Neural networks for long-term earthquake prediction using modified meta-learning

Abstract

Neural networks have been successfully applied for modeling time series. However, the results of long-term prediction are not satisfied. In this paper, the modified Meta-Learning is applied to the neural model. The normal Meta-Learning is modified by time-varying learning rates and adding a momentum term to improve convergence speed and robustness property. The stability of the learning process is proven. Finally, two experiments are presented to evaluate the proposed method. The first one shows an improvement in earthquakes prediction in the long-term, and the second one is a classical Benchmark problem. In both experiments, the modified Meta-Learning technique minimizes remarkably the mean square error index.

Keywords

Meta-learning neural networks long-term earthquake prediction

Get full access to this article

View all access options for this article.

References

Chatfield

, The analysis of time series: an introduction, Florida, US: CRC Press, 2004.

Palit

A.K.

and Popovic

, Computational Intelligence in Time Series Forecasting: Theory and Engineering Applications, 2005

Billings

S.A.

, Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains, (2013-07-23).

Mushtaq

, Akram

, Aamir

, Ali

and Zulqarnain

, Neural network techniques for time series prediction: A review, International Journal on Informatics Visualization.

Taieb

S.B.

, Sorjamaa

and Bontempi

, Multiple-output modeling for multi-step-ahead time series forecasting, Neurocomputing.

Clements

M.P.

, Franses

P.H.

and Swanson

N.R.

, Forecasting economic and Financial time-series with non-linear models, International Journal of Forecasting.

Farwick

, Pasquazzo

, Breu

, Schweda

, Voges

and Hanschke

A Meta-Model for Automated Enterprise Architecture Model Maintenance, Proceedings of the 2012 IEEE 16th International Enterprise Distributed Object Computing Conference.

Cui

, Hu

, Weir

J.D.

and Wu

, A recommendation system formeta-modeling: A meta-learning based approach, Expert Systems with Applications 46 (2016), 33–44.

de la Rosa

and Yu

, Randomized algorithms for nonlinear systemidentification with deep learning modification, Information Sciences 364–365 (2016), 197–212.

10.

Gonzalez

and Yu

, Non-linear system modeling using LSTM neuralnetworks, IFAC-PapersOnLine 51(13) (2018), 485–489.

11.

and Li

, Automated Nonlinear System Modeling with MultipleFuzzy Neural Networks and Kernel Smoothing, InternationalJournal of Neural Systems 20(5) (2010), 429–435.

12.

Cui

, Wu

, Hu

, Weir

J.D.

and Chu

, Accuracy vs. robustness: bi-criteria optimizaed ensemble of metamodels, Proceedings of the 2014 Winter Simulation Conference, (2014), 616–627.

13.

Vilalta

and Drissi

, A perspective view and survey ofmeta-learning, Artif Intell Rev 18 (2002a), 77–95.

14.

Biggs

J.B.

, The role of meta-learning in study process, Br JEduc Psychol 55 (1985), 185–212.

15.

Finn

, Abbeel

and Levine

, Model-agnostic metalearning for fast adaptation of deep networks, In International Conference on Machine Learning, 2017, pp. 1126–1135.

16.

Ravi

and Larochelle

, Optimization as a Model for Few-Shot Learning, ICLR, (2017).

17.

Mantovani

, Rossi Alcobaça

, Vanschoren

and deCarvalho

, A meta-learning recommender system for hyperparametertuning: Predicting when tuning improves SVM classifiers, Information Sciences 501 (2019), 193–221.

18.

Gupta

, et al., Meta-Reinforcement Learning of Structured Exploration Strategies, NIPS, 2018.

19.

Lemke

and Bodgan

, Meta-learning for time series forecastingand forecast combination, Neurocomputing 73(10-12) (2010), 2006–2016.

20.

Finn

, Rajeswaran

, Kakade

and Levine

, Online meta-learning, International Conference on Machine Learning (ICML), 2019.

21.

Amasyali

M.F.

and Okan

, Ersoy, A Study of Meta Learning for Regression, (2009).

22.

Lemley

, Bazrafkan

and Corcoran

, Transfer Learning of Temporal Information for Driver Action Classification, MAICS, 2017.

23.

Brazdil

, Giraud-Carrier

and Soares

, Vilalta R Metalearning: applications to data mining, Springer, Berlin, (2009).

24.

Naik

D.K.

and Mammone

R.J.

, Meta-Neural Networks that learn by learning, Proceedings IJCNN International Joint Conference on Neural Networks, 1992.

25.

and Li

, Discrete-time neuro identification without robustmodification, IEE Proc-Control Theory Appl Col 150(3) (2003).

26.

Sontag

E.D.

, Input to State Stability: Basic Concepts and Results, In: P. Nistri, G. Stefani, (eds) Nonlinear and Optimal Control Theory, Lecture Notes in Mathematics, vol. 1932. Springer, Berlin, Heidelberg, 2008.

27.

Box

, Jenkins

and Reinsel

, Time Series Analysis: Forecasting and Control, 4th Ed, Wiley, 2008.

28.

Lim

and Zohren

, Time series forecasting with deep learning: A survey, arXiv preprint arXiv:2004.13408 (2020).

29.

Schoukens

, Suykens

and Ljung

, Wiener-Hammerstein benchmark, 15th IFAC Symposiumon System Identification, Saint-Malo, France, 2009.

30.

Hospedales

T.M.

, Antoniou

and Micaelli

, StorkeyMeta-Learning

A.J.

, Meta-Learning in Neural Networks: A Survey, arXiv:2004.05439 (2020).

31.

and Fildes

, Retail sales forecasting with meta-learning, European Journal of Operational Research 288(1) (2020), 111–128. 10.1016/j.ejor.2020.05.038.

32.

Cybenko

, Aproximation by superposition of sigmoidal activationfunction, Math Control Signals Syst 2 (1989), 857–869.

33.

Narendra

K.S.

and Parthasarathy

, Gradient methods for optimization of dynamical systems containing neural networks, IEEE Transactions of Neural Networks, 1991, pp. 252–262.

34.

Jiang

Z.P.

and Wang

, Input-to-State Stability for Discrete-TimeNonlinear Systems, Automatica 37(2) (2001), 857–869.

35.

Asim

K.M.

, Martínez-Álvarez

, Basit

and Iqbal

, Earthquake magnitude prediction in Hindukush region using machinelearning techniques, Natural Hazards 85(1) (2017), 471–486.

36.

Asencio-Cortés

, Martínez-Álvarez

, Troncoso

and Morales-Esteban

, Medium–large earthquake magnitude prediction in Tokyo with artificial neural networks, Neural Computing andApplications 28(5) (2017), 1043–1055.

37.

Florido

, Aznarte

J.L.

, Morales-Esteban

and Martínez-Álvarez

, Earthquake magnitude prediction based onartificial neural networks: A survey, Croatian Operational Research Review 7(2) (2016), 159–169.

38.

Narayanakumar

and Raja

, A BP artificial neural network modelfor earthquake magnitude prediction in Himalayas, India, Circuits Syst 7(11) (2016), 3456–3468.

39.

Deng

, Three Classes of Deep Learning Architectures and Their Applications: A Tutorial Survey, 2012.

40.

Maya

and Yu

, Short-term prediction of the earthquake through Neural Networks and Meta-Learning, 16th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE19), Mexico City, Mexico, 2019.