{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:54:14Z","timestamp":1781636054267,"version":"3.54.5"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007480","name":"Universidad de Castilla la Mancha","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007480","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Earth Sci Inform"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine Learning techniques have gained traction in earthquake forecasting, with recent studies reporting exceptionally high accuracy rates. However, concerns regarding the reliability of these models in real-world scenarios persist. This study provides a critical reappraisal of a recently proposed Machine Learning workflow that originally reported &gt;97% accuracy in forecasting seismic events. We replicated the methodology using a new dataset from Tokyo, Japan, to assess its generalizability and robustness. While standard random train-test splits reproduced the originally reported high accuracy (&gt;99%) in this distinct tectonic setting, subsequent analysis revealed this performance to be an artifact of data leakage. When subjected to rigorous time-based validation and walk-forward testing, the model\u2019s predictive performance dropped drastically to near-baseline levels (24%). Furthermore, direct cross-location testing yielded results indistinguishable from random chance (16%), confirming that the model relies on local artifacts rather than physical precursors. Our findings suggest that the promising results often found in the literature may stem from improper handling of seismic data characteristics. We conclude that the advance of ML-based earthquake forecasting requires a fundamental shift towards stricter methodological standards, prioritizing realistic validation protocols and domain-specific rigor over optimistic performance metrics.<\/jats:p>","DOI":"10.1007\/s12145-026-02078-x","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T11:07:11Z","timestamp":1770894431000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Forecasting earthquakes by Machine Learning techniques: lights and shadows"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9213-3238","authenticated-orcid":false,"given":"Jes\u00fas","family":"Jover-Alfaro","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1968-7108","authenticated-orcid":false,"given":"Enrique","family":"Arias-Ant\u00fanez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6599-5684","authenticated-orcid":false,"given":"Jose Antonio","family":"Mateo-Cort\u00e9s","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,12]]},"reference":[{"key":"2078_CR1","doi-asserted-by":"publisher","unstructured":"Aksoy CG, Chupilkin M, Koczan Z et\u00a0al (2024) Unearthing the impact of earthquakes: A review of economic and social consequences. J Policy Anal Manag 44:1450\u20131471. https:\/\/doi.org\/10.1002\/pam.22642","DOI":"10.1002\/pam.22642"},{"issue":"1","key":"2078_CR2","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/s11069-016-2579-3","volume":"85","author":"KM Asim","year":"2017","unstructured":"Asim KM, Mart\u00ednez-\u00c1lvarez F, Basit A et al (2017) Earthquake magnitude prediction in hindukush region using machine learning techniques. Nat Hazards 85(1):471\u2013486. https:\/\/doi.org\/10.1007\/s11069-016-2579-3","journal-title":"Nat Hazards"},{"issue":"7","key":"2078_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0199004","volume":"13","author":"KM Asim","year":"2018","unstructured":"Asim KM, Idris A, Iqbal T et al (2018) Earthquake prediction model using support vector regressor and hybrid neural networks. PLoS ONE 13(7):1\u201322. https:\/\/doi.org\/10.1371\/journal.pone.0199004","journal-title":"PLoS ONE"},{"key":"2078_CR4","doi-asserted-by":"publisher","unstructured":"Beroza GC, Segou M, Mostafa\u00a0Mousavi S (2021) Machine learning and earthquake forecasting\u2013next steps. Nature Communications 12(1):4761. https:\/\/doi.org\/10.1038\/s41467-021-24952-6","DOI":"10.1038\/s41467-021-24952-6"},{"key":"2078_CR5","doi-asserted-by":"publisher","unstructured":"Bird P (2003) An updated digital model of plate boundaries. Geochemistry, Geophysics, Geosystems 4(3). https:\/\/doi.org\/10.1029\/2001GC000252","DOI":"10.1029\/2001GC000252"},{"key":"2078_CR6","doi-asserted-by":"publisher","unstructured":"Chatterjee A, Pennington CN, Trugman DT et\u00a0al (2025) A deep learning-aided workflow for decoding the stress regime of southern nevada. Seismol Res Lett 96(4):2418\u20132430. https:\/\/doi.org\/10.1785\/0220240443","DOI":"10.1785\/0220240443"},{"key":"2078_CR7","doi-asserted-by":"publisher","first-page":"3963","DOI":"10.1007\/s11831-024-10099-2","volume":"31","author":"A Chitkeshwar","year":"2024","unstructured":"Chitkeshwar A (2024) The role of machine learning in earthquake seismology: A review. Archives of Computational Methods in Engineering 31:3963\u2013397. https:\/\/doi.org\/10.1007\/s11831-024-10099-2","journal-title":"Archives of Computational Methods in Engineering"},{"key":"2078_CR8","doi-asserted-by":"publisher","unstructured":"Corbera\u00a0Terrones J, Montalvo\u00a0Olazabal J, Munive\u00a0Mendoza A et\u00a0al (2025) Predicci\u00f3n de sismos en ica usando machine learning. https:\/\/doi.org\/10.13140\/RG.2.2.28496.83204","DOI":"10.13140\/RG.2.2.28496.83204"},{"issue":"1","key":"2078_CR9","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1080\/19942060.2018.1512010","volume":"12","author":"P Hajikhodaverdikhan","year":"2018","unstructured":"Hajikhodaverdikhan P, Nazari M, Mohsenizadeh M et al (2018) Earthquake prediction with meteorological data by particle filter-based support vector regression. Engineering Applications of Computational Fluid Mechanics 12(1):679\u2013688. https:\/\/doi.org\/10.1080\/19942060.2018.1512010","journal-title":"Engineering Applications of Computational Fluid Mechanics"},{"key":"2078_CR10","unstructured":"Jaiswal K (2023) New usgs-fema study highlights economic earthquake risk united states. https:\/\/www.usgs.gov\/news\/national-news-release\/new-usgs-fema-study-highlights-economic-earthquake-risk-united-states, accessed: 2025-11-25"},{"key":"2078_CR11","doi-asserted-by":"publisher","unstructured":"JohnsonPA, Rouet-Leduc B, Pyrak-Nolte LJ et al (2021) Laboratory earthquake forecasting: A machine learning competition. Proc Natl Acad Sci 118(5):e2011362118. https:\/\/doi.org\/10.1073\/pnas.2011362118","DOI":"10.1073\/pnas.2011362118"},{"key":"2078_CR12","doi-asserted-by":"crossref","unstructured":"Kapoor S, Narayanan A (2022) Leakage and the reproducibility crisis in ml-based science. arXiv:2207.07048","DOI":"10.1016\/j.patter.2023.100804"},{"key":"2078_CR13","doi-asserted-by":"publisher","unstructured":"Koehler J, Li W, Faber J et\u00a0al (2023) Testing the Potential of Deep Learning in Earthquake Forecasting. https:\/\/doi.org\/10.48550\/arXiv.2307.01812","DOI":"10.48550\/arXiv.2307.01812"},{"key":"2078_CR14","doi-asserted-by":"publisher","unstructured":"Kroll K, Sherman C (2023) Orion: Operational forecasting of induced seismicity. https:\/\/doi.org\/10.18141\/1958726","DOI":"10.18141\/1958726"},{"key":"2078_CR15","doi-asserted-by":"publisher","unstructured":"MacheS, Chatterjee A, Rajendran K et al (2022) Hilbert\u2013huang transform and energy rate functions for earthquake source characterization-a study from the japan trench. Bull Seismol Soc Am 112(6):2847\u20132858. https:\/\/doi.org\/10.1785\/0120220099","DOI":"10.1785\/0120220099"},{"issue":"7776","key":"2078_CR16","doi-asserted-by":"publisher","first-page":"E1","DOI":"10.1038\/s41586-019-1582-8","volume":"574","author":"A Mignan","year":"2019","unstructured":"Mignan A, Broccardo M (2019) One neuron versus deep learning in aftershock prediction. Nature 574(7776):E1\u2013E3. https:\/\/doi.org\/10.1038\/s41586-019-1582-8","journal-title":"Nature"},{"key":"2078_CR17","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1146\/annurev-earth-071822-100323","volume":"51","author":"SM Mousavi","year":"2023","unstructured":"Mousavi SM, Beroza GC (2023) Machine learning in earthquake seismology. Annu Rev Earth Planet Sci 51:105\u2013120. https:\/\/doi.org\/10.1146\/annurev-earth-071822-100323","journal-title":"Annu Rev Earth Planet Sci"},{"issue":"1","key":"2078_CR18","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1038\/s41467-020-17591-w","volume":"11","author":"SM Mousavi","year":"2020","unstructured":"Mousavi SM, Ellsworth WL, Zhu W et al (2020) Earthquake transformer-an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nat Commun 11(1):3952. https:\/\/doi.org\/10.1038\/s41467-020-17591-w","journal-title":"Nat Commun"},{"key":"2078_CR19","unstructured":"Organization WH (2025) Earthquakes. https:\/\/www.who.int\/health-topics\/earthquakes, accessed: 2025-11-25"},{"key":"2078_CR20","unstructured":"Pandala S, Silva B (2024) lazypredict: Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning. GitHub, https:\/\/github.com\/shankarpandala\/lazypredict, online software"},{"key":"2078_CR21","doi-asserted-by":"publisher","unstructured":"Saad OM, Chen Y, Savvaidis A et\u00a0al (2023) Earthquake forecasting using big data and artificial intelligence: A 30-week real-time case study in china. Bulletin of the Seismological Society of America 113(6):2461\u20132478. https:\/\/doi.org\/10.1785\/0120230031","DOI":"10.1785\/0120230031"},{"issue":"1","key":"2078_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-025-00804-x","volume":"15","author":"R Singh","year":"2025","unstructured":"Singh R, Roy B (2025) Scalable earthquake magnitude prediction using spatio-temporal data and model versioning. Sci Rep 15(1):1\u201321. https:\/\/doi.org\/10.1038\/s41598-025-00804-x","journal-title":"Sci Rep"},{"key":"2078_CR23","doi-asserted-by":"publisher","unstructured":"Styron R, Pagani M (2020) The gem global active faults database. Earthquake Spectra 36(1 (suppl)):160\u2013180. https:\/\/doi.org\/10.1177\/8755293020944182","DOI":"10.1177\/8755293020944182"},{"key":"2078_CR24","doi-asserted-by":"publisher","unstructured":"Tehseen R, Farooq MS, Abid A (2020) Earthquake prediction using expert systems: A systematic mapping study. Sustainability 12(6). https:\/\/doi.org\/10.3390\/su12062420","DOI":"10.3390\/su12062420"},{"key":"2078_CR25","unstructured":"Utsu T (1961) A statistical study on the occurrence of aftershocks. Geophysical magazine 30:521\u2013605. https:\/\/api.semanticscholar.org\/CorpusID:128557592"},{"key":"2078_CR26","doi-asserted-by":"publisher","first-page":"8536","DOI":"10.3390\/app12178536","volume":"12","author":"C Wang","year":"2022","unstructured":"Wang C, Li C, Yong S et al (2022) Time series and non-time series models of earthquake prediction based on aeta data: 16-week real case study. Appl Sci 12:8536. https:\/\/doi.org\/10.3390\/app12178536","journal-title":"Appl Sci"},{"key":"2078_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijdrr.2024.104680","volume":"111","author":"C Wang","year":"2024","unstructured":"Wang C, Engler D, Li X et al (2024) Near-real-time earthquake-induced fatality estimation using crowdsourced data and large-language models. International Journal of Disaster Risk Reduction 111:104680. https:\/\/doi.org\/10.1016\/j.ijdrr.2024.104680","journal-title":"International Journal of Disaster Risk Reduction"},{"issue":"4","key":"2078_CR28","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1785\/0119990114","volume":"90","author":"S Wiemer","year":"2000","unstructured":"Wiemer S, Wyss M (2000) Minimum magnitude of completeness in earthquake catalogs: Examples from alaska, the western united states, and japan. Bull Seismol Soc Am 90(4):859\u2013869. https:\/\/doi.org\/10.1785\/0119990114","journal-title":"Bull Seismol Soc Am"},{"key":"2078_CR29","doi-asserted-by":"publisher","unstructured":"Witten IH, Frank E, Hall MA (eds) (2011) Data Mining: Practical Machine Learning Tools and Techniques (Third Edition), third edition edn. The Morgan Kaufmann Series in Data Management Systems, Morgan Kaufmann, Boston, https:\/\/doi.org\/10.1016\/B978-0-12-374856-0.00023-7","DOI":"10.1016\/B978-0-12-374856-0.00023-7"},{"issue":"2","key":"2078_CR30","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1785\/0120040007","volume":"95","author":"J Woessner","year":"2005","unstructured":"Woessner J, Wiemer S (2005) Assessing the quality of earthquake catalogues: Estimating the magnitude of completeness and its uncertainty. Bull Seismol Soc Am 95(2):684\u2013698. https:\/\/doi.org\/10.1785\/0120040007","journal-title":"Bull Seismol Soc Am"},{"key":"2078_CR31","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.tecto.2017.02.017","volume":"702","author":"TE Yano","year":"2017","unstructured":"Yano TE, Takeda T, Matsubara M et al (2017) Japan unified high-resolution relocated catalog for earthquakes (juice): Crustal seismicity beneath the japanese islands. Tectonophysics 702:19\u201328. https:\/\/doi.org\/10.1016\/j.tecto.2017.02.017","journal-title":"Tectonophysics"},{"key":"2078_CR32","doi-asserted-by":"publisher","unstructured":"Yavas C, Chen L, Kadlec C et al (2024) Improving earthquake prediction accuracy in los angeles with machine learning. Sci Rep 14. https:\/\/doi.org\/10.1038\/s41598-024-76483-x","DOI":"10.1038\/s41598-024-76483-x"},{"key":"2078_CR33","doi-asserted-by":"publisher","unstructured":"Ying X (2019) An Overview of Overfitting and its Solutions. J Phys: Conf Ser 1168(2):022022. https:\/\/doi.org\/10.1088\/1742-6596\/1168\/2\/022022. publisher: IOP Publishing","DOI":"10.1088\/1742-6596\/1168\/2\/022022"},{"issue":"12","key":"2078_CR34","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.1002\/cpe.1519","volume":"22","author":"JD Zechar","year":"2010","unstructured":"Zechar JD, Schorlemmer D, Liukis M et al (2010) The collaboratory for the study of earthquake predictability perspective on computational earthquake science. Concurrency and Computation Practice and Experience 22(12):1836\u20131847. https:\/\/doi.org\/10.1002\/cpe.1519","journal-title":"Concurrency and Computation Practice and Experience"}],"container-title":["Earth Science Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-026-02078-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12145-026-02078-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-026-02078-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:09:52Z","timestamp":1781633392000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12145-026-02078-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2078"],"URL":"https:\/\/doi.org\/10.1007\/s12145-026-02078-x","relation":{},"ISSN":["1865-0473","1865-0481"],"issn-type":[{"value":"1865-0473","type":"print"},{"value":"1865-0481","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"10 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"The authors declare no ethical concerns. This study does not involve human participants or animals.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"24"}}