Abstract
Earthquakes are natural calamities that are destructive and result in the loss of lives and economic losses globally. It is vital to identify earthquakes at an early stage to reduce the damage caused to the environment and infrastructure. But, traditional monitoring much lacks timely warnings. A study has suggested an innovative framework that utilizes Machine Learning (ML) and Deep Learning (DL) to identify animal behaviour to predict earthquakes. This research proposes a novel framework to identify earthquake precursors using the field of bioacoustics, and ML and DL models. Animal’s audio recordings of historical animal vocalizations were enhanced using data augmentation techniques to increase the audio dataset. The library utilized Librosa for extracting temporal and spectral features from the audio data. The ML algorithms used in the model were XGBoost, Random Forest, and Multi-Layer Perceptron. The DL algorithms used were Recurrent Neural Networks, Long Short-Term Memory, Bidirectional LSTM, and Gated Recurrent Units. The model was trained using a ratio of 80:20. Hyperparameter tuning and early stopping were used to improve the model’s performance. DL methods have shown their potential to go beyond the conventional ML methods in handling temporal dependencies of the sequential audio data. The Bi-LSTM model obtained a test accuracy of 98.87%, and the AUC was found to be close to 1.00, which shows the effectiveness of the model in terms of generalization and robustness to environmental noises. The scalability of the model was tested using unseen datasets. The proposed approach permits a cost-effective early warning system. The approach is more beneficial in areas where there is no advance infrastructure available for seismic activity detection. Future work will be focused on the integration of IoT technology with edge computing technology to improve the scalability of the system.
Similar content being viewed by others
Data availability
The dataset and other materials used in this study is available from the corresponding authors.
References
United States Geological Survey (USGS). Earthquake Hazards Program (Accessed 15 March 2025); https://www.usgs.gov/natural-hazards/earthquake-hazards
EM-DAT. The 2010 Haiti Earthquake: Disaster response and recovery (Accessed 15 March 2025); https://www.emdat.be
United States Geological Survey (USGS. The 2008 Sichuan Earthquake: Seismology and Impact (Accessed 15 March 2025); https://earthquake.usgs.gov
Japan Meteorological Agency. The 2011 Tohoku Earthquake and Tsunami: Lessons from Japan (Accessed 15 March 2025); https://www.jma.go.jp
National Disaster Management Authority, India. Disaster management in India: The 2001 Gujarat earthquake (Accessed 15 March 2025); https://ndma.gov.in
Zhang, M. et al. Brief communication: Effective earthquake early warning systems: Appropriate messaging and public awareness roles. Nat. Hazards Earth Syst. Sci. 21(10), 3243–3250. https://doi.org/10.5194/nhess-21-3243-2021 (2021).
Abdalzaher, M. S., Soliman, M. S. & El-Hady, S. M. Seismic intensity estimation for earthquake early warning using optimized machine learning model. IEEE Trans. Geosci. Remote Sens. 61, 1–11. https://doi.org/10.1109/TGRS.2023.3296520 (2023).
Sadhukhan, B., Chakraborty, S., Mukherjee, S. & Samanta, R. K. Climatic and seismic data-driven deep learning model for earthquake magnitude prediction. Front. Earth Sci. 11, 1082832. https://doi.org/10.3389/feart.2023.1082832 (2023).
Lakshmi, K., Nagesh, Y. & Krishna, M. V. Analysis on predicting earthquakes through an abnormal behavior of animals. Int. J. Sci. Eng. Res. 5(4), 845–857 (2014).
Hayakawa, M. & Yamauchi, H. Unusual animal behavior as a possible candidate of earthquake prediction. Appl. Sci. 14(10), 4317. https://doi.org/10.3390/app14104317 (2024).
bhargava2009earthquake: Earthquake prediction through animal behavior: A review vol. 78, 159–165 (2009)
Lott, D. F., Hart, B. L. & Howell, M. W. Retrospective studies of unusual animal behavior as an earthquake predictor. Geophys. Res. Lett. 8(12), 1203–1206. https://doi.org/10.1029/GL008i012p0120330 (1981).
Convertito, V., Giampaolo, F., Amoroso, O. & Piccialli, F. Deep learning forecasting of large induced earthquakes via precursory signals. Sci. Rep. 14(1), 2964. https://doi.org/10.1038/s41598-024-52935-2 (2024).
Kirschvink, J. L. Earthquake prediction by animals: Evolution and sensory perception. Bull. Seismol. Soc. Am. 90, 312–323. https://doi.org/10.1785/0119980114 (2000).
Fidani, C., Freund, F., Grant, R. Unusual behaviour of cows prior to a large earthquake. In EGU General Assembly conference abstracts 2013–13865. https://doi.org/10.3390/ani4020292 (2013).
Hayakawa, M. Earthquake precursor studies in Japan. In Pre-earthquake processes: A multidisciplinary approach to earthquake prediction studies 7–18 (Wiley, 2018). https://doi.org/10.1002/9781119156949.ch2.
Wei, S. et al. A comparison on data augmentation methods based on deep learning for audio classification. J. Phys.: Conf. Ser. 1453, 012085. https://doi.org/10.1088/1742-6596/1453/1/012085 (2020).
Galkina, A., Grafeeva, N. Machine learning methods for earthquake prediction: A survey. In Proceedings of the Fourth Conference on Software Engineering and Information Management (SEIM-2019), Saint Petersburg, Russia, vol. 13 25 (2019).
Kulkarni, M., Mulay, C., Marathe, S. & Itankar, P. Earthquake prediction using machine learning. Int. J. Adv. Res., Ideas Innov. Techno 7(3), 806 (2021).
VijayaSaraswathi, R. Machine learning-powered earthquake early warning system. Int. J. Innov. Sci. Res. Technol. (IJISRT) 9(6), 1492–1503. https://doi.org/10.38124/ijisrt/IJISRT24JUN1107 (2024).
Liso, G., Fidani, C. & Viotto, A. Unusual animal behaviour before earthquakes and multiple parameter monitoring in Western Piedmont. Earth Sci. 3, 14–25. https://doi.org/10.11648/j.earth (2014).
Sánchez, J. J. Reports of abnormal animal behavior in relation to earth-quakes in Colombia. Boletın Geológíco. 51 (1) (2024)
Garstang, M. & Kelley, M. C. Understanding animal detection of precursor earthquake sounds. Animals 7(9), 66. https://doi.org/10.3390/ani7090066 (2017).
Astuti, W., Aibinu, A., Salami, M. E., Akmelawati, R., Muthalif, A. G. Animal sound activity detection using multi-class support vector machines. In 2011 4th International Conference on Mechatronics (ICOM) 1–5. https://doi.org/10.1109/ICOM.2011.5937122 (2011).
Wikelski, M. et al. Potential short-term earthquake forecasting by farm animal monitoring. Ethology 126(9), 931–941. https://doi.org/10.1111/eth.13078 (2020).
Muhammad, D., Ahmad, I., Khalil, M. I., Khalil, W. & Ahmad, M. O. A generalized deep learning approach to seismic activity prediction. Appl. Sci. 13(3), 1598. https://doi.org/10.3390/app13031598 (2023).
Mukherjee, T., Singh, C., Biswas, P. K. A novel approach for earthquake early warning system design using deep learning techniques. arXiv preprint arXiv:2101.06517https://doi.org/10.48550/arXiv.2101.06517 (2021).
Dascher-Cousineau, K., Shchur, O., Brodsky, E. E. & Günnemann, S. Using deep learning for flexible and scalable earthquake forecasting. J. Geophys. Res.: Solid Earth https://doi.org/10.1029/2023JB026955 (2023).
Tokuda, T., Nakata, R. & Okubo, M. Seismic-phase detection using multiple deep learning models based on local and global waveform representations. Geophys. J. Int. 235(2), 1163–1178. https://doi.org/10.1093/gji/ggad253 (2023).
Murshed, R. U. et al. Real-time seismic intensity prediction using self-supervised contrastive graph neural network for earthquake early warning. arXiv https://doi.org/10.48550/arXiv.2306.14336 (2023).
Yavas, C. E., Chen, L., Kadlec, C. & Ji, Y. Improving earthquake prediction accuracy in Los Angeles with machine learning. Sci. Rep. 14, 27684. https://doi.org/10.1038/s41598-024-76483-x (2024).
Li, W. et al. Earthquake monitoring using deep learning with a case study of the Kahramanmaras Turkey earthquake aftershock sequence. Solid Earth 15(2), 197–213. https://doi.org/10.5194/se-15-197-2024 (2024).
Cambrin, D. R., Stevens, E., Tuia, D., & Lobry, S. QuakeSet: A dataset and low-resource models to monitor earthquakes through Sentinel-1. arXiv. https://doi.org/10.48550/arXiv.2403.18116 (2024).
Zhu, W., Wang, H., Rong, B., Yu, E., Zuzlewski, S., Tepp, G., Taira, T., Marty, J., Husker, A., & Allen, R. M. California earthquake dataset for machine learning and cloud computing (CEED). arXiv. https://doi.org/10.48550/arXiv.2502.11500 (2025).
Zhu, W., Song, J., Wang, H., & Münchmeyer, J. Towards end-to-end earthquake monitoring using a multitask deep learning model. arXiv preprint arXiv:2506.06939. https://doi.org/10.48550/arXiv.2506.06939 (2025).
Kriuk, B., & Kriuk, F. POSEIDON: Physics-optimized seismic energy inference and detection operating network. arXiv. https://doi.org/10.48550/arXiv.2601.02264 (2026).
Ravishan, D., Herath, P., Doyle, E. E. H. & Prasanna, R. Lightweight convolutional neural network for real-time earthquake P-wave detection on edge devices in New Zealand. Sci. Rep. 16(1), 42568. https://doi.org/10.1038/s41598-026-42568-y (2026).
Nagamani, K. et al. Disaster management and earthquake prediction system using machine learning. Int. J. Res. Publ. Eng., Technol. Manag. (IJRPETM) 9(2), 495–499. https://doi.org/10.15662/IJRPETM.2026.0902002 (2026).
Ahmad, N., Ullah, A., & Khan, M. Data quality aware deep learning for reliable seismic event detection. ResearchGate. (2026). https://www.researchgate.net/publication/398021136_Data_Quality_Aware_Deep_Learning_for_Reliable_Seismic_Event_Detection
Jena, R., Pradhan, B., Almazroui, M., Assiri, M. & Park, H.-J. Earthquakeinduced liquefaction hazard mapping at national-scale in Australia using deep learning techniques. Geosci. Front. 14(1), 101460. https://doi.org/10.1016/j.gsf.2022.101460 (2023).
Huang, J., Wang, X., Zhao, Y., Xin, C. & Xiang, H. Large earthquake magnitude prediction in Taiwan based on deep learning neural network. Neural Netw. World https://doi.org/10.14311/NNW.2018.28.009 (2018).
Xie, Y. Deep learning in earthquake engineering: A comprehensive review. ASCE Open Multidiscip. J. Civ. Eng. 3(1), 03125001. https://doi.org/10.48550/arXiv.2405.09021 (2025).
Navarro-Rodríguez, A. et al. Recent advances in early earthquake magnitude estimation by using machine learning algorithms: A systematic review. Appl. Sci. 15(7), 3492. https://doi.org/10.3390/app15073492 (2025).
Kuyuk, H. S. & Susumu, O. Real-time classification of earthquake using deep learning. Procedia Comput. Sci. 140, 298–305. https://doi.org/10.1016/j.procs.2018.10.323 (2018).
Ocak, A. et al. Prediction of damping capacity demand in seismic base isolators via machine learning. Comput. Model. Eng. Sci. 138(3), 2915–2934. https://doi.org/10.32604/cmes.2024.047653 (2024).
Wardhani, T. P. M. et al. Deep learning approach in seismology: Enhancing earthquake forecasting using K-means clustering and LSTM networks. J. Inf. Commun. Technol. 24(1), 29–51. https://doi.org/10.32890/jict2025.24.1.2 (2025).
Murwantara, I. M., Yugopuspito, P. & Hermawan, R. Comparison of machine learning performance for earthquake prediction in Indonesia using 30 years historical data. TELKOMNIKA (Telecommun., Comput., Electron. Control.) 18(3), 1331–1342. https://doi.org/10.12928/TELKOMNIKA.v18i3.14756 (2020).
Kang, S. et al. Deep learning method for post-earthquake damage assessment of frame structures based on time–frequency analysis and CGAN. Earth Syst. Environ. https://doi.org/10.1007/s41748-024-00458-1 (2024).
Asha, V., Devi, P. D. V., Shreya, A., Manisha, N., & Hasini, K. C. Seismic shift: Predicting earthquakes with deep learning. In Proceedings of international conference on computer science and communication engineering (ICCSCE 2025) (eds Katiyar, J. K. et al.) 3005–3017. https://doi.org/10.2991/978-94-6463-858-5_252 (Atlantis Press, 2025).
Wang, Y., Li, X., Wang, Z. & Liu, J. Deep learning for magnitude prediction in earthquake early warning. Georisk Assess. Manag. Risk Eng. Syst. Geohazards https://doi.org/10.1016/j.gr.2022.06.009 (2022).
Terlapu, P. V. Drinkers voice recognition intelligent system: An ensemble stacking machine learning approach. Ann. Data Sci. 12(4), 1157–1187. https://doi.org/10.1007/s40745-024-00559-8 (2025).
Vital, T. P. R., Nayak, J., Naik, B. & Jayaram, D. Probabilistic neural network-based model for identification of Parkinson’s disease by using voice profile and personal data. Arab. J. Sci. Eng. 46(4), 3383–3407. https://doi.org/10.1007/s13369-020-05080-7 (2021).
Vital Terlapu, P. & Prasad Reddy Sadi, R. Real-time speech-based intoxication detection system: Vowel biomarker analysis with artificial neural networks. Int. J. Comput. Digit. Syst. 15(1), 1637–1666. https://doi.org/10.12785/ijcds/1501116 (2024).
Salakapuri, R. et al. Intelligent brain tumor detection using hybrid finetuned deep transfer features and ensemble machine learning algorithms. Sci. Rep. 15(1), 23899. https://doi.org/10.1038/s41598-025-08689-6 (2025).
Zhang, Y., Liu, X. & Wang, J. Forecasting future earthquakes with deep neural networks. Geophys. J. Int. 240(1), 81–95. https://doi.org/10.1093/gji/ggae358 (2025).
Quinteros-Cartaya, C., Diaz, M. & Garcia, R. A deep learning pipeline for large earthquake analysis using GNSS data. Earth Sci. Inf. https://doi.org/10.1007/s12145-025-02023-4 (2025).
Kaftan, I. & Aydin, M. Machine learning applications for earthquake magnitude prediction using seismic datasets. Appl. Sci. 15(20), 10909. https://doi.org/10.3390/app152010909 (2025).
Kaushal, A., Sharma, R. & Singh, P. Earthquake prediction optimization using hybrid RNN–LSTM deep learning model. Soil Dyn. Earthq. Eng. 181, 108358. https://doi.org/10.1016/j.soildyn.2025.109432 (2025).
Yavas, C. E., Karabulut, H. & Ozturk, S. Improving earthquake prediction accuracy using machine learning models and optimized seismic features. Sci. Rep. 14(1), 76483. https://doi.org/10.1038/s41598-024-76483-x (2024).
Zhao, Y., Lv, S. & Liu, P. Advances in earthquake prevention and reduction based on machine learning: A scoping review. IEEE Access 13, 42187–42204. https://doi.org/10.1109/ACCESS.2025.3541289 (2025).
Ansari, A., Rao, K. S., Jain, A. K. & Ansari, A. Deep learning model for predicting tunnel damages and track serviceability under seismic environment. Model. Earth Syst. Environ. 9(1), 1349–1368. https://doi.org/10.1007/s40808-022-01556-7 (2022).
Al Banna, M. H. et al. Application of artificial intelligence in predicting earthquakes: State-of-the-art and future challenges. IEEE Access 8, 192880–192923. https://doi.org/10.1109/ACCESS.2020.3029859 (2020).
Bektaş, N. & Kegyes-Brassai, O. Developing a machine learning-based rapid visual screening method for seismic assessment of existing buildings on a case study data from the 2015 Gorkha, Nepal earthquake. Bull. Earthq. Eng. 23(12), 4981–5019. https://doi.org/10.1007/s10518-024-01924-x (2025).
Turarbek, A. et al. Deep convolutional neural network for accurate prediction of seismic events. Int. J. Adv. Comput. Sci. Appl. https://doi.org/10.14569/IJACSA.2023.0141070 (2023).
Li, S. et al. SeisT: A foundational deep learning model for earthquake monitoring tasks. IEEE Trans. Geosci. Remote Sens. 62, 1–16. https://doi.org/10.1109/TGRS.2024.3371503 (2024).
Gentili, S., Marzocchi, W. & Taroni, M. Forecasting strong subsequent earthquakes in Japan using an improved version of NESTORE machine learning algorithm. arXiv https://doi.org/10.48550/arXiv.2408.12956 (2024).
Ahmed, F., & Bin Harez, J. Earthquake magnitude prediction using machine learning techniques. In 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) 1–6. https://doi.org/10.1109/IATMSI60426.2024.10502770 (IEEE, 2024).
Wang, X., Liu, F., Su, R., Wang, Z., Bai, L., & Ouyang, W. SeisMoLLM: Advancing seismic monitoring via cross-modal transfer with pre-trained large language model. arXiv. https://doi.org/10.48550/arXiv.2502.19960 (2025).
Zhexebay, D. et al. Deep learning for early earthquake detection: Application of convolutional neural networks for P-wave detection. Appl. Sci. 15(7), 3864. https://doi.org/10.3390/app15073864 (2025).
Leema, A. et al. SeismoQuakeGNN: A hybrid framework for spatio-temporal earthquake prediction with transformer-enhanced models. Front. Artif. Intell. https://doi.org/10.3389/frai.2025.1690476 (2025).
Kaushal, A., Gupta, A. K. & Sehgal, V. K. Earthquake prediction optimization using deep learning hybrid RNN-LSTM model for seismicity analysis. Soil Dyn. Earthq. Eng. https://doi.org/10.1016/j.soildyn.2025.109432 (2025).
Yilmaz, M. & Dirikgil, T. A data-driven approach for rapid seismic risk prediction of RC buildings. Bull. Earthq. Eng. https://doi.org/10.1007/s10518-026-02384-1 (2026).
Öztürk, M. Earthquake-induced liquefaction severity index prediction using machine learning techniques. J. Mt. Sci. 22(10), 3769–3789. https://doi.org/10.1007/s11629-025-0023-4 (2025).
Funding
Open access funding provided by Symbiosis International (Deemed University). No specific funding was received for this study.
Author information
Authors and Affiliations
Contributions
Authors Surya Pavan Kumar Gudla, Rakesh Salakapuri and Panduranga Vital Terlapu contributed to Idea Conceptualization, Methodology, Review, Editing, Software, and Writing Original Draft. All authors Rambabu Pemula, Kishore Raju Kalidindi and Koppala Venugopal read and approved the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
This study does not involve human participants, clinical trials, or animal experimentation. All data used in this research were obtained from publicly available sources and handled in accordance with ethical research standards. The study complies with all relevant institutional, national, and international guidelines for ethical research and data usage.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Salakapuri, R., Gudla, S.P.K., Terlapu, P.V. et al. Intelligent earthquake prediction using animal vocal behavior analysis based on machine learning and deep learning approaches. Sci Rep (2026). https://doi.org/10.1038/s41598-026-48690-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-48690-1
