Early detection of earthquake magnitude based on stacked ensemble model
•Stacked ensemble machine learning model has been developed in this paper.•Feature and model ablation study has been performed in the model.•Prediction error has been calculated using records of various earthquakes.•Magnitude has been calculated for a test earthquake using developed model.•Predictio...
Saved in:
| Published in | Journal of Asian Earth Sciences: X Vol. 8; p. 100122 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
01.12.2022
Elsevier |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | •Stacked ensemble machine learning model has been developed in this paper.•Feature and model ablation study has been performed in the model.•Prediction error has been calculated using records of various earthquakes.•Magnitude has been calculated for a test earthquake using developed model.•Predictions with conventional methods establishes the efficacy of the model.
Anew machine learning model, named, EEWPEnsembleStack has been developed for predicting the magnitude of the earthquake from a few seconds of recorded ground motion after the arrival of the P phase. The testing and training dataset consists of 2360 and 591 strong-motion records from central Japan recorded by the Kyoshin Network. Eight parameters that are well correlated with the magnitude have been used for training and testing of the model. Feature ablation study using several models shows that a minimum mean absolute error of 0.42 has been obtained for the case when the model has been trained by using all parameters rather than by a single parameter. The model ablation study indicates that among all individually trained single models, the minimum error has been obtained for a Decision Tree regression model. However, the error is minimized when all machine learning models have been together utilized in the EEWPEnsembleStack model for the training purposes. The EEWPEnsembleStack model has been used to predict a 6.3 magnitude earthquake by using its 21 records from various stations that lie within 50 to 150 km epicentral distance. The predicted magnitude from the developed model using weighted magnitude prediction is obtained as 6.4, which is close to the actual magnitude. The comparison of the predicted magnitude of this earthquake from the developed model with that predicted by using popular τc and Pd methods clearly indicates the suitability of the developed machine learning model over other conventional models. |
|---|---|
| AbstractList | •Stacked ensemble machine learning model has been developed in this paper.•Feature and model ablation study has been performed in the model.•Prediction error has been calculated using records of various earthquakes.•Magnitude has been calculated for a test earthquake using developed model.•Predictions with conventional methods establishes the efficacy of the model.
Anew machine learning model, named, EEWPEnsembleStack has been developed for predicting the magnitude of the earthquake from a few seconds of recorded ground motion after the arrival of the P phase. The testing and training dataset consists of 2360 and 591 strong-motion records from central Japan recorded by the Kyoshin Network. Eight parameters that are well correlated with the magnitude have been used for training and testing of the model. Feature ablation study using several models shows that a minimum mean absolute error of 0.42 has been obtained for the case when the model has been trained by using all parameters rather than by a single parameter. The model ablation study indicates that among all individually trained single models, the minimum error has been obtained for a Decision Tree regression model. However, the error is minimized when all machine learning models have been together utilized in the EEWPEnsembleStack model for the training purposes. The EEWPEnsembleStack model has been used to predict a 6.3 magnitude earthquake by using its 21 records from various stations that lie within 50 to 150 km epicentral distance. The predicted magnitude from the developed model using weighted magnitude prediction is obtained as 6.4, which is close to the actual magnitude. The comparison of the predicted magnitude of this earthquake from the developed model with that predicted by using popular τc and Pd methods clearly indicates the suitability of the developed machine learning model over other conventional models. A new machine learning model, named, EEWPEnsembleStack has been developed for predicting the magnitude of the earthquake from a few seconds of recorded ground motion after the arrival of the P phase. The testing and training dataset consists of 2360 and 591 strong-motion records from central Japan recorded by the Kyoshin Network. Eight parameters that are well correlated with the magnitude have been used for training and testing of the model. Feature ablation study using several models shows that a minimum mean absolute error of 0.42 has been obtained for the case when the model has been trained by using all parameters rather than by a single parameter. The model ablation study indicates that among all individually trained single models, the minimum error has been obtained for a Decision Tree regression model. However, the error is minimized when all machine learning models have been together utilized in the EEWPEnsembleStack model for the training purposes. The EEWPEnsembleStack model has been used to predict a 6.3 magnitude earthquake by using its 21 records from various stations that lie within 50 to 150 km epicentral distance. The predicted magnitude from the developed model using weighted magnitude prediction is obtained as 6.4, which is close to the actual magnitude. The comparison of the predicted magnitude of this earthquake from the developed model with that predicted by using popular τc and Pd methods clearly indicates the suitability of the developed machine learning model over other conventional models. |
| ArticleNumber | 100122 |
| Author | Vishnu, Chalavadi Joshi, Anushka Mohan, C Krishna |
| Author_xml | – sequence: 1 givenname: Anushka orcidid: 0000-0002-7262-4379 surname: Joshi fullname: Joshi, Anushka email: anushka_j@cs.iitr.ac.in – sequence: 2 givenname: Chalavadi orcidid: 0000-0001-9184-3545 surname: Vishnu fullname: Vishnu, Chalavadi – sequence: 3 givenname: C Krishna surname: Mohan fullname: Mohan, C Krishna |
| BookMark | eNqFkM9OwzAMhyM0JP7tCbj0BTaSNMmSAweExpiExAXOkZu4kNK1kBTE3p6MIoQ4wMmW5e8n-zsik67vkJBTRueMMnXWzBvA9D7nlPM8oYzzPXLIpaEzKhWd_OgPyDSlhlLKtVRa6EOyWkJst4XHAd0Q-q7o6wIhDo8vr_CExQYeujC8eiwqSOiLvJAGcE-5xS7hpmrzTu-xPSH7NbQJp1_1mNxfLe8ur2c3t6v15cXNzAkmhpkUZuFExYR0QmhXL0pjlKa6pKIGkJpxJ0uDpRNKSeZr8GqByDxHVAZVWR6T9Zjre2jscwwbiFvbQ7Cfgz4-2Hx9cC1aUxrBQaEGo4SusZJacaOkq0XlgGHOKscsF_uUItbfeYzanVrb2E-1dqfWjmozZX5RLgywczdECO0_7PnIYlb0FjDa5AJ2Dn2I2X_-IfzJfwBqdJbc |
| CitedBy_id | crossref_primary_10_1109_TGRS_2024_3459425 crossref_primary_10_1109_TGRS_2024_3492023 crossref_primary_10_1007_s00521_024_09891_9 crossref_primary_10_1007_s12145_024_01253_2 crossref_primary_10_1007_s11069_025_07134_1 crossref_primary_10_1785_0120240119 crossref_primary_10_1007_s00521_024_10002_x |
| Cites_doi | 10.1785/gssrl.80.5.727 10.1023/A:1024813612271 10.1785/gssrl.66.6.42 10.5194/nhess-20-921-2020 10.1002/2013GL058580 10.1016/j.asoc.2012.10.014 10.1111/j.2517-6161.1996.tb02080.x 10.1029/2008GL036689 10.1007/s12040-013-0346-3 10.1029/2009GL038678 10.1785/0120130146 10.1007/s00024-015-1114-x 10.1016/j.nrjag.2013.08.001 10.1785/0120150143 10.1785/0220140179 10.1126/sciadv.1700578 10.1029/2008GL035611 10.1785/0220200317 10.1146/annurev.earth.33.092203.122626 10.1029/2008GL035576 10.1785/0120020008 10.1029/2020GL089394 10.1785/gssrl.82.3.394 10.1007/s00024-015-1061-6 10.1785/0120070054 10.1213/ANE.0000000000002864 10.1785/0220170140 10.1190/1.1441433 10.3390/app10093227 10.1029/2006GL027795 10.1785/BSSA0680051521 10.1007/978-94-007-0152-6_12 10.1785/0220170062 10.1111/j.1365-246X.2007.03430.x 10.1126/science.1080912 10.1785/gssrl.80.5.717 10.1038/s41598-020-78046-2 10.1109/ACCESS.2019.2893448 10.1016/j.geog.2017.03.010 10.1785/0120080034 10.1029/2019GL085976 10.3389/feart.2021.653226 10.1016/j.jseaes.2012.04.014 10.1785/gssrl.80.1.57 10.1785/0120010217 10.1029/2005GL025395 10.1785/0220170146 10.1029/2011GL047461 10.1007/s11589-013-0005-4 10.1785/0220210144 10.1785/0120040097 10.1098/rsta.2014.0375 |
| ContentType | Journal Article |
| Copyright | 2022 The Authors |
| Copyright_xml | – notice: 2022 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.jaesx.2022.100122 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2590-0560 |
| ExternalDocumentID | oai_doaj_org_article_93942a6e8a9648feb5862965cf4bca1e 10_1016_j_jaesx_2022_100122 S2590056022000433 |
| GroupedDBID | 0SF 6I. AACTN AAEDW AAFTH AALRI AAXUO ABMAC ADBBV AEXQZ AFTJW AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ BCNDV EBS EJD FDB GROUPED_DOAJ M41 NCXOZ OK1 ROL SSZ 0R~ AAYWO AAYXX ACVFH ADCNI ADVLN AEUPX AFJKZ AFPUW AIGII AKBMS AKYEP APXCP CITATION |
| ID | FETCH-LOGICAL-c414t-5497c4b145c448cf73996808304faa5812c539e3c46651dfad67ee1d2ee69e633 |
| IEDL.DBID | DOA |
| ISSN | 2590-0560 |
| IngestDate | Wed Aug 27 01:28:34 EDT 2025 Thu Apr 24 23:10:02 EDT 2025 Tue Jul 01 04:01:57 EDT 2025 Tue Jul 25 20:59:32 EDT 2023 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Strong motion Magnitude Prediction Machine learning |
| Language | English |
| License | This is an open access article under the CC BY license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c414t-5497c4b145c448cf73996808304faa5812c539e3c46651dfad67ee1d2ee69e633 |
| ORCID | 0000-0002-7262-4379 0000-0001-9184-3545 |
| OpenAccessLink | https://doaj.org/article/93942a6e8a9648feb5862965cf4bca1e |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_93942a6e8a9648feb5862965cf4bca1e crossref_primary_10_1016_j_jaesx_2022_100122 crossref_citationtrail_10_1016_j_jaesx_2022_100122 elsevier_sciencedirect_doi_10_1016_j_jaesx_2022_100122 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2022-12-01 2022-12-00 |
| PublicationDateYYYYMMDD | 2022-12-01 |
| PublicationDate_xml | – month: 12 year: 2022 text: 2022-12-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of Asian Earth Sciences: X |
| PublicationYear | 2022 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | Wei, Seno (b0270) 1998 Aranda, Jimenez, Ibarrola, Alcantar, Aguilar, Inostroza, Maldonado (b0025) 1995; 66 Allen (b0010) 1978; 68 Wu, Y.M., Kanamori, H., Richard, M.A., Hauksson, E, 2007. Determination of earthquake early warning parameters, τ Chen, Liu, Chen, Liu, Zhang, Liu (b0090) 2019; 7 Erdik, Fahjan, Ozel, Alcik, Mert, Gul (b0100) 2003; 1 Zollo, Iannaccone, Lancieri, Cantore, Convertito, Emolo, Festa, Gallovič, Vassallo, Martino (b0320) 2009; 36 Wang, Ni, Chen, Kanamori (b0260) 2009; 36 Kanamori (b0140) 2005; 33 Perol, Gharbi, Denolle (b0200) 2018; 4 Jin, Zhang, Li, Wei, Ma (b0130) 2013; 26 Kuang, Yuan, Zhang (b0150) 2021; 92 X, Zhang, M, Zhang, & X, Tian, (2021). Real-time earthquake early warning with deep learning: Application to the 2016 M 6.0 Central Apennines, Italy Earthquake. Chamoli, Kumar, Chen, Gairola, Jakka, Pandey, Kumar, Rathore (b0075) 2019 Zhu, Li, Song, Wang (b0310) 2021; 9 Satake (b0215) 2015; 373 Takla, Yumoto, Okano, Uozumi, Abe (b0240) 2013; 2 Wang, Wang (b0265) 2020; 10 Sinvhal, Khattri (b0235) 1983; 48 Ionescu, Böse, Wenzel, Marmureanu, Grigore, Marmureanu (b0125) 2007 Chen, Guestrin (b0085) 2016 Wu, Zhao (b0295) 2006; 331 . Zhang, Jin, Wei, Li, Kang, Wang, Huang, Yu (b0300) 2016; 106 Bishop (b0050) 2006 Chen, Jiang, Zhuang (b0080) 2016; 173 Zollo, Lancieri, Nielsen (b0325) 2006; 33 Lin, Wu, Chen (b0165) 2011; 38 Wang, Li, Song (b0255) 2020; 10 Mousavi, Beroza (b0175) 2020; 47 Reddy, Nair (b0205) 2013; 122 Olivieri, Allen, Wurman (b0190) 2008; 98 Allen, Kanamori (b0005) 2003; 300 Hastie, Tibshirani, Friedman (b0120) 2009 Kohler, Cochran, Given, Guiwits, Neuhauser, Henson, Hartog, Bodin, Kress, Thompson (b0145) 2018; 89 Sheen, Park, Chi, Hwang, Lim, Seong, Pak (b0225) 2017; 88 Festa, Zollo, Lancieri (b0105) 2008; 35 Kuyuk, Allen, Brown, Hellweg, Henson, Neuhauser (b0160) 2014; 104 Gunes, F., Wolfinger, R., Tan, P., 2017. Stacked Ensemble Models for Improved Prediction Accuracy. SAS-2017. Wu, Yen, Zhao, Huang, Liang (b0290) 2006; 33 S, Aoi, T, Kunugi, H, Nakamura, H, Fujiwara, 2011. Deployment of new strong motion seismographs of K-NET and KiK-net. In: Akkar et al (Eds.) Earthquake data in engineering seismology, geotechnical, geological, and earthquake engineering 14. Springer, Berlin, pp. 167–186. doi Atefi, Heidari, Mirzaei, Siahkoohi (b0040) 2017; 88 Odaka, Ashiya, Tsukada, Sato, Ohtake, Nozaka (b0185) 2003; 93 Brown, Allen, Richard, Grasso (b0065) 2009; 80 Wakita (b0250) 2013; 72 and Breiman, Friedman, Olshen, Stone (b0060) 1984 Geophys. Res. Lett. Freund, Schapire (b0110) 1997 for southern California. Geophys. J. Int. 170, 711–717. Wu, Kanamori (b0275) 2005; 95 Schober, Boer, Schwarte (b0220) 2018; 126 Wu, Teng (b0285) 2002; 92 Kamigaichi, Saito, Doi, Matsumori, Tsukada, Takeda, Shimoyama, Nakamura, Kiyomoto, Watanabe (b0135) 2009; 80 48, 2020GL089394. Reyes, Morales-Esteban, Martínez-Álvarez (b0210) 2013; 13 Peng, Wu, Wu, Yu, Zhang, Huang (b0195) 2011; 82 Zhu, Li, Song (b0315) 2021; 93 Carranza, Buforn, Zollo (b0070) 2015; 172 Lundberg, Lee (b0170) 2017 Behr, Clinton, Kästli, Cauzzi, Racine, Meier (b0045) 2015; 86 Colombelli, Carotenuto, Elia, Zollo (b0095) 2020; 20 Ochoa, Niño, Vargas (b0180) 2017; 9 Allen, Marano, Earle, Wald (b0015) 2009; 80 Kuyuk, Allen (b0155) 2013; 40 Shieh, Wu, Allen (b0230) 2008; 35 Böse, Hauksson, Solanki, Kanamori, Wu, Heaton (b0055) 2009; 99 Tibshirani (b0245) 1996; 58 Behr (10.1016/j.jaesx.2022.100122_b0045) 2015; 86 Perol (10.1016/j.jaesx.2022.100122_b0200) 2018; 4 Ionescu (10.1016/j.jaesx.2022.100122_b0125) 2007 Wu (10.1016/j.jaesx.2022.100122_b0285) 2002; 92 Chen (10.1016/j.jaesx.2022.100122_b0085) 2016 Zhu (10.1016/j.jaesx.2022.100122_b0315) 2021; 93 Zollo (10.1016/j.jaesx.2022.100122_b0320) 2009; 36 Kuyuk (10.1016/j.jaesx.2022.100122_b0160) 2014; 104 10.1016/j.jaesx.2022.100122_b0020 Odaka (10.1016/j.jaesx.2022.100122_b0185) 2003; 93 Kanamori (10.1016/j.jaesx.2022.100122_b0140) 2005; 33 Shieh (10.1016/j.jaesx.2022.100122_b0230) 2008; 35 Wu (10.1016/j.jaesx.2022.100122_b0295) 2006; 331 Allen (10.1016/j.jaesx.2022.100122_b0010) 1978; 68 Peng (10.1016/j.jaesx.2022.100122_b0195) 2011; 82 Takla (10.1016/j.jaesx.2022.100122_b0240) 2013; 2 Satake (10.1016/j.jaesx.2022.100122_b0215) 2015; 373 Jin (10.1016/j.jaesx.2022.100122_b0130) 2013; 26 Allen (10.1016/j.jaesx.2022.100122_b0005) 2003; 300 10.1016/j.jaesx.2022.100122_b0115 Kuang (10.1016/j.jaesx.2022.100122_b0150) 2021; 92 Colombelli (10.1016/j.jaesx.2022.100122_b0095) 2020; 20 Wu (10.1016/j.jaesx.2022.100122_b0275) 2005; 95 Reddy (10.1016/j.jaesx.2022.100122_b0205) 2013; 122 Carranza (10.1016/j.jaesx.2022.100122_b0070) 2015; 172 10.1016/j.jaesx.2022.100122_b0305 Zollo (10.1016/j.jaesx.2022.100122_b0325) 2006; 33 Schober (10.1016/j.jaesx.2022.100122_b0220) 2018; 126 Freund (10.1016/j.jaesx.2022.100122_b0110) 1997 Erdik (10.1016/j.jaesx.2022.100122_b0100) 2003; 1 Sinvhal (10.1016/j.jaesx.2022.100122_b0235) 1983; 48 Zhu (10.1016/j.jaesx.2022.100122_b0310) 2021; 9 Atefi (10.1016/j.jaesx.2022.100122_b0040) 2017; 88 Böse (10.1016/j.jaesx.2022.100122_b0055) 2009; 99 10.1016/j.jaesx.2022.100122_b0280 Zhang (10.1016/j.jaesx.2022.100122_b0300) 2016; 106 Olivieri (10.1016/j.jaesx.2022.100122_b0190) 2008; 98 Aranda (10.1016/j.jaesx.2022.100122_b0025) 1995; 66 Lin (10.1016/j.jaesx.2022.100122_b0165) 2011; 38 Ochoa (10.1016/j.jaesx.2022.100122_b0180) 2017; 9 Wei (10.1016/j.jaesx.2022.100122_b0270) 1998 Chen (10.1016/j.jaesx.2022.100122_b0080) 2016; 173 Festa (10.1016/j.jaesx.2022.100122_b0105) 2008; 35 Kamigaichi (10.1016/j.jaesx.2022.100122_b0135) 2009; 80 Wakita (10.1016/j.jaesx.2022.100122_b0250) 2013; 72 Sheen (10.1016/j.jaesx.2022.100122_b0225) 2017; 88 Wang (10.1016/j.jaesx.2022.100122_b0260) 2009; 36 Wang (10.1016/j.jaesx.2022.100122_b0255) 2020; 10 Wu (10.1016/j.jaesx.2022.100122_b0290) 2006; 33 Breiman (10.1016/j.jaesx.2022.100122_b0060) 1984 Allen (10.1016/j.jaesx.2022.100122_b0015) 2009; 80 Hastie (10.1016/j.jaesx.2022.100122_b0120) 2009 Brown (10.1016/j.jaesx.2022.100122_b0065) 2009; 80 Chen (10.1016/j.jaesx.2022.100122_b0090) 2019; 7 Lundberg (10.1016/j.jaesx.2022.100122_b0170) 2017 Kohler (10.1016/j.jaesx.2022.100122_b0145) 2018; 89 Tibshirani (10.1016/j.jaesx.2022.100122_b0245) 1996; 58 Wang (10.1016/j.jaesx.2022.100122_b0265) 2020; 10 Bishop (10.1016/j.jaesx.2022.100122_b0050) 2006 Mousavi (10.1016/j.jaesx.2022.100122_b0175) 2020; 47 Chamoli (10.1016/j.jaesx.2022.100122_b0075) 2019 Kuyuk (10.1016/j.jaesx.2022.100122_b0155) 2013; 40 Reyes (10.1016/j.jaesx.2022.100122_b0210) 2013; 13 |
| References_xml | – volume: 95 start-page: 347 year: 2005 end-page: 353 ident: b0275 article-title: Experiment on an onsite early warning method for Taiwan early warning system publication-title: Bull. Seismol. Soc. Am. – volume: 36 year: 2009 ident: b0320 article-title: Earthquake early warning system in southern Italy: methodologies and performance evaluation publication-title: Geophys. Res. Lett. – volume: 126 start-page: 1763 year: 2018 end-page: 1768 ident: b0220 article-title: Correlation Coefficients: appropriate Use and Interpretation publication-title: Anesthesia and Analgesia. – volume: 89 start-page: 99 year: 2018 end-page: 107 ident: b0145 article-title: Earthquake early warning ShakeAlert system: west coast wide production prototype publication-title: Seismol. Res. Lett. – volume: 10 start-page: 3227 year: 2020 ident: b0265 article-title: Application of improved LightGBM model in blood glucose prediction publication-title: Appl. Sci. – volume: 173 start-page: 305 year: 2016 end-page: 319 ident: b0080 article-title: Statistical evaluation of efficiency and possibility of earthquake predictions with gravity field variations and its analytic signal in western China publication-title: Pure. Appl. Geophys. – reference: and – volume: 35 start-page: L22307 year: 2008 ident: b0105 article-title: Earthquake magnitude estimation from early radiated energy publication-title: Geophys. Res. Lett. – volume: 26 start-page: 23 year: 2013 end-page: 31 ident: b0130 article-title: Earthquake magnitude estimation using the τc and Pd method for earthquake early warning systems publication-title: Earthq. Sci. – volume: 331 year: 2006 ident: b0295 article-title: Magnitude estimation using the first three second P-wave amplitude in earthquake early warning publication-title: Geophy. Res. Lett. – volume: 9 year: 2021 ident: b0310 article-title: Magnitude estimation for earthquake early warning using a deep convolutional neural network publication-title: Front. Earth Sci. – volume: 33 year: 2006 ident: b0325 article-title: Earthquake magnitude estimation from peak amplitudes of very early seismic signals on strong motion records publication-title: Geophys. Res. Lett. – volume: 82 start-page: 394 year: 2011 end-page: 403 ident: b0195 article-title: Developing a prototype earthquake early warning system in the Beijing capital region publication-title: Seismol. Res. Lett. – volume: 1 start-page: 157 year: 2003 end-page: 163 ident: b0100 article-title: Istanbul earthquake rapid response and the early warning system publication-title: Bull. Earthq. Eng. – volume: 72 start-page: 75 year: 2013 end-page: 87 ident: b0250 article-title: Geology and tectonics of Japanese islands: a review - the key to understanding the geology of Asia publication-title: J. Asian Earth Sci. – volume: 104 start-page: 162 year: 2014 end-page: 173 ident: b0160 article-title: Designing a network-based earthquake early warning algorithm for California: Elarms-2 publication-title: Bull. Seism. Soc. Am. – volume: 48 start-page: 498 year: 1983 end-page: 1513 ident: b0235 article-title: Application of seismic reflection data to discriminate subsurface lithostratigraphy publication-title: Geophysics. – year: 1984 ident: b0060 article-title: Classification and Regression Trees – volume: 20 start-page: 921 year: 2020 end-page: 931 ident: b0095 article-title: Design and implementation of a mobile device app for network-based earthquake early warning systems (EEWSs): application to the PRESTo EEWS in southern Italy publication-title: Nat. Hazards Earth Syst. Sci. – reference: S, Aoi, T, Kunugi, H, Nakamura, H, Fujiwara, 2011. Deployment of new strong motion seismographs of K-NET and KiK-net. In: Akkar et al (Eds.) Earthquake data in engineering seismology, geotechnical, geological, and earthquake engineering 14. Springer, Berlin, pp. 167–186. doi: – volume: 10 start-page: 21055 year: 2020 ident: b0255 article-title: Threshold-based evolutionary magnitude estimation for an earthquake early warning system in the Sichuan-Yunnan region publication-title: China. Sci. Rep. – year: 2019 ident: b0075 article-title: A prototype earthquake early warning system for northern india publication-title: J. Earthq. Eng. – reference: X, Zhang, M, Zhang, & X, Tian, (2021). – volume: 80 start-page: 727 year: 2009 end-page: 739 ident: b0065 article-title: Testing ElarmS in Japan publication-title: Seismol. Res. Lett. – volume: 98 start-page: 495 year: 2008 end-page: 503 ident: b0190 article-title: The potential for earthquake early warning in Italy using elarmS publication-title: Bul. Seismol. Soc. Am. – volume: 80 start-page: 717 year: 2009 end-page: 726 ident: b0135 article-title: Earthquake early warning in Japan: warning the general public and future prospects publication-title: Seismol. Res. Lett. – volume: 93 start-page: 526 year: 2003 end-page: 532 ident: b0185 article-title: A new method of quickly estimating epicentral distance and magnitude from a single seismic record publication-title: Bull. Seismol. Soc. Am. – volume: 35 year: 2008 ident: b0230 article-title: A comparison of τc and τpmax for magnitude estimation in earthquake early warning publication-title: Geophy. Res. Lett. – volume: 4 year: 2018 ident: b0200 article-title: Convolutional neural network for earthquake detection and location publication-title: Sci. Adv. – volume: 300 start-page: 786 year: 2003 end-page: 789 ident: b0005 article-title: The potential for earthquake early warning in southern California publication-title: Sci. – volume: 58 start-page: 267 year: 1996 end-page: 288 ident: b0245 article-title: Regression shrinkage and selection via the lasso publication-title: J. R. Stat. Soc. Series B (Methodol.) – reference: Real-time earthquake early warning with deep learning: Application to the 2016 M 6.0 Central Apennines, Italy Earthquake. – volume: 47 year: 2020 ident: b0175 article-title: A machine-learning approach for earthquake magnitude estimation publication-title: Geophy. Res. Lett. – volume: 80 start-page: 57 year: 2009 end-page: 62 ident: b0015 article-title: PAGER-CAT: a composite earthquake catalog for calibrating global fatality models publication-title: Seismol. Res. Lett. – volume: 66 start-page: 42 year: 1995 end-page: 53 ident: b0025 article-title: Mexico City seismic alert system publication-title: Seismol. Res. Lett. – year: 1998 ident: b0270 article-title: Determination of the Amurian Plate Motion publication-title: Mantle Dynamics and Plate Interactions in East Asia – start-page: 343 year: 2007 end-page: 349 ident: b0125 article-title: An early warning system for deep Vrancea (Romania) earthquakes publication-title: Earthquake Early Warning Systems – reference: 48, 2020GL089394. – start-page: 785 year: 2016 end-page: 794 ident: b0085 article-title: XGBoost: a Scalable Tree Boosting System. KDD '16 publication-title: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – volume: 122 start-page: 1423 year: 2013 end-page: 1434 ident: b0205 article-title: The efficacy of support vector machines (SVM) in robust determination of earthquake early warning magnitudes in central Japan publication-title: Jour. Earth Syst. Sci. – year: 1997 ident: b0110 article-title: 1997 – volume: 68 start-page: 1521 year: 1978 end-page: 1532 ident: b0010 article-title: Automatic earthquake recognition and timing from single traces publication-title: Bull. Seismol. Soc. Am. – volume: 86 start-page: 830 year: 2015 end-page: 840 ident: b0045 article-title: Anatomy of an earthquake early warning (EEW) alert: Predicting time delays for an end-to-end EEW system publication-title: Seismol. Res. Lett. – volume: 92 start-page: 2008 year: 2002 end-page: 2018 ident: b0285 article-title: A virtual sub-network approach to earthquake early warning publication-title: Bull. Seism. Soc. Am. – start-page: 4768 year: 2017 end-page: 4777 ident: b0170 article-title: A unified approach to interpreting model predictions publication-title: Proceedings of the 31st International Conference on Neural Information Processing Systems – volume: 38 year: 2011 ident: b0165 article-title: Magnitude estimation using initial P-wave amplitude and its spatial distribution in earthquake early warning in Taiwan publication-title: Geophys. Res. Lett. – volume: 93 start-page: 126 year: 2021 end-page: 136 ident: b0315 article-title: Magnitude estimation for earthquake early warning with multiple parameter inputs and a support vector machine publication-title: Seismol. Res. Lett. – volume: 92 start-page: 2245 year: 2021 end-page: 2254 ident: b0150 article-title: Network-based earthquake magnitude determination via deep learning publication-title: Seismol. Res. Lett. – volume: 106 start-page: 755 year: 2016 end-page: 765 ident: b0300 article-title: An earthquake early warning system in Fujian publication-title: China. Bull. Seismol. Soc. Am. – volume: 7 start-page: 13149 year: 2019 end-page: 13158 ident: b0090 article-title: XGBoost-Based algorithm interpretation and application on post-fault transient stability status prediction of power system publication-title: IEEE Access. – volume: 99 start-page: 897 year: 2009 end-page: 905 ident: b0055 article-title: A new trigger criterion for improved real-time performance of onsite earthquake early warning in southern California publication-title: Bull. Seismol. Soc. Am. – reference: Gunes, F., Wolfinger, R., Tan, P., 2017. Stacked Ensemble Models for Improved Prediction Accuracy. SAS-2017. – year: 2006 ident: b0050 publication-title: Pattern Recognition and Machine Learning – volume: 88 start-page: 1527 year: 2017 end-page: 1533 ident: b0040 article-title: Rapid Estimation of Earthquake Magnitude by a New Wavelet-Based Proxy publication-title: Seismol. Res. Lett. – volume: 36 year: 2009 ident: b0260 article-title: Magnitude estimation for early warning applications using the initial part of P waves: a case study on the 2008 Wenchuan sequence publication-title: Geophys. Res. Lett. – volume: 172 start-page: 2435 year: 2015 end-page: 2448 ident: b0070 article-title: Testing the earthquake early-warning parameter correlations in the southern Iberian Peninsula publication-title: Pure Appl. Geophys. – volume: 40 start-page: 6329 year: 2013 end-page: 6333 ident: b0155 article-title: A global approach to provide magnitude estimates for earthquake early warning alerts publication-title: Geophy. Res. Let. – volume: 2 start-page: 185 year: 2013 end-page: 195 ident: b0240 article-title: The signature of the 2011 Tohoku mega earthquake on the geomagnetic field measurements in Japan publication-title: NRIAG. J. Astronomy and Geophys. – volume: 13 start-page: 1314 year: 2013 end-page: 1328 ident: b0210 article-title: Neural networks to predict earthquakes in Chile publication-title: Appl. Soft. Comput. – reference: Geophys. Res. Lett., – reference: . – reference: Wu, Y.M., Kanamori, H., Richard, M.A., Hauksson, E, 2007. Determination of earthquake early warning parameters, τ – volume: 88 start-page: 1491 year: 2017 end-page: 1498 ident: b0225 article-title: The first stage of an earthquake early warning system in South Korea publication-title: Seismol. Res. Lett. – volume: 9 start-page: 34 year: 2017 end-page: 41 ident: b0180 article-title: Fast magnitude determination using a single seismological station record implementing machine learning techniques publication-title: Geod. Geodyn. – volume: 33 start-page: 195 year: 2005 end-page: 214 ident: b0140 article-title: Real-time seismology and earthquake damage mitigation publication-title: Annu. Rev. Earth Planet. Sci. – volume: 373 start-page: 20140375 year: 2015 ident: b0215 article-title: Geological and historical evidence of irregular recurrent earthquakes in Japan publication-title: Phil. Trans. R. Soc. A – volume: 33 year: 2006 ident: b0290 article-title: Magnitude determination using initial P waves: a single-station approach publication-title: Geophys. Res. Lett. – year: 2009 ident: b0120 article-title: The elements of statistical learning – reference: , for southern California. Geophys. J. Int. 170, 711–717. – volume: 80 start-page: 727 year: 2009 ident: 10.1016/j.jaesx.2022.100122_b0065 article-title: Testing ElarmS in Japan publication-title: Seismol. Res. Lett. doi: 10.1785/gssrl.80.5.727 – volume: 1 start-page: 157 year: 2003 ident: 10.1016/j.jaesx.2022.100122_b0100 article-title: Istanbul earthquake rapid response and the early warning system publication-title: Bull. Earthq. Eng. doi: 10.1023/A:1024813612271 – volume: 66 start-page: 42 year: 1995 ident: 10.1016/j.jaesx.2022.100122_b0025 article-title: Mexico City seismic alert system publication-title: Seismol. Res. Lett. doi: 10.1785/gssrl.66.6.42 – volume: 20 start-page: 921 year: 2020 ident: 10.1016/j.jaesx.2022.100122_b0095 article-title: Design and implementation of a mobile device app for network-based earthquake early warning systems (EEWSs): application to the PRESTo EEWS in southern Italy publication-title: Nat. Hazards Earth Syst. Sci. doi: 10.5194/nhess-20-921-2020 – volume: 40 start-page: 6329 year: 2013 ident: 10.1016/j.jaesx.2022.100122_b0155 article-title: A global approach to provide magnitude estimates for earthquake early warning alerts publication-title: Geophy. Res. Let. doi: 10.1002/2013GL058580 – volume: 13 start-page: 1314 year: 2013 ident: 10.1016/j.jaesx.2022.100122_b0210 article-title: Neural networks to predict earthquakes in Chile publication-title: Appl. Soft. Comput. doi: 10.1016/j.asoc.2012.10.014 – volume: 58 start-page: 267 year: 1996 ident: 10.1016/j.jaesx.2022.100122_b0245 article-title: Regression shrinkage and selection via the lasso publication-title: J. R. Stat. Soc. Series B (Methodol.) doi: 10.1111/j.2517-6161.1996.tb02080.x – volume: 36 year: 2009 ident: 10.1016/j.jaesx.2022.100122_b0320 article-title: Earthquake early warning system in southern Italy: methodologies and performance evaluation publication-title: Geophys. Res. Lett. doi: 10.1029/2008GL036689 – volume: 122 start-page: 1423 year: 2013 ident: 10.1016/j.jaesx.2022.100122_b0205 article-title: The efficacy of support vector machines (SVM) in robust determination of earthquake early warning magnitudes in central Japan publication-title: Jour. Earth Syst. Sci. doi: 10.1007/s12040-013-0346-3 – ident: 10.1016/j.jaesx.2022.100122_b0115 – volume: 36 year: 2009 ident: 10.1016/j.jaesx.2022.100122_b0260 article-title: Magnitude estimation for early warning applications using the initial part of P waves: a case study on the 2008 Wenchuan sequence publication-title: Geophys. Res. Lett. doi: 10.1029/2009GL038678 – volume: 104 start-page: 162 year: 2014 ident: 10.1016/j.jaesx.2022.100122_b0160 article-title: Designing a network-based earthquake early warning algorithm for California: Elarms-2 publication-title: Bull. Seism. Soc. Am. doi: 10.1785/0120130146 – year: 2006 ident: 10.1016/j.jaesx.2022.100122_b0050 – volume: 173 start-page: 305 year: 2016 ident: 10.1016/j.jaesx.2022.100122_b0080 article-title: Statistical evaluation of efficiency and possibility of earthquake predictions with gravity field variations and its analytic signal in western China publication-title: Pure. Appl. Geophys. doi: 10.1007/s00024-015-1114-x – volume: 2 start-page: 185 year: 2013 ident: 10.1016/j.jaesx.2022.100122_b0240 article-title: The signature of the 2011 Tohoku mega earthquake on the geomagnetic field measurements in Japan publication-title: NRIAG. J. Astronomy and Geophys. doi: 10.1016/j.nrjag.2013.08.001 – start-page: 785 year: 2016 ident: 10.1016/j.jaesx.2022.100122_b0085 article-title: XGBoost: a Scalable Tree Boosting System. KDD '16 – volume: 106 start-page: 755 year: 2016 ident: 10.1016/j.jaesx.2022.100122_b0300 article-title: An earthquake early warning system in Fujian publication-title: China. Bull. Seismol. Soc. Am. doi: 10.1785/0120150143 – volume: 86 start-page: 830 year: 2015 ident: 10.1016/j.jaesx.2022.100122_b0045 article-title: Anatomy of an earthquake early warning (EEW) alert: Predicting time delays for an end-to-end EEW system publication-title: Seismol. Res. Lett. doi: 10.1785/0220140179 – volume: 4 year: 2018 ident: 10.1016/j.jaesx.2022.100122_b0200 article-title: Convolutional neural network for earthquake detection and location publication-title: Sci. Adv. doi: 10.1126/sciadv.1700578 – volume: 35 year: 2008 ident: 10.1016/j.jaesx.2022.100122_b0230 article-title: A comparison of τc and τpmax for magnitude estimation in earthquake early warning publication-title: Geophy. Res. Lett. doi: 10.1029/2008GL035611 – volume: 92 start-page: 2245 year: 2021 ident: 10.1016/j.jaesx.2022.100122_b0150 article-title: Network-based earthquake magnitude determination via deep learning publication-title: Seismol. Res. Lett. doi: 10.1785/0220200317 – volume: 331 year: 2006 ident: 10.1016/j.jaesx.2022.100122_b0295 article-title: Magnitude estimation using the first three second P-wave amplitude in earthquake early warning publication-title: Geophy. Res. Lett. – volume: 33 start-page: 195 year: 2005 ident: 10.1016/j.jaesx.2022.100122_b0140 article-title: Real-time seismology and earthquake damage mitigation publication-title: Annu. Rev. Earth Planet. Sci. doi: 10.1146/annurev.earth.33.092203.122626 – volume: 35 start-page: L22307 year: 2008 ident: 10.1016/j.jaesx.2022.100122_b0105 article-title: Earthquake magnitude estimation from early radiated energy publication-title: Geophys. Res. Lett. doi: 10.1029/2008GL035576 – volume: 93 start-page: 526 year: 2003 ident: 10.1016/j.jaesx.2022.100122_b0185 article-title: A new method of quickly estimating epicentral distance and magnitude from a single seismic record publication-title: Bull. Seismol. Soc. Am. doi: 10.1785/0120020008 – ident: 10.1016/j.jaesx.2022.100122_b0305 doi: 10.1029/2020GL089394 – volume: 82 start-page: 394 year: 2011 ident: 10.1016/j.jaesx.2022.100122_b0195 article-title: Developing a prototype earthquake early warning system in the Beijing capital region publication-title: Seismol. Res. Lett. doi: 10.1785/gssrl.82.3.394 – volume: 172 start-page: 2435 year: 2015 ident: 10.1016/j.jaesx.2022.100122_b0070 article-title: Testing the earthquake early-warning parameter correlations in the southern Iberian Peninsula publication-title: Pure Appl. Geophys. doi: 10.1007/s00024-015-1061-6 – volume: 98 start-page: 495 year: 2008 ident: 10.1016/j.jaesx.2022.100122_b0190 article-title: The potential for earthquake early warning in Italy using elarmS publication-title: Bul. Seismol. Soc. Am. doi: 10.1785/0120070054 – volume: 126 start-page: 1763 year: 2018 ident: 10.1016/j.jaesx.2022.100122_b0220 article-title: Correlation Coefficients: appropriate Use and Interpretation publication-title: Anesthesia and Analgesia. doi: 10.1213/ANE.0000000000002864 – volume: 89 start-page: 99 year: 2018 ident: 10.1016/j.jaesx.2022.100122_b0145 article-title: Earthquake early warning ShakeAlert system: west coast wide production prototype publication-title: Seismol. Res. Lett. doi: 10.1785/0220170140 – volume: 48 start-page: 498 year: 1983 ident: 10.1016/j.jaesx.2022.100122_b0235 article-title: Application of seismic reflection data to discriminate subsurface lithostratigraphy publication-title: Geophysics. doi: 10.1190/1.1441433 – year: 1984 ident: 10.1016/j.jaesx.2022.100122_b0060 – volume: 10 start-page: 3227 year: 2020 ident: 10.1016/j.jaesx.2022.100122_b0265 article-title: Application of improved LightGBM model in blood glucose prediction publication-title: Appl. Sci. doi: 10.3390/app10093227 – volume: 33 year: 2006 ident: 10.1016/j.jaesx.2022.100122_b0325 article-title: Earthquake magnitude estimation from peak amplitudes of very early seismic signals on strong motion records publication-title: Geophys. Res. Lett. doi: 10.1029/2006GL027795 – volume: 68 start-page: 1521 year: 1978 ident: 10.1016/j.jaesx.2022.100122_b0010 article-title: Automatic earthquake recognition and timing from single traces publication-title: Bull. Seismol. Soc. Am. doi: 10.1785/BSSA0680051521 – year: 2019 ident: 10.1016/j.jaesx.2022.100122_b0075 article-title: A prototype earthquake early warning system for northern india publication-title: J. Earthq. Eng. – ident: 10.1016/j.jaesx.2022.100122_b0020 doi: 10.1007/978-94-007-0152-6_12 – volume: 88 start-page: 1491 year: 2017 ident: 10.1016/j.jaesx.2022.100122_b0225 article-title: The first stage of an earthquake early warning system in South Korea publication-title: Seismol. Res. Lett. doi: 10.1785/0220170062 – ident: 10.1016/j.jaesx.2022.100122_b0280 doi: 10.1111/j.1365-246X.2007.03430.x – volume: 300 start-page: 786 year: 2003 ident: 10.1016/j.jaesx.2022.100122_b0005 article-title: The potential for earthquake early warning in southern California publication-title: Sci. doi: 10.1126/science.1080912 – volume: 80 start-page: 717 year: 2009 ident: 10.1016/j.jaesx.2022.100122_b0135 article-title: Earthquake early warning in Japan: warning the general public and future prospects publication-title: Seismol. Res. Lett. doi: 10.1785/gssrl.80.5.717 – start-page: 4768 year: 2017 ident: 10.1016/j.jaesx.2022.100122_b0170 article-title: A unified approach to interpreting model predictions – volume: 10 start-page: 21055 year: 2020 ident: 10.1016/j.jaesx.2022.100122_b0255 article-title: Threshold-based evolutionary magnitude estimation for an earthquake early warning system in the Sichuan-Yunnan region publication-title: China. Sci. Rep. doi: 10.1038/s41598-020-78046-2 – volume: 7 start-page: 13149 year: 2019 ident: 10.1016/j.jaesx.2022.100122_b0090 article-title: XGBoost-Based algorithm interpretation and application on post-fault transient stability status prediction of power system publication-title: IEEE Access. doi: 10.1109/ACCESS.2019.2893448 – volume: 9 start-page: 34 year: 2017 ident: 10.1016/j.jaesx.2022.100122_b0180 article-title: Fast magnitude determination using a single seismological station record implementing machine learning techniques publication-title: Geod. Geodyn. doi: 10.1016/j.geog.2017.03.010 – volume: 99 start-page: 897 year: 2009 ident: 10.1016/j.jaesx.2022.100122_b0055 article-title: A new trigger criterion for improved real-time performance of onsite earthquake early warning in southern California publication-title: Bull. Seismol. Soc. Am. doi: 10.1785/0120080034 – start-page: 343 year: 2007 ident: 10.1016/j.jaesx.2022.100122_b0125 article-title: An early warning system for deep Vrancea (Romania) earthquakes – volume: 47 year: 2020 ident: 10.1016/j.jaesx.2022.100122_b0175 article-title: A machine-learning approach for earthquake magnitude estimation publication-title: Geophy. Res. Lett. doi: 10.1029/2019GL085976 – volume: 9 year: 2021 ident: 10.1016/j.jaesx.2022.100122_b0310 article-title: Magnitude estimation for earthquake early warning using a deep convolutional neural network publication-title: Front. Earth Sci. doi: 10.3389/feart.2021.653226 – volume: 72 start-page: 75 year: 2013 ident: 10.1016/j.jaesx.2022.100122_b0250 article-title: Geology and tectonics of Japanese islands: a review - the key to understanding the geology of Asia publication-title: J. Asian Earth Sci. doi: 10.1016/j.jseaes.2012.04.014 – year: 2009 ident: 10.1016/j.jaesx.2022.100122_b0120 – volume: 80 start-page: 57 year: 2009 ident: 10.1016/j.jaesx.2022.100122_b0015 article-title: PAGER-CAT: a composite earthquake catalog for calibrating global fatality models publication-title: Seismol. Res. Lett. doi: 10.1785/gssrl.80.1.57 – volume: 92 start-page: 2008 year: 2002 ident: 10.1016/j.jaesx.2022.100122_b0285 article-title: A virtual sub-network approach to earthquake early warning publication-title: Bull. Seism. Soc. Am. doi: 10.1785/0120010217 – volume: 33 year: 2006 ident: 10.1016/j.jaesx.2022.100122_b0290 article-title: Magnitude determination using initial P waves: a single-station approach publication-title: Geophys. Res. Lett. doi: 10.1029/2005GL025395 – volume: 88 start-page: 1527 year: 2017 ident: 10.1016/j.jaesx.2022.100122_b0040 article-title: Rapid Estimation of Earthquake Magnitude by a New Wavelet-Based Proxy publication-title: Seismol. Res. Lett. doi: 10.1785/0220170146 – volume: 38 year: 2011 ident: 10.1016/j.jaesx.2022.100122_b0165 article-title: Magnitude estimation using initial P-wave amplitude and its spatial distribution in earthquake early warning in Taiwan publication-title: Geophys. Res. Lett. doi: 10.1029/2011GL047461 – volume: 26 start-page: 23 year: 2013 ident: 10.1016/j.jaesx.2022.100122_b0130 article-title: Earthquake magnitude estimation using the τc and Pd method for earthquake early warning systems publication-title: Earthq. Sci. doi: 10.1007/s11589-013-0005-4 – volume: 93 start-page: 126 year: 2021 ident: 10.1016/j.jaesx.2022.100122_b0315 article-title: Magnitude estimation for earthquake early warning with multiple parameter inputs and a support vector machine publication-title: Seismol. Res. Lett. doi: 10.1785/0220210144 – year: 1997 ident: 10.1016/j.jaesx.2022.100122_b0110 – volume: 95 start-page: 347 year: 2005 ident: 10.1016/j.jaesx.2022.100122_b0275 article-title: Experiment on an onsite early warning method for Taiwan early warning system publication-title: Bull. Seismol. Soc. Am. doi: 10.1785/0120040097 – volume: 373 start-page: 20140375 year: 2015 ident: 10.1016/j.jaesx.2022.100122_b0215 article-title: Geological and historical evidence of irregular recurrent earthquakes in Japan publication-title: Phil. Trans. R. Soc. A doi: 10.1098/rsta.2014.0375 – year: 1998 ident: 10.1016/j.jaesx.2022.100122_b0270 article-title: Determination of the Amurian Plate Motion |
| SSID | ssj0002856848 |
| Score | 2.4739485 |
| Snippet | •Stacked ensemble machine learning model has been developed in this paper.•Feature and model ablation study has been performed in the model.•Prediction error... A new machine learning model, named, EEWPEnsembleStack has been developed for predicting the magnitude of the earthquake from a few seconds of recorded ground... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Enrichment Source Index Database Publisher |
| StartPage | 100122 |
| SubjectTerms | Machine learning Magnitude Prediction Strong motion |
| Title | Early detection of earthquake magnitude based on stacked ensemble model |
| URI | https://dx.doi.org/10.1016/j.jaesx.2022.100122 https://doaj.org/article/93942a6e8a9648feb5862965cf4bca1e |
| Volume | 8 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA6yJy-iqLi-yMGjxW2azDZHFXUR9KSwt5LHBF21vrrgz3eSdpd60YvXMk3CTNLvm2b4hrEjBaWX2kKmnVKZDIXItHE2C8L7UWnAl6nk_-YWJvfyeqqmvVZfsSaslQduHXeiCy2FASyNBlkGtIo4uAblgrTO5Bi_voR5vWRqln4Z0SJS6yyi9_G2F0YLyaFU3DUz-PlF2aEQSYRIiB-wlNT7e-jUQ5zLdbbWUUV-2i5xg61gvcmukiIx99ikGqqavwZOm7V5eJ-bJ-QvJlYDzT3yCE-ekwHRPzqpnlO-ii_2mWxi85stdn95cXc-ybpmCJmTuWwyyuPGTtpcKkcZlQtjYhaxbUYxksEYRTjtVKGxcBJA5T4YD2PE3AtE0AhFsc0G9WuNO4znCpUDbRSddYIjZ60FYwKBWElsBMyQiYUvKtcphceGFc_VoiRsViUHVtGBVevAITtevvTWCmX8bn4Wnbw0jSrX6QHFvupiX_0V-yGDRYiqjjC0RICGevxt9t3_mH2PrcYh29qWfTZoPuZ4QAylsYdpM34D_qrgsQ |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Early+detection+of+earthquake+magnitude+based+on+stacked+ensemble+model&rft.jtitle=Journal+of+Asian+Earth+Sciences%3A+X&rft.au=Anushka+Joshi&rft.au=Chalavadi+Vishnu&rft.au=C+Krishna+Mohan&rft.date=2022-12-01&rft.pub=Elsevier&rft.issn=2590-0560&rft.eissn=2590-0560&rft.volume=8&rft.spage=100122&rft_id=info:doi/10.1016%2Fj.jaesx.2022.100122&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_93942a6e8a9648feb5862965cf4bca1e |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2590-0560&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2590-0560&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2590-0560&client=summon |