LARGE EARTHQUAKE MAGNITUDE PREDICTION IN TAIWAN BASED ON DEEP LEARNING NEURAL NETWORK

Jipan Huang, Xin'an Wang, Yong Zhao, Chen Xin, Han Xiang

Abstract


In this paper, a deep learning-based method for earthquake prediction is proposed. Large-magnitude earthquakes and tsunamis triggered by earthquakes can kill thousands of people and cause millions of dollars worth of economic losses.
The accurate prediction of large-magnitude earthquakes is a worldwide problem. In recent years, deep learning technology that can automatically extract features from mass data has been applied in image recognition, natural language process-
ing, object recognition, etc., with great success. We attempt to apply deep learning technology to earthquake prediction. We propose a deep learning method for continuous earthquake prediction using historical seismic events. First, we project the
historical seismic events onto a topographic map. Taking Taiwan as an example, we generate the images of the dataset for deep learning and mark a label "1" or "0" depending on whether in the upcoming 30 days a greater than M6 earthquake will
occur. Second, we train our deep leaning network model, using the images of the dataset. Finally, we make earthquake predictions using the trained network model. The result shows that we can get the best result when we predict earthquakes in
the upcoming 30 days using data from the past 120 days. The best R score is 0.289. Although the R score is not high enough, using the past 120 days' historic seismic event to predict the upcoming 30 days' biggest earthquake magnitude can
be regarded as the pattern of Taiwan earthquake because the R score is rather good compared to other datasets. The proposed method performs well without manually designing feature vectors, as in the traditional neural network method. This method can be applied to earthquake prediction in other seismic zones.


Keywords


Large Earthquake Magnitude Prediction;Deep Learning Neural Network;Taiwan;Pattern Recognition

References


Adeli, H., Panakkat, A.: A probabilistic neural network for earthquake magnitude prediction.Neural Networks the Ocial Journal of the International Neural Network Society 22(7),1018{1024 (2009)

Administration, C.E.: More than m2 earthquakes in the country (since 1965). http://www.csi.ac.cn/publish/main/813/5/index.html (2016.

Akhoondzadeh, M.: A mlp neural network as an investigator of tec time series to detect

seismo-ionospheric anomalies. Advances in Space Research 51(11), 2048{2057 (2013)

Allen, C.R.: Responsibilities in earthquake prediction: To the seismological society of america,

delivered in edmonton, alberta, may 12, 1976. Bulletin of the Seismological Society of America (6), 2069{2074 (1976)

Asencio-Cortes, G., Martnez-Alvarez, F., Troncoso, A., Morales-Esteban, A.: Medium{large

earthquake magnitude prediction in tokyo with articial neural networks. Neural Computing& Applications pp. 1{13 (2015)

Camanni, G., Alvarez-Marron, J., Brown, D., Ayala, C., Wu, Y.M., Hsieh, H.H.: The deep structure of south-central taiwan illuminated by seismic tomography and earthquake hypocenter data. Tectonophysics 679, 235{245 (2016)

Ding, X., Zhang, Y., Liu, T., Duan, J.: Deep learning for event-driven stock prediction. In:International Conference on Articial Intelligence (2015)

Florido, E., Mart??nez-??lvarez, F., Morales-Esteban, A., Reyes, J., Aznarte-Mellado, J.L.:Detecting precursory patterns to enhance earthquake prediction in chile. Computers &

Geosciences 76, 112{120 (2015)

Gutenberg, B., Richter, C.F.: Book reviews: Seismicity of the earth and associated phenomena.Science 111 (1950)

Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. Computer Science 3(4),

:pags. 212{223 (2012)

Ikram, A., Qamar, U.: Developing an expert system based on association rules and predicate logic for earthquake prediction. Knowledge-Based Systems 75(C), 87?C103 (2015)

Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S.,Darrell, T.: Cae: Convolutional architecture for fast feature embedding. Eprint Arxiv pp.

{678 (2014)

Krahenbuhl, P., Koltun, V.: Parameter learning and convergent inference for dense random

elds. In: ICML (3), pp. 513{521 (2013)

Krizhevsky, A.: Convolutional deep belief networks on cifar-10 (2012)

Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classication with deep convolutional neural networks. Advances in Neural Information Processing Systems 25(2), 2012 (2012)

Lv, Y., Duan, Y., Kang, W., Li, Z., Wang, F.Y.: Trac

ow prediction with big data: A

deep learning approach. IEEE Transactions on Intelligent Transportation Systems 16(2),1{9 (2015)

Mirrashid, M.: Earthquake magnitude prediction by adaptive neuro-fuzzy inference system

(ans) based on fuzzy c-means algorithm. Natural Hazards 74(3), 1577{1593 (2014)

Morales-Esteban, A., Mart??nez-??lvarez, F., Troncoso, A., Justo, J.L., Rubio-Escudero, C.:

Pattern recognition to forecast seismic time series. Expert Systems with Applications 37(12),8333{8342 (2010)

Panakkat, A., Adeli, H.: Neural network models for earthquake magnitude prediction using

multiple seismicity indicators. International Journal of Neural Systems 17(1), 13{33 (2007)

Petersen, M.D., Cao, T., Campbell, K.W., Frankel, A.D.: Time-independent and timedependent

seismic hazard assessment for the state of california: Uniform california earthquake rupture forecast model 1.0. Seismological Research Letters 78(1), 99{109 (2007)

Shen, Z.K., Jackson, D.D., Yan, Y.K.: Implications of geodetic strain rate for future earthquakes, with a ve-year forecast of m5 earthquakes in southern california. Seismological Research Letters 78(1), 116{120 (2007)

Shi, Y., Zhang, J.L.G.: An evaluation of chinese annual earthquake predictions, 1990{1998

A, 222{231 (2001)

Unterthiner, T., Mayr, A., Klambauer, G., Hochreiter, S.: Toxicity prediction using deep learning. Computer Science (2015)

Wang, K.L., Chen, Q.F., Sun, S.H., Wang, A.D.: Predicting the 1975 haicheng earthquake.Bulletin of the Seismological Society of America 96(3), 757{795 (2006)

Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional

neural networks. In: International Conference on Pattern Recognition, pp. 3304{3308 (2012)

Wang, W.L., Wang, T.T., Su, J.J., Lin, C.H., Seng, C.R., Huang, T.H.: Assessment of damage in mountain tunnels due to the taiwan chi-chi earthquake. Tunnelling & Underground

Space Technology 16(3), 133{150 (2001)

Yan, Y.K., Jackson, D.D., Rong, Y.: A testable ve-year forecast of moderate and large

earthquakes in southern california based on smoothed seismicity. Seismological Research

Letters 78(1), 94{98 (2007)




DOI: http://dx.doi.org/10.14311/NNW.2018.%25x

Refbacks

  • There are currently no refbacks.


Should you encounter an error (non-functional link, missing or misleading information, application crash), please let us know at nnw.ojs@fd.cvut.cz.
Please, do not use the above address for non-OJS-related queries (manuscript status, etc.).
For your convenience we maintain a list of frequently asked questions here. General queries to items not covered by this FAQ shall be directed to the journal editoral office at nnw@fd.cvut.cz.