Abstract
The global civil aviation is growing day by which is resulting into more congestion into the air transportation system. Over the past few years, many efforts have been put in the direction to improve the aviation safety and avoid fatal air accidents. Learning from the previous accidents could be crucial to enhance the safety standards and minimise the possibility of such aviation safety events. Hence, this manuscript provides an analysis of time-series-based machine learning models to investigate the impact of aviation accident injuries and fatalities. Time series models are highly capable of predicting aviation accidents due to their statistical association. This study has examined ASRS database containing accident and incident data from 1988 to 2020 by employing time series models such as autoregressive integrated moving average (ARIMA), seasonal ARIMA with an exogenous factor (SARIMAX), deep-learning-based long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), and gated recurrent unit (GRU). Here, MSE, RMSE, and MAE are used as performance indicators. The results proved that the Bi-LSTM prediction was superior compared to the other models. Deep-learning-based analysis helps to bring forward the various hidden patterns along with essential information for accident prevention and reducing the accident probability for improving the aviation safety. Ultimately, overall aviation safety level will enhance by minimising the likelihood of occurrence of unsafe events and aviation management optimise their actions towards safety
Similar content being viewed by others
Availability of Data and Materials
ASRS Dataset [23] is used in this research.
References
Dong T, Yang Q, Ebadi N, Luo XR, Rad P. Identifying incident causal factors to improve aviation transportation safety: proposing a deep learning approach. J Adv Transp. 2021;2021:1–15.
Oster CV Jr, Strong JS, Zorn CK. Analyzing aviation safety: problems, challenges, opportunities. Res Transp Econ. 2013;43(1):148–64.
Janic M. An assessment of risk and safety in civil aviation. J Air Transp Manag. 2000;6(1):43–50.
Harris D. Decision making in aviation. Routledge; 2017.
Shi D, Guan J, Zurada J, Manikas A. A data-mining approach to identification of risk factors in safety management systems. J Manag Inf Syst. 2017;34(4):1054–81.
Tamasi G, Demichela M. Risk assessment techniques for civil aviation security. Reliabil Eng Syst Saf. 2011;96(8):892–9.
Hyndman RJ. Forecasting: an overview. International Encyclopedia of Statistical Science, 2011; 536–9.
Box GE, Jenkins GM, Reinsel GC, Ljung GM. Time series analysis: forecasting and control. John Wiley & Sons; 2015.
Li Y. Analysis and forecast of global civil aviation accidents for the period 1942-2016. Math Prob Eng. 2019; 2019.
Matthews B, Das S, Bhaduri K, Das K, Martin R, Oza N. Discovering anomalous aviation safety events using scalable data mining algorithms. J Aerosp Inf Syst. 2013;10(10):467–75.
Zeng H, Guo J, Zhang H, Ren B, Wu J. Research on aviation safety prediction based on variable selection and lstm. Sensors. 2022;23(1):41.
Subramanian SV, Rao AH. Deep-learning based time series forecasting of go-around incidents in the national airspace system. In: 2018 AIAA Modeling and Simulation Technologies Conference, 2018; p 0424.
Andreoni A, Postorino MN. A multivariate Arima model to forecast air transport demand. In: Proceedings of the Association for European Transport and Contributors, 2006; 1–14.
Ming W, Bao Y, Hu Z, Xiong T. Multistep-ahead air passengers traffic prediction with hybrid Arima-Svms models. Sci World J. 2014; 2014.
Juarez Garcia E, Stephens C, Napoli NJ. Detecting high-risk anomalies in aircraft dynamics through entropic analysis of time series data. In: AIAA AVIATION 2022 Forum, 2022;p 3257.
Calabrese CG, Molesworth BR, Hatfield J, Slavich E. Effects of the federal aviation administration’s compliance program on aircraft incidents and accidents. Transp Res Part A. 2022;163:304–19.
Kong Y, Mahadevan S. Aircraft landing distance prediction: a multistep long short-term memory approach. J Aerosp Inf Syst. 2022;19(5):344–54.
Srinivasan P, Nagarajan V, Mahadevan S. Mining and classifying aviation accident reports. In: AIAA Aviation 2019 Forum, 2019; p. 2938.
Abesamis PPR, de Dios Bulos R, Ching M. Improving aviation incidents using association rule mining algorithm and time series analysis. In: IOP Conference Series: Materials Science and Engineering, vol. 946, 2020; p. 012005. IOP Publishing.
Sun Y, Geng N. Forecasting civil aviation incident rate in china using a combined prediction model. J Adv Transp. 2021;2021:1–9.
Xu S, Chan HK, Zhang T. Forecasting the demand of the aviation industry using hybrid time series Sarima-SVR approach. Transp Res Part E. 2019;122:169–80.
Kanavos A, Kounelis F, Iliadis L, Makris C. Deep learning models for forecasting aviation demand time series. Neural Comput Appl. 2021;33(23):16329–43.
ASRS Database Online - Aviation Safety Reporting System. NASA. https://asrs.arc.nasa.gov/search/database.html
Prabhakaran S. Arima model-complete guide to time series forecasting in python. Machine Learning Plus. 2019. https://www.machinelearningplus.com/time-series/arima-model-time-seriesforecasting-python.
Diebold FX. Elements of forecasting. Citeseer; 1998.
Paolella MS. Linear models and time-series analysis: regression, ANOVA, ARMA and GARCH. John Wiley & Sons; 2018.
Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735–80.
Gers FA, Schmidhuber J, Cummins F. Learning to forget: continual prediction with lstm. Neural Comput. 2000;12(10):2451–71.
Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Netw. 2005;18(5–6):602–10.
Cho K, Van Merriënboer B, Bahdanau D, Bengio Y. On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)
Dey R, Salem FM. Gate-variants of gated recurrent unit (gru) neural networks. In: 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), 2017; pp. 1597–600. IEEE.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
On behalf of all the authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the topical collection “Research Trends in Computational Intelligence” guest edited by Anshul Verma, Pradeepika Verma, Vivek Kumar Singh and S. Karthikeyan.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Monika, Verma, S. & Kumar, P. Generic Deep-Learning-Based Time Series Models for Aviation Accident Analysis and Forecasting. SN COMPUT. SCI. 5, 32 (2024). https://doi.org/10.1007/s42979-023-02353-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-023-02353-4