Automated Aviation Wind Nowcasting: Exploring Feature-Based Machine Learning Methods
Source abstract
Abstract
Wind factors significantly influence air travel, and extreme conditions can cause operational disruptions. Machine learning approaches are emerging as a valuable tool for predicting wind patterns. This research, using Madeira International Airport as a case study, delves into the effectiveness of feature creation and selection for wind nowcasting, focusing on predicting wind speed, direction, and gusts. Data from four sensors provided 56 features to forecast wind conditions over intervals of 2, 10, and 20 min. Five feature selection techniques were analyzed, namely mRMR, PCA, RFECV, GA, and XGBoost. The results indicate that combining new wind features with optimized feature selection can boost prediction accuracy and computational efficiency. A strong spatial correlation was observed among sensors at different locations, suggesting that the spatial-temporal context enhances predictions. The best accuracy for wind speed forecasts yielded a mean absolute percentage error of 0.35%, 0.53%, and 0.63% for the three time intervals, respectively. Wind gust errors were 0.24%, 0.33%, and 0.38%, respectively, while wind direction predictions remained challenging with errors above 100% for all intervals.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Air Traffic Management and Optimization · Aerospace and Aviation Technology · Forecasting Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Exact Sciences and Engineering, University of Madeira, 9020-105 Funchal, Portugal
Interactive Technologies Institute (ITI/LARSyS and ARDITI), 9020-105 Funchal, Portugal
Funding
LARSyS · ARDITI—Agência Regional para o Desenvolvimento da Investigação, Tecnologia e Inovação
References (60)
Show source-provided references
1. A Review of High Impact Weather for Aviation Meteorology10.1007/s00024-019-02168-6 ↗
2. World Meteorological Organization (2018). WMO-No. 8—Guide to Instruments and Methods of Observation (Observing Systems), World Meteorological Organization. [2018th ed.].
3. A hybrid neural network model for short-term wind speed forecasting based on decomposition, multi-learner ensemble, and adaptive multiple error corrections10.1016/j.renene.2020.11.002 ↗
4. Leveraging data from nearby stations to improve short-term wind speed forecasts10.1016/j.energy.2022.125644 ↗
5. Spatio-temporal wind speed forecasting using graph networks and novel Transformer architectures10.1016/j.apenergy.2022.120565 ↗
6. Jain, A., Patel, H., Nagalapatti, L., Gupta, N., Mehta, S., Guttula, S., Mujumdar, S., Afzal, S., Mittal, R.S., and Munigala, V. (2020, January 6–10). Overview and Importance of Data Quality for Machine Learning Tasks. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, New York, NY, USA.10.1145/3394486.3406477 ↗
7. Gupta, N., Mujumdar, S., Patel, H., Masuda, S., Panwar, N., Bandyopadhyay, S., Mehta, S., Guttula, S., Afzal, S., and Mittal, R.S. (2021, January 14–18). Data Quality for Machine Learning Tasks. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, New York, NY, USA.10.1145/3447548.3470817 ↗
8. Kaur, A., Guleria, K., and Trivedi, N.K. (2021, January 4–5). Feature Selection in Machine Learning: Methods and Comparison. Proceedings of the 2021 International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), Greater Noida, India.10.1109/ICACITE51222.2021.9404623 ↗
9. Thomas, R.N., and Gupta, R. (2020, January 22–23). Feature Selection Techniques and its Importance in Machine Learning: A Survey. Proceedings of the 2020 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India.10.1109/SCEECS48394.2020.189 ↗
10. A survey on feature selection methods10.1016/j.compeleceng.2013.11.024 ↗
11. Feature selection in machine learning: A new perspective10.1016/j.neucom.2017.11.077 ↗
12. Feature selection in wind speed prediction systems based on a hybrid coral reefs optimization—Extreme learning machine approach10.1016/j.enconman.2014.06.041 ↗
13. Wind speed prediction using reduced support vector machines with feature selection10.1016/j.neucom.2014.09.090 ↗
14. Feature Selection used for Wind Speed Forecasting with Data Driven Approaches10.25103/jestr.085.17 ↗
15. Short-term wind speed forecasting using empirical mode decomposition and feature selection10.1016/j.renene.2016.05.023 ↗
16. A data-driven multi-model methodology with deep feature selection for short-term wind forecasting10.1016/j.apenergy.2017.01.043 ↗
17. Wind speed forecasting using deep neural network with feature selection10.1016/j.neucom.2019.08.108 ↗
18. Application of hybrid forecast engine based intelligent algorithm and feature selection for wind signal prediction10.1007/s12530-019-09271-y ↗
19. Ultra-short-term power forecast method for the wind farm based on feature selection and temporal convolution network10.1016/j.isatra.2022.01.024 ↗
20. El-Kenawy, E.-S.M., Mirjalili, S., Khodadadi, N., Abdelhamid, A.A., Eid, M.M., El-Said, M., and Ibrahim, A. (2023). Feature selection in wind speed forecasting systems based on meta-heuristic optimization. PLoS ONE, 18.10.1371/journal.pone.0278491 ↗
21. Multivariate wind speed forecasting based on multi-objective feature selection approach and hybrid deep learning model10.1016/j.energy.2022.126100 ↗
22. Nechaj, P., Gaál, L., Bartok, J., Vorobyeva, O., Gera, M., Kelemen, M., and Polishchuk, V. (2019). Monitoring of Low-Level Wind Shear by Ground-based 3D Lidar for Increased Flight Safety, Protection of Human Lives and Health. Int. J. Env. Res. Public Health, 16.10.3390/ijerph16224584 ↗
23. Forecasting Aviation Accidents and Incidents by Combining Occurrence Investigation and Meteorological Data using Machine Learning10.3846/aviation.2023.18641 ↗
24. Belo-Pereira, M., and Santos, J.A. (2020). Air-Traffic Restrictions at the Madeira International Airport Due to Adverse Winds: Links to Synoptic-Scale Patterns and Orographic Effects. Atmosphere, 11.10.3390/atmos11111257 ↗
25. Vortex streets to the lee of Madeira in a kilometre-resolution regional climate model10.5194/wcd-4-189-2023 ↗
26. Short-term wind speed forecasting system using deep learning for wind turbine applications10.11591/ijece.v10i6.pp5779-5784 ↗
27. World Meteorological Organization (2018). WMO-No. 8—Guide to Instruments and Methods of Observation (Measurement of Meteorological Variables), World Meteorological Organization. [2018th ed.].
28. Taha, A., Cosgrave, B., and Mckeever, S. (2022). Using Feature Selection with Machine Learning for Generation of Insurance Insights. Appl. Sci., 12.10.3390/app12063209 ↗
29. UPLIFT10.14778/3551793.3551842 ↗
30. Statistical Postprocessing of Different Variables for Airports in Spain Using Machine Learning
31. Watkins, J. (2023, August 01). An Introduction to the Science of Statistics: From Theory to Implementation. February 2016. Available online: http://perpus.poltekkesjkt2.ac.id/setiadi/index.php?p=show_detail&id=2406.
32. Haslwanter, T. (2022). An Introduction to Statistics with Python, Springer International Publishing.10.1007/978-3-030-97371-1 ↗
33. Machine-learning iterative calculation of entropy for physical systems10.1073/pnas.2017042117 ↗
34. Karaca, Y., and Moonis, M. (2022). Multi-Chaos, Fractal and Multi-Fractional Artificial Intelligence of Different Complex Systems, Elsevier.10.1016/B978-0-323-90032-4.00016-X ↗
35. Jüngel, A. (2016). Entropy Methods for Diffusive Partial Differential Equations, Springer International Publishing.10.1007/978-3-319-34219-1 ↗
36. Delgado-Bonal, A., and Marshak, A. (2019). Approximate Entropy and Sample Entropy: A Comprehensive Tutorial. Entropy, 21.10.3390/e21060541 ↗
37. The Multiscale Entropy Algorithm and Its Variants: A Review10.3390/e17053110 ↗
38. Permutation entropy and its variants for measuring temporal dependence10.1111/anzs.12376 ↗
39. Davalos, A., Jabloun, M., Ravier, P., and Buttelli, O. (2019). 2019 27th European Signal Processing Conference (EUSIPCO), IEEE.
40. Prastyo, P.H., Ardiyanto, I., and Hidayat, R. (2020). 2020 6th International Conference on Science and Technology (ICST), IEEE.
41. A feature extraction- and ranking-based framework for electricity spot price forecasting using a hybrid deep neural network10.1016/j.epsr.2021.107453 ↗
42. mRMRe: An R package for parallelized mRMR ensemble feature selection10.1093/bioinformatics/btt383 ↗
43. Principal component analysis: A review and recent developments10.1098/rsta.2015.0202 ↗
44. Image classification based on principal component analysis optimized generative adversarial networks10.1007/s11042-020-10137-8 ↗
45. Bechini, A., Barcena, J.L.C., Ducange, P., Marcelloni, F., and Renda, A. (2022, January 18–23). Increasing Accuracy and Explainability in Fuzzy Regression Trees: An Experimental Analysis. Proceedings of the 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Padua, Italy.10.1109/FUZZ-IEEE55066.2022.9882604 ↗
46. Investigation into Explainable Regression Trees for Construction Engineering Applications10.1061/(ASCE)CO.1943-7862.0002083 ↗
47. Loh, W.-Y. (2006). Optimality, Institute of Mathematical Statistics.
48. Olson, D.L., and Wu, D. (2017). Regression Tree Models, Springer.10.1007/978-981-10-2543-3_5 ↗
49. A note on the interpretation of tree-based regression models10.1002/bimj.201900195 ↗
50. Towards a simplification of models using regression trees10.1098/rsif.2012.0613 ↗
51. Recursive feature elimination in random forest classification supports nanomaterial grouping10.1016/j.impact.2019.100179 ↗
52. An unsupervised feature selection approach for actionable warning identification10.1016/j.eswa.2023.120152 ↗
53. Chen, X.-W., and Jeong, J.C. (2007). Sixth International Conference on Machine Learning and Applications (ICMLA 2007), IEEE.
54. Accelerating genetic algorithms with GPU computing: A selective overview10.1016/j.cie.2018.12.067 ↗
55. Optimization problems in water distribution systems using Non-dominated Sorting Genetic Algorithm II: An overview10.1016/j.asej.2022.101932 ↗
56. Improving protein-protein interactions prediction accuracy using XGBoost feature selection and stacked ensemble classifier10.1016/j.compbiomed.2020.103899 ↗
57. A CGRU multi-step wind speed forecasting model based on multi-label specific XGBoost feature selection and secondary decomposition10.1016/j.renene.2022.12.124 ↗
58. Song, J., Jin, L., Xie, Y., and Wei, C. (2021, January 20–22). Optimized XGBoost based sparrow search algorithm for short-term load forecasting. Proceedings of the 2021 IEEE International Conference on Computer Science, Artificial Intelligence and Electronic Engineering (CSAIEE), Virtual Conference.10.1109/CSAIEE54046.2021.9543453 ↗
59. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation10.7717/peerj-cs.623 ↗
60. Research of Machine Learning algorithms using K-fold cross validation10.35940/ijeat.F1043.0886S19 ↗