Aviation risk prediction based on Prophet–LSTM hybrid algorithm

Author:

Su Siyu,Sun Youchao,Zeng Yining,Peng Chong

Abstract

PurposeThe use of aviation incident data to carry out aviation risk prediction is of great significance for improving the initiative of accident prevention and reducing the occurrence of accidents. Because of the nonlinearity and periodicity of incident data, it is challenging to achieve accurate predictions. Therefore, this paper aims to provide a new method for aviation risk prediction with high accuracy.Design/methodology/approachThis paper proposes a hybrid prediction model incorporating Prophet and long short-term memory (LSTM) network. The flight incident data are decomposed using Prophet to extract the feature components. Taking the decomposed time series as input, LSTM is employed for prediction and its output is used as the final prediction result.FindingsThe data of Chinese civil aviation incidents from 2002 to 2021 are used for validation, and Prophet, LSTM and two other typical prediction models are selected for comparison. The experimental results demonstrate that the Prophet–LSTM model is more stable, with higher prediction accuracy and better applicability.Practical implicationsThis study can provide a new idea for aviation risk prediction and a scientific basis for aviation safety management.Originality/valueThe innovation of this work comes from combining Prophet and LSTM to capture the periodic features and temporal dependencies of incidents, effectively improving prediction accuracy.

Publisher

Emerald

Subject

Aerospace Engineering

Reference24 articles.

1. ARIMA models and the box-Jenkins methodology,2016

2. The combination of forecasts,2001

3. CAAC (2022), “Aviation safety information system of CAAC”, [Online], available at: https://safety.caac.gov.cn/index/initpage.act (accessed 27 June 2022).

4. Short – term traffic prediction using Fb-PROPHET and Neural-PROPHET,2022

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. QAR Data Driven Quality Measurement for Aviation Safety;2023 IEEE 5th International Conference on Civil Aviation Safety and Information Technology (ICCASIT);2023-10-11

2. Trend Analysis of Civil Aviation Incidents Based on Causal Inference and Statistical Inference;Aerospace;2023-09-21

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3