Abstract
Numerical weather prediction of wind speed requires statistical postprocessing of systematic errors to obtain reliable and accurate forecasts. However, use of postprocessing models is often undesirable for extreme weather events such as gales. Here, we propose a postprocessing algorithm based on a gale-aware deep attention network to simultaneously improve wind speed forecasts and gale area warnings. Specifically, the algorithm includes both a galeaware loss function that focuses the model on potential gale areas, and an observation station supervision strategy that alleviates the problem of missing extreme values caused by data gridding. The effectiveness of the proposed model was verified by using data from 235 wind speed observation stations. Experimental results show that our model can produce wind speed forecasts with a root-mean-square error of 1.1547 m s−1, and a Hanssen–Kuipers discriminant score of 0.517, performance that is superior to that of the other postprocessing algorithms considered.
This is a preview of subscription content, log in via an institution to check access.
References
Arcomano, T., I. Szunyogh, A. Wikner, et al., 2022: A hybrid approach to atmospheric modeling that combines machine learning with a physics-based numerical model. J. Adv. Model. Earth Syst., 14, e2021MS002712, doi: https://doi.org/10.1029/2021MS002712.
Bakker, K., K. Whan, W. Knap, et al., 2019: Comparison of statistical post-processing methods for probabilistic NWP forecasts of solar radiation. Solar Energy, 191, 138–150, doi: https://doi.org/10.1016/j.solener.2019.08.044.
Baran, S., and S. Lerch, 2015: Log-normal distribution based ensemble model output statistics models for probabilistic wind-speed forecasting. Quart. J. Roy. Meteor. Soc., 141, 2289–2299, doi: https://doi.org/10.1002/qj.2521.
Bauer, P., A. Thorpe, and G. Brunet, 2015: The quiet revolution of numerical weather prediction. Nature, 525, 47–55, doi: https://doi.org/10.1038/nature14956.
Chen, K. R., P. Wang, X. J. Yang, et al., 2020: A model output deep learning method for grid temperature forecasts in Tianjin area. Appl. Sci., 10, 5808, doi: https://doi.org/10.3390/app10175808.
Cho, D., C. Yoo, B. Son, et al., 2022: A novel ensemble learning for post-processing of NWP model’s next-day maximum air temperature forecast in summer using deep learning and statistical approaches. Wea. Climate Extremes, 35, 100410, doi: https://doi.org/10.1016/j.wace.2022.100410.
Choi, E. C. C., and A. Tanurdjaja, 2002: Extreme wind studies in Singapore. An area with mixed weather system. J. Wind Eng. Ind. Aerodyn., 90, 1611–1630, doi: https://doi.org/10.1016/S0167-6105(02)00274-X.
Dupuy, F., O. Mestre, M. Serrurier, et al., 2021: ARPEGE cloud cover forecast postprocessing with convolutional neural network. Wea. Forecasting, 36, 567–586, doi: https://doi.org/10.1175/WAF-D-20-0093.1.
Ganaie, M. A., and M. Tanveer, 2022: KNN weighted reduced universum twin SVM for class imbalance learning. Knowl.-Based Syst., 245, 108578, doi: https://doi.org/10.1016/j.knosys.2022.108578.
Glahn, H. R., and D. A. Lowry, 1972: The use of model output statistics (MOS) in objective weather forecasting. J. Appl. Meteor. Climatol., 11, 1203–1211, doi: https://doi.org/10.1175/1520-0450(1972)011<1203:TUOMOS>2.0.CO;2.
Gu, Q. H., J. N. Tian, X. X. Li, et al., 2022: A novel random forest integrated model for imbalanced data classification problem. Knowl.-Based Syst., 250, 109050, doi: https://doi.org/10.1016/j.knosys.2022.109050.
He, Y. Y., and W. Y. Zhang, 2020: Probability density forecasting of wind power based on multi-core parallel quantile regression neural network. Knowl.-Based Syst., 209, 106431, doi: https://doi.org/10.1016/j.knosys.2020.106431.
Hossain, F., 2021: Application of wind energy into the transportation sector. Int. J. Precis. Eng. Manuf.-Green Technol., 8, 1225–1237, doi: https://doi.org/10.1007/s40684-020-00235-1.
Li, B., 2017: 3D fully convolutional network for vehicle detection in point cloud. 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Vancouver, Canada, 1513–1518, doi: https://doi.org/10.1109/IROS.2017.8205955.
Li, Q. W., J. Z. Wang, and H. P. Zhang, 2021: A wind speed interval forecasting system based on constrained lower upper bound estimation and parallel feature selection. Knowl.-Based Syst., 231, 107435, doi: https://doi.org/10.1016/j.knosys.2021.107435.
Li, X. F., J. A. Zhang, X. F. Yang, et al., 2013: Tropical cyclone morphology from spaceborne synthetic aperture radar. Bull. Amer. Meteor. Soc., 94, 215–230, doi: https://doi.org/10.1175/BAMS-D-11-00211.1.
Liang, T., Q. Zhao, Q. Z. Lv, et al., 2021: A novel wind speed prediction strategy based on Bi-LSTM, MOOFADA and transfer learning for centralized control centers. Energy, 230, 120904, doi: https://doi.org/10.1016/j.energy.2021.120904.
Liu, X. L., Z. Lin, and Z. M. Feng, 2021: Short-term offshore wind speed forecast by seasonal ARIMA—A comparison against GRU and LSTM. Energy, 227, 120492, doi: https://doi.org/10.1016/j.energy.2021.120492.
McGovern, A., K. L. Elmore, D. J. GagneII, et al., 2017: Using artificial intelligence to improve real-time decision-making for high-impact weather. Bull. Amer. Meteor. Soc., 98, 2073–2090, doi: https://doi.org/10.1175/BAMS-D-16-0123.1.
Nandi, A., A. De, A. Mallick, et al., 2022: Attention based long-term air temperature forecasting network: ALTF net. Knowl.-Based Syst., 252, 109442, doi: https://doi.org/10.1016/j.knosys.2022.109442.
Niu, R. Y., P. M. Zhai, and B. Q. Zhou, 2015: Evaluation of forecast performance of asian summer monsoon low-level winds using the TIGGE dataset. Wea. Forecasting, 30, 455–470, doi: https://doi.org/10.1175/WAF-D-13-00141.1.
Niu, Z. Y., G. Q. Zhong, and H. Yu, 2021: A review on the attention mechanism of deep learning. Neurocomputing, 452, 48–62, doi: https://doi.org/10.1016/j.neucom.2021.03.091.
Pan, B. X., G. J. Anderson, A. Goncalves, et al., 2021: Learning to correct climate projection biases. J. Adv. Model. Earth Syst., 13, e2021MS002509, doi: https://doi.org/10.1029/2021MS002509.
Pillai, S. R., A. Yadav, H. Yadav, et al., 2021: Predicting the output of a wind mill using ANN modelling. Recent Advances in Mechanical Engineering, A. Kumar, A. Pal, S. S. Kachhwaha, et al., Eds., Springer, Singapore, 207–215, doi: https://doi.org/10.1007/978-981-15-9678-0_18.
Rasp, S., and S. Lerch, 2018: Neural networks for postprocessing ensemble weather forecasts. Mon. Wea. Rev., 146, 3885–3900, doi: https://doi.org/10.1175/MWR-D-18-0187.1.
Rhudy, M. B., M. L. Fravolini, M. Porcacchia, et al., 2019: Comparison of wind speed models within a pitot-free airspeed estimation algorithm using light aviation data. Aerosp. Sci. Technol., 86, 21–29, doi: https://doi.org/10.1016/j.ast.2018.12.028.
Ribeiro, R. P., and N. Moniz, 2020: Imbalanced regression and extreme value prediction. Mach. Learn., 109, 1803–1835, doi: https://doi.org/10.1007/s10994-020-05900-9.
Schauwecker, S., M. Schwarb, M. Rohrer, et al., 2021: Heavy precipitation forecasts over switzerland—an evaluation of bias-corrected ECMWF predictions. Wea. Clim. Extremes, 34, 100372, doi: https://doi.org/10.1016/j.wace.2021.100372.
Song, Z. Y., Y. J. Tang, J. K. Ji, et al., 2020: Evaluating a dendritic neuron model for wind speed forecasting. Knowl.-Based Syst., 201–202, 106052, doi: https://doi.org/10.1016/j.knosys.2020.106052.
Swinbank, R., M. Kyouda, P. Buchanan, et al., 2016: The TIGGE project and its achievements. Bull. Amer. Meteor. Soc., 97, 49–67, doi: https://doi.org/10.1175/BAMS-D-13-00191.1.
Vannitsem, S., J. B. Bremnes, J. Demaeyer, et al., 2021: Statistical postprocessing for weather forecasts: Review, challenges, and avenues in a big data world. Bull. Amer. Meteor. Soc., 102, E681–E699, doi: https://doi.org/10.1175/BAMS-D-19-0308.1.
Whan, K., and M. Schmeits, 2018: Comparing area probability forecasts of (extreme) local precipitation using parametric and machine learning statistical postprocessing methods. Mon. Wea. Rev., 146, 3651–3673, doi: https://doi.org/10.1175/MWR-D-17-0290.1.
Xia, J. J., H. C. Li, Y. Y. Kang, et al., 2020: Machine learning-based weather support for the 2022 Winter Olympics. Adv. Atmos. Sci., 37, 927–932, doi: https://doi.org/10.1007/s00376-020-0043-5.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Natural Science Foundation of China (62106169).
Rights and permissions
About this article
Cite this article
Chen, K., Zhou, Y., Wang, P. et al. Improving Wind Forecasts Using a Gale-Aware Deep Attention Network. J Meteorol Res 37, 775–789 (2023). https://doi.org/10.1007/s13351-023-3020-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13351-023-3020-y