications. J Geodyn 5(3–4):353–358

    Article  Google Scholar 

  34. Guglielmi AV, Klain BI (2019) Global magnitude of the earthquakes. arXiv preprint arXiv:1909.00879

  35. Huber F (2018) A logical introduction to probability and induction. New York: Oxford University Press. ISBN 9780190845414

  36. Hosseini K et al (2020) Global mantle structure from multifrequency tomography using P, PP and P-diffracted waves. Geophys J Int Oxf Univ Press (OUP) 220(1):96–141. https://doi.org/10.1093/gji/ggz394

    Article  Google Scholar 

  37. Manzunzu B et al (2019) ‘Towards a homogeneous moment magnitude determination for earthquakes in South Africa: reduction of associated uncertainties. J Afr Earth Sci 173:104051

    Article  Google Scholar 

  38. Joshi A, Vishnu C, Mohan CK (2022) Early detection of earthquake magnitude based on stacked ensemble model. J Asian Earth Sci: X 8:100122. https://doi.org/10.1016/j.jaesx.2022.100122

    Article  Google Scholar 

  39. Yin J et al (2023) Earthquake magnitude with DAS: a transferable data-based scaling relation. Geophys Res Lett Am Geophys Union (AGU) 50(10):1. https://doi.org/10.1029/2023gl103045

    Article  Google Scholar 

  40. Chen D-Y, Wu Y-M, Chin T-L (2017) ‘An empirical evolutionary magnitude estimation for early warning of earthquakes. J Asian Earth Sci 135:190–197. https://doi.org/10.1016/j.jseaes.2016.12.028

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Physics, Faculty of Computer Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran

    Rezvan Esmaeili, Roohollah Kimiaefar, Alireza Hajian & Maryam Hodhodi

  2. Department of Mathematics, Faculty of Computer Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran

    Khosro Soleimani-Chamkhorami

Authors
  1. Rezvan Esmaeili
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Roohollah Kimiaefar
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Alireza Hajian
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Khosro Soleimani-Chamkhorami
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Maryam Hodhodi
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

RE, RK, AH, KSCK, and MH contributed to the design and implementation of the research, to the analysis of the results, and to the writing of the manuscript.

Corresponding author

Correspondence to Roohollah Kimiaefar.

Ethics declarations

Conflict of interest

All authors declare that they have no conflicts of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Esmaeili, R., Kimiaefar, R., Hajian, A. et al. Performance enhancement of deep neural network using fusional data assimilation and divide-and-conquer approach; case study: earthquake magnitude calculation. Neural Comput & Applic 36, 16899–16910 (2024). https://doi.org/10.1007/s00521-024-10002-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-024-10002-x

Keywords