Predicting the Earthquake Magnitude Using the Multilayer Perceptron Neural Network with Two Hidden Layers

Mahmoudi, Jamal; Arjomand, Mohammad; Rezaei, Masoud; Mohammadi, Mohammad Hossein

doi:10.28991/cej-2016-00000008

Cited by 31 publications

(13 citation statements)

References 16 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…10.1029/2019RS006931 fault zones (Kannan, 2014), and an empirical probabilistic model that had been proposed to predict onset and magnitude of an upcoming EQ (Papazachos & Papaioannou, 1993). Several machine learning models are also implemented on past seismic activity data to predict EQ onset, magnitude, or epicenter such as decision trees, random forest, AdaBoost, information network, multiobjective info-fuzzy network, k-nearest neighbors, support vector machine (SVM), artificial neural networks (Asencio-Cortés et al, 2015, 2016Last et al, 2016;Mahmoudi et al, 2016;Moustra et al, 2011) , support vector regressors and hybrid neural networks trained on an EQ catalog (Asim et al, 2018), deep neural networks (Panakkat & Adeli, 2009;Wang et al, 2017), and convolutional neural networks to predict an upcoming EQ with seismic waveforms of length of 100 s Ibrahim et al (2018).…”

Section: Radio Sciencementioning

confidence: 99%

“…Some of the proposed mathematical models can be listed as fault line strain related force models that are investigated to suggest a periodicity in EQ appearances (Bendick & Bilham, 2017), Fibonacci, Lucas, Dual (FDL) numbers that are embedded in the occurrence times of old EQs to predict the upcoming EQ onsets (Boucouvalas et al, 2015), spatial connection model that fits to the EQ occurrence pattern around the fault zones (Kannan, 2014), and an empirical probabilistic model that had been proposed to predict onset and magnitude of an upcoming EQ (Papazachos & Papaioannou, 1993). Several machine learning models are also implemented on past seismic activity data to predict EQ onset, magnitude, or epicenter such as decision trees, random forest, AdaBoost, information network, multiobjective info‐fuzzy network, k ‐nearest neighbors, support vector machine (SVM), artificial neural networks (Asencio‐Cortés et al, 2015, 2016; Last et al, 2016; Mahmoudi et al, 2016; Moustra et al, 2011) , support vector regressors and hybrid neural networks trained on an EQ catalog (Asim et al, 2018), deep neural networks (Panakkat & Adeli, 2009; Wang et al, 2017), and convolutional neural networks to predict an upcoming EQ with seismic waveforms of length of 100 s Ibrahim et al (2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning‐Based Detection of Earthquake Precursors Using Ionospheric Data

Akyol

Arıkan

2020

Radio Science

View full text Add to dashboard Cite

Detection of precursors of strong earthquakes is a challenging research area. Recently, it has been shown that strong earthquakes affect electron distribution in the regional ionosphere with indirectly observable changes in the ionospheric delays of GPS signals. Especially, the total electron content (TEC) estimated from GPS data can be used in the seismic precursor detection for strong earthquakes. Although physical mechanisms are not well understood yet, GPS‐based seismic precursors can be observed days prior to the occurrence of the earthquake. In this study, a novel machine learning‐based technique, EQ‐PD, is proposed for detection of earthquake precursors in near real time based on GPS‐TEC data along with daily geomagnetic indices. The proposed EQ‐PD technique utilizes support vector machine (SVM) classifier to decide whether an observed spatiotemporal anomaly is related to an earthquake precursor or not. The data fed to the classifier are composed of spatiotemporal variability map of a region. Performance of the EQ‐PD technique is demonstrated in a case study over a region covering Italy in between the dates of 1 January 2014 and 30 September 2016. The data are partitioned into three nonoverlapping time periods, that are used for training, validation, and test of detecting precursors of earthquakes with magnitudes above 4 in Richter scale. The EQ‐PD technique is able to detect precursors in 17 out of 21 earthquakes while generating 7 false alarms during the validation period of 266 days and 22 out of 24 earthquakes while generating 13 false alarms during the test period of 282 days.

show abstract

Section: Radio Sciencementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Machine Learning‐Based Detection of Earthquake Precursors Using Ionospheric Data

Akyol

Arıkan

2020

Radio Science

View full text Add to dashboard Cite

show abstract

“…Penelitian [8] telah mengusulkan perceptron multilayer untuk memprediksi besarnya gempa bumi, terdiri dari tiga lapisan utama; lapisan input, lapisan tersembunyi dan lapisan keluaran. Hasil percobaan menunjukkan bahwa jaringan saraf plastik menghasilkan 128 model untuk menentukan model prediksi terbaik.…”

Section: Pendahuluanunclassified

Pengembangan Model Jaringan Syaraf Tiruan untuk Mendeteksi Anomali Satelit LAPAN-TUBSAT

Herawan¹

2019

JEPIN

View full text Add to dashboard Cite

Kasus satelit mengalami anomali seringkali di temukan pada satelit-satelit yang beroperasi pada orbit polar. Namun permasalahan yang muncul adalah kondisi satelit sering berubah-ubah sehingga operator belum bisa mengantisipasi kondisi tersebut. Oleh sebab itu, model deteksi kondisi satelit dapat berperan sebagai early warning operator satelit untuk mempersiapkan strategi yang berkaitan dengan kebijakan preventif terkait pencegahan ketika satelit mengalami kondisi tidak normal. Tujuan penelitian ini adalah menerapkan Jaringan Syaraf Tiruan (JST) bakcpropagation dalam mendeteksi kondisi anomali pada satelit LAPAN-TUBSAT, serta mengetahui tingkat akurasi dari proses deteksi tersebut sehingga diperoleh parameter dan arsitektur jaringan JST terbaik. Proses pembelajaran dan pengujian JST menggunakan data kejadian anomali tahun 2009 sampai 2014. Arsitektur JST yang digunakan adalah jumlah node input 4, dua hidden layer, jumlah node lapisan tersembunyi (hidden neuron) divariasikan pada nilai 5, 10, 15 dan 20. Parameter yang diberikan pada proses pembelajaran antara lain adalah fungsi aktivasi, toleransi galat, jumlah epoch maksimal dan variasi nilai laju pembelajaran (learning rate). Empat parameter input yang digunakan yakni elektron (mep0e1), proton (mep0p1), indeks Kp serta indeks Dst. Hasil penelitian menunjukkan bahwa arsitektur jaringan syaraf terbaik dihasilkan oleh jaringan dengan jumlah input node empat, hidden neuron 20 dan 10, nilai learning rate sebesar 0.05 dengan 306 epoch, menghasilan rata-rata akurasi sebesar 98.13%, serta nilai precision dan recall sebesar 98.21% dan 94.81%.

show abstract

“…Most hydrologic processes exhibit a high degree of temporal and spatial variability, and are further plagued by issues of nonlinearity of physical processes, conflicting spatial and temporal scale, and uncertainty in parameter estimates. Over the past years, artificial intelligence techniques have been frequently used to predict nonlinear problems and achieved good results [2][3][4][5][6]. Also, conjunction with wavelet transform enhances ANN popularity which Wavelet-ANN or wavelet-ANFIS models were successfully hired for nonlinear time series forecasting [7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Development of a PSO-ANN Model for Rainfall-Runoff Response in Basins, Case Study: Karaj Basin

Motahari

Mazandaranizadeh

2017

Civ Eng J

View full text Add to dashboard Cite

Successful daily river flow forecasting is necessary in water resources planning and management. A reliable rainfall-runoff model can provide useful information for water resources planning and management. In this study, particle swarm optimization algorithm (PSO) as a metaheuristic approach is employed to train artificial neural network (ANN). The proposed PSO-ANN model is applied to simulate the rainfall runoff process in Karaj River for one and two days ahead. In this regard, different combinations of the input variables including flow and rainfall time series in previous days have been taken under consideration in order to obtain the best model's performances. To evaluate efficiency of the PSO algorithm in training ANNs, separate ANN models are developed using Levenberg-Marquardt (LM) training algorithm and the results are compared with those of the PSO-ANN models. The comparison reveals superiority of the PSO algorithm than the LM algorithm in training the ANN models. The best model for 1 and 2 days ahead runoff forecasting has R2 of 0.88 and 0.78. Results of this study shows that a reliable prediction of runoff in 1 and 2 days ahead can be achieved using PSO-ANN model. Overall, results of this study revealed that an acceptable prediction of the runoff up to two days ahead can be achieved by applying the PSO-ANN model.

show abstract

Predicting the Earthquake Magnitude Using the Multilayer Perceptron Neural Network with Two Hidden Layers

Cited by 31 publications

References 16 publications

A Machine Learning‐Based Detection of Earthquake Precursors Using Ionospheric Data

A Machine Learning‐Based Detection of Earthquake Precursors Using Ionospheric Data

Pengembangan Model Jaringan Syaraf Tiruan untuk Mendeteksi Anomali Satelit LAPAN-TUBSAT

Development of a PSO-ANN Model for Rainfall-Runoff Response in Basins, Case Study: Karaj Basin

Contact Info

Product

Resources

About