Automated design of an interpretable machine learning model for operational coastal wind forecasting

The article considers the problem of designing a system for operational short-term forecasting of wind speed at a specific point on the coast. An automated approach to designing hybrid machine learning models that combine an ensemble of multilayer neural networks and an interpretable system based on fuzzy logic is proposed. The method is based on the automated formation of an ensemble of neural networks and a system based on fuzzy logic using self-configuring evolutionary algorithms, which allows adapting to the features of the input data without manual tuning. After constructing the neural network ensemble, a separate system based on fuzzy logic is formed, learning from its inputs and outputs. This approach allows reproducing the behavior of the neural network model in an interpretable form. Based on experimental testing on a meteorological dataset, the effectiveness of the method is proven, which ensures a balance between the quality of the forecast and the interpretability of the model. It is shown that the constructed interpretable system reproduces the key patterns of the neural network ensemble, while remaining compact and understandable for analysis. The constructed model can be used in decision-making in port services and in organizing coastal events for quick and easy forecasting. The proposed approach as a whole allows obtaining similar models in various situations similar to the one considered.

1. Ratner Yu.B., Fomin V.V., Ivanchik A.M., Ivanchik M.V. System of the Wind Wave Operational Forecast by the Black Sea Marine Forecast Center. Physical Oceanography. 2017;(5):51–59. https://doi.org/10.22449/1573-160X-2017-5-51-59

2. Zelenko A.A., Strukov B.S., Resnyansky Yu.D., Martynov S.L. A System of Wind Wave Forecasting in the World Ocean and Seas Of Russia. Trudy Gosudarstvennogo okeanograficheskogo instituta. 2014;(215):90–101. (In Russ.).

3. Solari G., Repetto M.P., Burlando M., et al. The Wind Forecast for Safety Management of Port Areas. Journal of Wind Engineering and Industrial Aerodynamics. 2012;104–106:266–277. https://doi.org/10.1016/j.jweia.2012.03.029

4. Burlando M., De Gaetano P., Pizzo M., Repetto M.P., Solari G., Tizzi M. Wind Short-Term Forecast in Port Areas. In: Proceedings of the 6th European-African Conference on Wind Engineering (EACWE), 07–11 July 2013, Cambridge, United Kingdom. 2013. P. 6–8.

5. Chu X., Bai W., Sun Yu., Li W., Liu C., Song H. A Machine Learning-Based Method for Wind Fields Forecasting Utilizing GNSS Radio Occultation Data. IEEE Access. 2022;10:30258–30273. https://doi.org/10.1109/ACCESS.2022.3159231

6. Zhang W., Tian M., Hai Sh., et al. Improving the Forecasts of Coastal Wind Speeds in Tianjin, China Based on the WRF Model with Machine Learning Algorithms. Journal of Meteorological Research. 2024;38(3):570–585. https://doi.org/10.1007/s13351-024-3096-z

7. Aksenov S.V., Novosel'tsev V.B. Organizatsiya i ispol'zovanie neironnykh setei (metody i tekhnologii). Tomsk: Izd-vo NTL; 2006. 128 p. (In Russ.).

8. Terano T., Asai K., Sugeno M. Prikladnye nechetkie sistemy. Moscow: Mir; 1993. 368 p. (In Russ.).

9. Rokach L., Maimon O.Z. Data Mining with Decision Trees: Theory and Applications. Singapore: World Scientific Publishing Co. Pte. Ltd.; 2008. 244 p.

10. Semenkin E. Computational Intelligence Algorithm-Based Comprehensive Human Expert and Data-Driven Model Mining for the Control, Optimization and Design of Complicated Systems. International Journal on Information Technologies & Security. 2019;11:63–66.

11. Lipinsky L.V., Semenkin E.S. Application of Genetic Programming Algorithm in Automated Design of Intellectual Information Technologies. Vestnik SibSAU. Aerospace Tehnologies and Control Systems. 2006;(3):22–26. (In Russ.).

12. Koza J.R. Genetic Programming: On the Programming of Computers by Means of Natural Selection. Cambridge: The MIT Press; 1998. 819 p.

13. Al-Helali B., Chen Q., Xue B., Zhang M. Genetic Programming-Based Feature Selection for Symbolic Regression on Incomplete Data. Evolutionary Computation. 2024;1–27. https://doi.org/10.1162/evco_a_00362

14. Gorzałczany M.B., Rudziński F. Time-Series-Dynamics Modelling and Forecasting – An Accurate and Interpretable Genetic-Fuzzy Approach. In: Advances in Fuzzy Logic and Technology 2017: Proceedings of: EUSFLAT-2017 – The 10th Conference of the European Society for Fuzzy Logic and Technology, 11–15 September 2017, Warsaw, Poland; IWIFSGN'2017 – The Sixteenth International Workshop on Intuitionistic Fuzzy Sets and Generalized Nets, 13–15 September 2017, Warsaw, Poland: Volume 2. Cham: Springer; 2018. P. 165–175. https://doi.org/10.1007/978-3-319-66824-6_15

15. Ishibuchi H., Nozaki K., Tanaka H. Distributed Representation of Fuzzy Rules and Its Application to Pattern Classification. Fuzzy Sets and Systems. 1992;52(1):21–32. https://doi.org/10.1016/0165-0114(92)90032-Y

16. Holland J.H. Genetic Algorithms. Scientific American. 1992;267:66–72. https://doi.org/10.1038/scientificamerican0792-66

17. Alam T., Qamar Sh., Dixit A., Benaida M. Genetic Algorithm: Reviews, Implementations, and Applications. International Journal of Engineering Pedagogy. 2020;10(6):57–77. https://doi.org/10.3991/ijep.v10i6.14567

18. Mamdani E.H., Assilian S. An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller. International Journal of Man-Machine Studies. 1975;7(1):1–13. https://doi.org/10.1016/S0020-7373(75)80002-2

19. Sherstnev P.A., Semenkin E.S. Self-Configuring Genetic Programming Algorithms with Success History-Based Adaptation. Siberian Aerospace Journal. 2025;26(1):60–70.

20. Breiman L., Friedman J., Olshen R.A., Stone Ch.J. Classification and Regression Trees. New York: Chapman & Hall/CRC; 1984. 368 p. https://doi.org/10.1201/9781315139470

21. Zakharova O.I., Artyushkina E.S., Kholopov S.V. Derev'ya reshenii i algoritmy ikh postroeniya. Eurasian Scientific Association. 2020;(4–2):97–99. (In Russ.).

22. Karaseva T.S. Self-Configuring Genetic Programming Algorithm for a Cauchy Problem and Variational Problem in Symbolic Form. Proceedings of the Institute for Systems Analysis Russian Academy of Sciences. 2019;69(3):80–90. (In Russ.). https://doi.org/10.14357/20790279190307

23. Mitrofanov S., Semenkin E.S. Decision Tree Pruning Method Using Delayed Sampling. In: 2024 International Conference on Information Technologies (InfoTech), 11–12 September 2024, Sofia, Bulgaria. IEEE; 2024. P. 1–4. https://doi.org/10.1109/InfoTech63258.2024.10701393

24. Storn R., Price K. Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces. Journal of Global Optimization. 1997;11(4):341–359. https://doi.org/10.1023/A:1008202821328

25. Sherstnev P.A. Self-Configuring Evolutionary Algorithms Based Design of Hybrid Interpretable Machine Learning Models. In: Hybrid Methods of Modeling and Optimization in Complex Systems: Proceedings of International Workshop "Hybrid Methods of Modeling and Optimization in Complex Systems" (in the Framework of the Eleventh International Conference on Mathematical Models and Their Applications), 22–24 November 2022, Krasnoyarsk, Russia. European Publisher; 2023. P. 313–321. https://doi.org/10.15405/epct.23021.38

26. Tanabe R., Fukunaga A. Success-History Based Parameter Adaptation for Differential Evolution. In: 2013 IEEE Congress on Evolutionary Computation, 20–23 June 2013, Cancun, Mexico. IEEE; 2013. P. 71–78. https://doi.org/10.1109/CEC.2013.6557555

27. Mann H.B., Whitney D.R. On a Test of Whether One of Two Random Variables Is Stochastically Larger than the Other. Annals of Mathematical Statistics. 1947;18(1):50–60. https://doi.org/10.1214/aoms/1177730491