Abstract
This study focuses on the importance of reliable surface wind forecasts for various sectors, particularly energy production. Traditional numerical weather prediction models are facing limitations and increasing complexity, leading to the development of machine learning models as alternatives or supplements. The research consists of two stages. In the first stage, the ERA5 database is used to evaluate the long-term performance of different combinations of features and two tree-based algorithms for predicting surface wind characteristics (speed and direction) in Cairo. The XGBoost algorithm slightly outperforms the Random Forest algorithm, especially when combined with appropriate feature selection. Even three years after the training period, the results remain very good, with an RMSE of 0.59 m/s, rRMSE of 17%, and R2 of 0.84. The second stage assesses the multivariate approach's ability to forecast wind speed evolution at different time horizons (1–12 h) during a week characterized by significant wind dynamics. The forecasts demonstrate excellent agreement with observations at a 1-h time horizon, with an RMSE of 0.35 m/s, rRMSE of 7.6%, and R2 of 0.98, surpassing or comparable to other literature results. However, as the time lag increases, the RMSE (0.86, 1.14, and 1.51 m/s for 3, 6, and 12 h, respectively) and rRMSE (18.7%, 24.8%, and 32.9% for 3, 6, and 12 h, respectively) also increase, while R2 decreases (0.86, 0.79, and 0.60). Furthermore, the wind variations' amplitude is underestimated. To address this bias, a simple correction method is proposed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Abbreviations
- ACF:
-
AutoCorrelation Function
- ADALINE:
-
ADAptive Linear Neuron
- AI:
-
Artificial Intelligence
- ANN:
-
Artificial Neural Network
- AR:
-
AutoRegressive
- ARIMA:
-
AutoRegressive Integrated Moving Average
- ARMA:
-
AutoRegressive Moving Average
- CFBP:
-
Conjugate Free Back Propagation
- DJF:
-
December, January, February (winter season in Northern Hemisphere)
- ECMWF:
-
European Centre for Medium-Range Weather Forecasts
- EMA:
-
Exponential Moving Average
- ERA5:
-
ECMWF Re-Analysis 5
- GC:
-
Greater Cairo
- GEP:
-
Genetic Expression Programming
- LAMs:
-
Limited Area Models
- LSSVM:
-
Least Squares Support Vector Machine
- MA:
-
Moving Average
- MAE:
-
Mean Absolute Error
- MAPE:
-
Mean Absolute Percentage Error
- ML:
-
Machine Learning
- MLP:
-
Multi-Layer Perceptron
- MSE:
-
Mean Squared Error
- NARX:
-
Nonlinear AutoRegressive with eXogenous input
- NREL:
-
National Renewable Energy Laboratory
- NWP:
-
Numerical Weather Prediction
- NWTC:
-
National Wind Technology Center
- PG:
-
Pressure Gradient Force
- PG_SN: Pressure Gradient:
-
From South To North
- PG_WE: Pressure Gradient:
-
From West To East
- RBF:
-
Radial Basis Function
- RBFNN:
-
Radial Basis Function Neural Network
- RF:
-
Random Forest
- RFE:
-
Recursive Feature Elimination
- RMSE:
-
Root Mean Square Error
- Rrmse:
-
Relative Root Mean Square Error
- SP:
-
Signal Processing
- SOM:
-
Self-Organizing Map
- SVMs:
-
Support Vector Machines
- SVR:
-
Support Vector Regression
- WHO:
-
World Health Organization
- WS:
-
Ind Speed
- XGB:
-
XGBoost (an open-source software library which provides a gradient boosting framework)
References
Agrawal, S. (2021). Train Valid Test Dataset after sorting the data. Towards Data Science. https://miro.medium.com/max/720/1*AxtaQkMAJQe4dM5egTX2Uw.webp
Alexopoulos, E. C. (2010). Introduction to Multivariate Regression Analysis. Hippokratia, 14(Suppl 1), 23–28. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3049417/
Al-Yahyai S, Charabi Y, Gastli A (2010) Review of the use of Numerical Weather Prediction (NWP) Models for wind energy assessment. Renew Sustain Energy Rev 14(9):3192–3198. https://doi.org/10.1016/j.rser.2010.07.001
Boukabara S-A, Krasnopolsky V, Stewart JQ, Maddy E, Shahroudi N, Hoffman RN (2020) Realizing the Benefits of AI across the Numerical Weather Prediction Value Chain. Bull Am Meteor Soc 101(1):29–33. https://doi.org/10.1175/BAMS-D-18-0324.A
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140. https://doi.org/10.1007/BF00058655
Breiman L (2001) Random Forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Cadenas E, Rivera W, Campos-Amezcua R, Heard C (2016) Wind speed prediction using a univariate ARIMA model and a Multivariate NARX model. Energies 9:109. https://doi.org/10.3390/en9020109
Campos RM, Gramcianinov CB, de Camargo R, da Silva Dias PL (2022) Assessment and Calibration of ERA5 Severe Winds in the Atlantic Ocean Using Satellite Data. Remote Sensing 14(19):4918. https://doi.org/10.3390/rs14194918
Carneiro TC, Rocha PAC, Carvalho PCM, Fernández-Ramírez LM (2022) Ridge regression ensemble of machine learning models applied to solar and wind forecasting in Brazil and Spain. Appl Energy 314:118936. https://doi.org/10.1016/j.apenergy.2022.118936
Chen N, Sun H, Zhang Q, Li S (2022) A Short-Term Wind Speed Forecasting Model Based on EMD/CEEMD and ARIMA-SVM Algorithms. Appl Sci 12(12):6085. https://doi.org/10.3390/app12126085
Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
Deris AM, Zain AM, Sallehuddin R (2011) Overview of Support Vector Machine in Modeling Machining Performances. Procedia Engineering 24:308–312. https://doi.org/10.1016/j.proeng.2011.11.2647
Dhakal R, Sedai A, Pol S, Parameswaran S, Nejat A, Moussa H (2022) A Novel Hybrid Method for Short-Term Wind Speed Prediction Based on Wind Probability Distribution Function and Machine Learning Models. Appl Sci 12(18):9038. https://doi.org/10.3390/app12189038
Dhiman HS, and Deb D (2020) A Review of Wind Speed and Wind Power Forecasting Techniques (arXiv:2009.02279). arXiv. http://arxiv.org/abs/2009.02279
Ebert E, Brown B, Göber M, Haiden T, Mittermaier M, Nurmi P, Wilson L, Jackson S, Johnston P, Schuster D (2018) The WMO Challenge to Develop and Demonstrate the Best New User-Oriented Forecast Verification Metric. Meteorol Z 27(6):435–440. https://doi.org/10.1127/metz/2018/0892
El-Metwally M, Alfaro SC, Abdel Wahab M, Chatenet B (2008) Aerosol characteristics over urban Cairo: Seasonal variations as retrieved from Sun photometer measurements. J Geophys Res Atmosp. https://doi.org/10.1029/2008JD009834
Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann Stat 29(5):1189–1232. https://doi.org/10.1214/aos/1013203451
Ganguly K (2017) Acquire and Prepare the Ingredients - Your Data. In R data analysis cookbook - second edition (p. 138). essay, Packt Publishing
Ghorbani MA, Khatibi R, FazeliFard MH, Naghipour L, Makarynskyy O (2016) Short-term wind speed predictions with machine learning techniques. Meteorol Atmos Phys 128(1):57–72. https://doi.org/10.1007/s00703-015-0398-9
Gultepe I, Tardif R, Michaelides SC, Cermak J, Bott A, Bendix J, Müller MD, Pagowski M, Hansen B, Ellrod G, Jacobs W, Toth G, Cober SG (2007) Fog Research: A Review of Past Achievements and Future Perspectives. Pure Appl Geophys 164(6):1121–1159. https://doi.org/10.1007/s00024-007-0211-x
Hair JF, Black WC, Babin BJ, Anderson RE (2009) Multivariate Data Analysis, 7th edn. Pearson, New York
Hamid N, Wibowo WC (2018) Wind Speed Forecasting Using Multivariate Time-Series Radial Basis Function Neural Network. Int Conf Adv Comp Sci Informat Syst (ICACSIS) 2018:423–428. https://doi.org/10.1109/ICACSIS.2018.8618223
Han Y, Mi L, Shen L, Cai CS, Liu Y, Li K, Xu G (2022) A short-term wind speed prediction method utilizing novel hybrid deep learning algorithms to correct numerical weather forecasting. Appl Energy 312:118777. https://doi.org/10.1016/j.apenergy.2022.118777
Hersbach H, Bell B, Berrisford P, Hirahara S, Horányi A, Muñoz-Sabater J, Nicolas J, Peubey C, Radu R, Schepers D, Simmons A, Soci C, Abdalla S, Abellan X, Balsamo G, Bechtold P, Biavati G, Bidlot J, Bonavita M, Thépaut J-N (2020) The ERA5 global reanalysis. Quart J Royal Meteorol Soc 146(730):1999–2049. https://doi.org/10.1002/qj.3803
Ho, T. K. (1995). Random decision forests. Proceedings of 3rd International Conference on Document Analysis and Recognition, 1, 278–282 vol.1. https://doi.org/10.1109/ICDAR.1995.598994
Holttinen H, Kiviluoma J, Robitaille A, Cutululis NA, and Orths A (2017) Design and operation of power systems with large amounts of wind power. Final summary report, IEA WIND Task 25, Phase two 2009–2011
Kariniotakis G, Martí I, Casas D, Pinson P, Nielsen TS, Madsen H, Giebel G, Usaola J, Sanchez I, Palomares AM, Brownsword R, Tambke J, Focken U, Lange M, Louka P, Kallos G, Lac C, Sideratos G, Descombes G (2004) What performance can be expected by short-term wind power prediction models depending on site characteristics? HAL (Le Centre Pour La Communication Scientifique Directe). https://hal-mines-paristech.archives-ouvertes.fr/hal-00529266
Kojo H, Leviäkangas P, Molarius R, and Tuominen A (2011) Extreme weather impacts on transport systems, Tech. rep., VTT Working Papers No. 168, https://publications.vtt.fi/pdf/workingpapers/2011/W168.pdf, accessed: 2022–03–22, 2011
Kong X, Liu X, Shi R, Lee KY (2015) Wind speed prediction using reduced support vector machines with feature selection. Neurocomputing 169:449–456. https://doi.org/10.1016/j.neucom.2014.09.090
Kuhn M, and Johnson K (2013) Applied Predictive Modeling (2013th ed.). Springer. https://doi.org/10.1007/978-1-4614-6849-3
Kurita H, Sasaki K, Muroga H, Ueda H, Wakamatsu S (1985) Long-Range Transport of Air Pollution under Light Gradient Wind Conditions. J Appl Meteorol Climatol 24(5):425–434. https://doi.org/10.1175/1520-0450(1985)024%3c0425:LRTOAP%3e2.0.CO;2
Landberg L (2001) Short-term prediction of local wind conditions. J Wind Eng Ind Aerodyn 89(3):235–245. https://doi.org/10.1016/S0167-6105(00)00079-9
Lew D, Milligan M, Jordan G and Piwko R (2011). Value of Wind Power Forecasting (NREL/CP-5500–50814). National Renewable Energy Lab. (NREL), Golden, CO (United States). https://www.osti.gov/biblio/1011280
Mostafa AN, Zakey AS, Alfaro SC, Wheida AA, Monem SA, Abdul Wahab MM (2019) Validation of RegCM-CHEM4 model by comparison with surface measurements in the Greater Cairo (Egypt) megacity. Environ Sci Pollut Res 26(23):23524–23541. https://doi.org/10.1007/s11356-019-05370-0
Nordhausen K (2009) The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Int Statist Rev, Second Edition by Trevor Hastie, Robert Tibshirani, Jerome Friedman. https://doi.org/10.1111/j.1751-5823.2009.00095_18.x
Pentikäinen PSS, O’Connor EJ, Ortiz-Amezcua P (2022) Evaluating wind profiles in a numerical weather prediction model with Doppler lidar [Preprint]. Clim Earth Sys Model. https://doi.org/10.5194/gmd-2022-150
Prechelt L (2012) Early Stopping — But When? In Lecture Notes in Computer Science (pp. 53–67). Springer Science+Business Media. https://doi.org/10.1007/978-3-642-35289-8_5
Ramon J, Lledó L, Pérez-Zanón N, Soret A, Doblas-Reyes FJ (2020) The Tall Tower Dataset: a unique initiative to boost wind energy research. Earth Syst Sci Data 12(1):429–439. https://doi.org/10.5194/essd-12-429-2020
Roulston MS, Kaplan DT, Hardenberg J, Smith LA (2003) Using medium-range weather forcasts to improve the value of wind energy production. Renew Energy 28(4):585–602. https://doi.org/10.1016/S0960-1481(02)00054-X
Schultz MG, Betancourt C, Gong B, Kleinert F, Langguth M, Leufen LH, Mozaffari A, Stadtler S (2021) Can deep learning beat numerical weather prediction? Philosoph Transact Royal Soc Mathemat Phys Eng Sci 379(2194):20200097. https://doi.org/10.1098/rsta.2020.0097
Seinfeld JH, Pandis SN (1998) Atmospheric Chemistry and Physics: From Air Pollution to Climate Change. John Wiley (Ed.), New York, 1326 pp
Sekuła P, Bokwa A, Bartyzel J, Bochenek B, Chmura Ł, Gałkowski M, Zimnoch M (2021) Measurement report: Effect of wind shear on PM10 concentration vertical structure in the urban boundary layer in a complex terrain. Atmos Chem Phys 21(15):12113–12139. https://doi.org/10.5194/acp-21-12113-2021
Shang Z, He Z, Chen Y, Chen Y, Xu M (2022) Short-term wind speed forecasting system based on multivariate time series and multi-objective optimization. Energy. https://doi.org/10.1016/j.energy.2021.122024
Sheela KG, Deepa SN (2013) A Review on Neural Network Models for Wind Speed Prediction. Wind Eng 37(2):111–123. https://doi.org/10.1260/0309-524X.37.2.111
Shi J, Guo J, Zheng S (2012) Evaluation of hybrid forecasting approaches for wind speed and power generation time series. Renew Sustain Energy Rev 16(5):3471–3480. https://doi.org/10.1016/j.rser.2012.02.044
Shumway RH, Stoffer DS (2011) Time Series Analysis and Its Applications (Third). Springer, New York. https://doi.org/10.1007/978-1-4419-7865-3
Smith DL, Zuckerberg FL, Schaefer JT and Rasch GE (1986) Forecast Problems: The Meteorological and Operational Factors. In P. S. Ray (Ed.), Mesoscale Meteorology and Forecasting (pp. 36–49). American Meteorological Society. https://doi.org/10.1007/978-1-935704-20-1_3
Wheida A, Nasser A, El Nazer M, Borbon A, Abo El Ata GA, Abdel Wahab M, Alfaro SC (2018) Tackling the mortality from long-term exposure to outdoor air pollution in megacities: Lessons from the Greater Cairo case study. Environ Res 160:223–231. https://doi.org/10.1016/j.envres.2017.09.028
Xue H, Jia Y, Wen P, Farkoush SG (2020) Using of improved models of Gaussian Processes in order to Regional wind power forecasting. J Clean Prod. https://doi.org/10.1016/j.jclepro.2020.121391
Yang J, Xingcheng W, Xiaofen L, Cheng J (2015) Intelligent Combined Prediction of Wind Power Based on Numerical Weather Prediction and Fuzzy Clustering. IFAC-PapersOnLine 48(28):538–543. https://doi.org/10.1016/j.ifacol.2015.12.184
Yano J-I, Ziemiański MZ, Cullen M, Termonia P, Onvlee J, Bengtsson L, Carrassi A, Davy R, Deluca A, Gray SL, Homar V, Köhler M, Krichak S, Michaelides S, Phillips VTJ, Soares PMM, Wyszogrodzki AA (2018) Scientific Challenges of Convective-Scale Numerical Weather Prediction. Bull Am Meteor Soc 99(4):699–710. https://doi.org/10.1175/BAMS-D-17-0125.1
Ye H, Yang B, Han Y, Li Q, Deng J, Tian S (2022) Wind Speed and Power Prediction Approaches: Classifications, Methodologies, and Comments. Front Energy Res. https://doi.org/10.3389/fenrg.2022.901767
Yousuf MU, Al-Bahadly I, Avci E (2022) Statistical wind speed forecasting models for small sample datasets: Problems, Improvements, and prospects. Energy Convers Manage. https://doi.org/10.1016/j.enconman.2022.115658
Acknowledgements
The first author is grateful to the French Embassy in Egypt and the Agence Universitaire de la Francophonie for funding his stays at the Laboratoire Inter-unversitaire des Systèmes Atmosphériques (Créteil, France).
Author information
Authors and Affiliations
Corresponding author
Additional information
Responsible Editor: Clemens Simmer, Ph.D.
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
ElTaweel, M.H., Alfaro, S.C., Siour, G. et al. Prediction and forecast of surface wind using ML tree-based algorithms. Meteorol Atmos Phys 136, 1 (2024). https://doi.org/10.1007/s00703-023-00999-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00703-023-00999-6