Abstract
This study introduces methodologies for constructing joint probability distribution functions utilizing the Copula function and neural networks, and evaluates their efficacy in marine and civil engineering projects. Through an analytical comparison of both models using a numerical example, it is revealed that the neural network model exhibits superior adaptability to large sample sizes. This adaptability is attributed to the neural network's ability to learn complex relationships within the data, which is especially beneficial when dealing with large datasets. The neural network model also demonstrates higher accuracy in constructing joint probability distribution functions compared to the Copula function model. In marine and civil engineering, the adaptability and accuracy of neural networks are of paramount importance due to the variable and complex nature of weather patterns. A practical engineering application is presented, wherein a joint probabilistic distribution neural network model of wind velocity and rain intensity is established for the Lanzhou–Xinjiang high-speed railroad in China. This model illustrates the promising application of neural networks in engineering projects where weather factors play a critical role. Subsequent to the construction of the joint probability distribution functions, a feature importance analysis is incorporated to quantify the contribution of different weather parameters such as wind velocity and rain intensity to the joint distribution function. This analysis provides an objective assessment of the relative importance of various weather factors and offers data-driven insights that are essential for engineering applications where weather conditions are a significant consideration. The study concludes by highlighting the potential benefits of neural network models in marine and civil engineering, suggesting areas for future exploration.
Similar content being viewed by others
Availability of data and materials
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
References
Bochenek B, Ustrnul Z (2022) Machine learning in weather prediction and climate analyses—applications and perspectives. Atmosphere 13(2):180
Chang Y, Zhao L, Ge YJ (2019) Theoretical and testing investigation of wind-rain coupling loads on some typical bluff bodies. Adv Struct Eng 22(1):156–171
Chatrabgoun O, Karimi R, Daneshkhah A et al (2020) Copula-based probabilistic assessment of intensity and duration of cold episodes: a case study of Malayer vineyard region. Agric Meteorol 295:108150
Cherubini U, Luciano E, Vecchiato W (2004) Copula methods in finance. John Wiley & Sons
Fan WL, Li ZL, Zhang P (2012) Modeling of the joint probabilistic structure of wind direction and speed. Chin Civil Eng J 45(4):81–90
Goda K, Tesfamariam S (2015) Multi-variate seismic demand modelling using copulas: application to non-ductile reinforced concrete frame in Victoria, Canada. Struct Saf 56:39–51
Gou HY, Leng D, Wang HY et al (2021) Joint probability distribution model of wind velocity and rainfall with mixed Copula function. China J Highw Transp 34(2):309–316
Hecht-Nielsen R (1989) Theory of the backpropagation neural network. In: International 1989 joint conference on neural networks, vol 1, pp 593–605
Hosseini Nodeh Z, Babapour Azar A, Khanjani Shiraz R et al (2020) Joint chance constrained shortest path problem with Copula theory. J Comb Optim 40:110–140
Huang CR, Sorger VJ, Miscuglio M et al (2022) Prospects and applications of photonic neural networks. Adv Phys X 7(1):1981155
Ilina O, Ziyadinov V, Klenov N et al (2022) A survey on symmetrical neural network architectures and applications. Symmetry 14(7):1391
Jin HY, Chen XH, Zhong RD et al (2022) Joint probability analysis of water and sediment and predicting sediment load based on copula function. Int J Sedim Res 37(5):639–652
Joe H (1997) Multivariate models and multivariate dependence concepts. CRC Press, New York
Johnstone C, Sulungu ED (2022) Application of neural network in prediction of temperature: a review. Neural Comput Appl 33:11487–11498
Kalajdjieski J et al (2020) Air pollution prediction with multi-modal data and deep neural networks. Remote Sens 12(24):4142. https://doi.org/10.3390/rs12244142
Li JH, Shi W, Zhang LX et al (2021) Wind-wave coupling effect on the dynamic response of a combined wind-wave energy converter. J Mar Sci Eng 9(10):1101. https://doi.org/10.3390/jmse9101101
Li H, Sun L, Yao Q (2023) Correlation analysis based on neural network copula function. Therm Sci 27(3):2081–2089
Luo ZH, Liu CL, Liu S (2020) A novel fault prediction method of wind turbine gearbox based on Pair-Copula construction and BP neural network. IEEE Access 8:91924–91939
Masood H, Zafar A, Ali MU et al (2022) Tracking of a fixed-shape moving object based on the gradient descent method. Sensors 22(3):1098
McNeil AJ, Frey R, Embrechts P (2005) Quantitative risk management: concepts, techniques and tools. Princeton University Press, Princeton
Menna BY, Mesfin HS, Gebrekidan AG et al (2022) Meteorological drought analysis using copula theory for the case of upper Tekeze river basin, Northern Ethiopia. Theor Appl Climatol 149:621–638
Nataf A (1962) Détermination des distributions dont les marges sont données. Comptes Rendus Hebdomadaires Des Séances De Lacadémie Des Sciences 225:42–43
Nelsen RB (2006) An introduction to copulas, 2nd edn. Springer, New York
Nguyen QN, Bedoui R, Majdoub N (2020) Hedging and safe-haven characteristics of Gold against currencies: an investigation based on multivariate dynamic copula theory. Resour Policy 68:101766
Russo A, Raischel F, Lind PG (2013) Air quality prediction using optimal neural networks with stochastic variables. Atmos Environ 79:822–830. https://doi.org/10.1016/j.atmosenv.2013.07.022
Sang B (2021) Application of genetic algorithm and BP neural network in supply chain finance under information sharing. J Comput Appl Math 384:113170
Sklar M (1959) Fonctions de repartition an dimensions et leurs marges. Publication De L’institut De Statistique De l’ Université De Paris 8:229–231
Tang XS, Li DQ, Zhou CB et al (2013) Bivariate distribution models using copulas for reliability analysis. Proc Inst Mech Eng Part O J Risk Reliab 227(5):499–512
Wang J et al (2022) Predicting wind-caused floater intrusion risk for overhead contact lines based on Bayesian neural network with spatiotemporal correlation analysis. Reliab Eng Syst Saf 225:108. https://doi.org/10.1016/j.ress.2022.108603
Weiss R, Karimijafarbigloo S, Roggenbuck D et al (2022) Applications of neural networks in biomedical data analysis. Biomedicines 10(7):1469
Weyn JA, Durran DR, Caruana R (2020) Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere. J Adv Model Earth Syst 12(9):e2020MS002109. https://doi.org/10.1029/2020MS002109
Yang FL, Zhang HJ, Zhou Q et al (2020) Wind-ice joint probability distribution analysis based on Copula function. J Phys Conf Ser 1570:012078
Yang PH, Yu Y, Gu F et al (2022) Prediction and risk assessment of extreme weather events based on Gumbel Copula function. J Funct Spaces 2022:1438373
Yue S (2002) The bivariate lognormal distribution for describing joint statistical properties of a multivariate storm event. Environmetrics 13(8):811–819
Zhao Z et al (2023) A hybrid deep learning framework for air quality prediction with spatial autocorrelation during the COVID-19 pandemic. Sci Rep 13(1):1015. https://doi.org/10.1038/s41598-023-28287-8
Zhuang, L., Xu, A., Wang, X.-L. (2023) A prognostic driven predictive maintenance framework based on Bayesian deep learning. Reliability Engineering & System Safety, 234, 109181. https://doi.org/10.1016/j.ress.2023.109181
Funding
This research was supported by the National Natural Science Foundation of China (Grant No.11962021), the Natural Science Foundation of Inner Mongolia (Grant No.2021MS05020, 2022MS05021) and the Basic scientific research business expenses of universities directly under the autonomous region No. JY20220383.
Author information
Authors and Affiliations
Contributions
YY, HL: designed the study and conducted the neural network model development. YY, DL: performed the comparative analysis and contributed to the literature review, focusing on the Copula function and neural network methodologies. DL: prepared figures 1, 2 and 3 and assisted in data analysis. YY, DL: analyzed the case study of the Lanzhou–Xinjiang high-speed railroad and contributed to the discussion of practical applications. All four authors reviewed, revised, and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflicts of interest regarding the publication of this paper.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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
Yang, Y., Li, D., Li, H. et al. Joint probability distribution of weather factors: a neural network approach for environmental science. Stoch Environ Res Risk Assess 37, 4385–4397 (2023). https://doi.org/10.1007/s00477-023-02513-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-023-02513-1