Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts (2312.16046v2)

Published 26 Dec 2023 in cs.LG, cs.AI, and physics.ao-ph

Abstract: Previous post-processing studies on rainfall forecasts using numerical weather prediction (NWP) mainly focus on statistics-based aspects, while learning-based aspects are rarely investigated. Although some manually-designed models are proposed to raise accuracy, they are customized networks, which need to be repeatedly tried and verified, at a huge cost in time and labor. Therefore, a self-supervised neural architecture search (NAS) method without significant manual efforts called AdaNAS is proposed in this study to perform rainfall forecast post-processing and predict rainfall with high accuracy. In addition, we design a rainfall-aware search space to significantly improve forecasts for high-rainfall areas. Furthermore, we propose a rainfall-level regularization function to eliminate the effect of noise data during the training. Validation experiments have been performed under the cases of \emph{None}, \emph{Light}, \emph{Moderate}, \emph{Heavy} and \emph{Violent} on a large-scale precipitation benchmark named TIGGE. Finally, the average mean-absolute error (MAE) and average root-mean-square error (RMSE) of the proposed AdaNAS model are 0.98 and 2.04 mm/day, respectively. Additionally, the proposed AdaNAS model is compared with other neural architecture search methods and previous studies. Compared results reveal the satisfactory performance and superiority of the proposed AdaNAS model in terms of precipitation amount prediction and intensity classification. Concretely, the proposed AdaNAS model outperformed previous best-performing manual methods with MAE and RMSE improving by 80.5\% and 80.3\%, respectively.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Q. Zhao, Y. Liu, W. Yao, and Y. Yao, “Hourly rainfall forecast model using supervised learning algorithm,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–9, 2021.
  2. J. Michalakes, S. Chen, J. Dudhia, L. Hart, J. Klemp, J. Middlecoff, and W. Skamarock, “Development of a next-generation regional weather research and forecast model,” in Developments in teracomputing, 2001, pp. 269–276.
  3. Y. Tang, H. W. Lean, and J. Bornemann, “The benefits of the met office variable resolution nwp model for forecasting convection,” Meteorological Applications, vol. 20, no. 4, pp. 417–426, 2013.
  4. Y. Seity, P. Brousseau, S. Malardel, G. Hello, P. Bénard, F. Bouttier, C. Lac, and V. Masson, “The arome-france convective-scale operational model,” Monthly Weather Review, vol. 139, no. 3, pp. 976–991, 2011.
  5. E. E. Ebert, “Ability of a poor man’s ensemble to predict the probability and distribution of precipitation,” Monthly Weather Review, vol. 129, no. 10, pp. 2461–2480, 2001.
  6. X. Zhi, W. Zhou, and Z. Xu, “Multi-model ensemble forecasts of the tc tracks over the western pacific using the tigge dataset,” in The 3rd International Conference on Information Science and Engineering, 2011, pp. 4173–4176.
  7. K. Dai, Y. Cao, Q. Qian, S. Gao, S. Zhao, Y. Chen, and C. Qian, “Situation and tendency of operational technologies in short-and medium-range weather forecast,” Meteor Mon, vol. 42, no. 12, pp. 1445–1455, 2016.
  8. L. Cuo, T. C. Pagano, and Q. Wang, “A review of quantitative precipitation forecasts and their use in short-to medium-range streamflow forecasting,” Journal of hydrometeorology, vol. 12, no. 5, pp. 713–728, 2011.
  9. T. Gneiting and M. Katzfuss, “Probabilistic forecasting,” Annual Review of Statistics and Its Application, vol. 1, pp. 125–151, 2014.
  10. J. C. Schaake, T. M. Hamill, R. Buizza, and M. Clark, “Hepex: the hydrological ensemble prediction experiment,” Bulletin of the American Meteorological Society, vol. 88, no. 10, pp. 1541–1548, 2007.
  11. F. Kong, K. K. Droegemeier, and N. L. Hickmon, “Multiresolution ensemble forecasts of an observed tornadic thunderstorm system. part i: Comparsion of coarse-and fine-grid experiments,” Monthly weather review, vol. 134, no. 3, pp. 807–833, 2006.
  12. Y. Zhang and A. Ye, “Machine learning for precipitation forecasts postprocessing: Multimodel comparison and experimental investigation,” Journal of Hydrometeorology, vol. 22, no. 11, pp. 3065–3085, 2021.
  13. W. Li, B. Pan, J. Xia, and Q. Duan, “Convolutional neural network-based statistical post-processing of ensemble precipitation forecasts,” Journal of hydrology, vol. 605, p. 127301, 2022.
  14. M. Ghazvinian, Y. Zhang, D.-J. Seo, M. He, and N. Fernando, “A novel hybrid artificial neural network-parametric scheme for postprocessing medium-range precipitation forecasts,” Advances in Water Resources, vol. 151, p. 103907, 2021.
  15. F. Xu, G. Li, Y. Du, Z. Chen, and Y. Lu, “Multi-layer networks for ensemble precipitation forecasts postprocessing,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 17, 2021, pp. 14 966–14 973.
  16. S. Vannitsem, J. B. Bremnes, J. Demaeyer, G. R. Evans, J. Flowerdew, S. Hemri, S. Lerch, N. Roberts, S. Theis, A. Atencia et al., “Statistical postprocessing for weather forecasts: Review, challenges, and avenues in a big data world,” Bulletin of the American Meteorological Society, vol. 102, no. 3, pp. E681–E699, 2021.
  17. X. He, K. Zhao, and X. Chu, “Automl: A survey of the state-of-the-art,” Knowledge-Based Systems, vol. 212, p. 106622, 2021.
  18. Y. Xu, L. Xie, X. Zhang, X. Chen, G.-J. Qi, Q. Tian, and H. Xiong, “Pc-darts: Partial channel connections for memory-efficient architecture search,” arXiv preprint arXiv:1907.05737, 2019.
  19. C. He, H. Ye, L. Shen, and T. Zhang, “Milenas: Efficient neural architecture search via mixed-level reformulation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11 993–12 002.
  20. K. Ahmed and L. Torresani, “Maskconnect: Connectivity learning by gradient descent,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 349–365.
  21. S. You, T. Huang, M. Yang, F. Wang, C. Qian, and C. Zhang, “Greedynas: Towards fast one-shot nas with greedy supernet,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 1999–2008.
  22. H. Cai, L. Zhu, and S. Han, “Proxylessnas: Direct neural architecture search on target task and hardware,” arXiv preprint arXiv:1812.00332, 2018.
  23. M. Tan and Q. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” in International Conference on Machine Learning.   PMLR, 2019, pp. 6105–6114.
  24. H. Liu, K. Simonyan, and Y. Yang, “Darts: Differentiable architecture search,” arXiv preprint arXiv:1806.09055, 2018.
  25. K. Yu, C. Sciuto, M. Jaggi, C. Musat, and M. Salzmann, “Evaluating the search phase of neural architecture search,” arXiv preprint arXiv:1902.08142, 2019.
  26. A. Yang, P. M. Esperança, and F. M. Carlucci, “Nas evaluation is frustratingly hard,” arXiv preprint arXiv:1912.12522, 2019.
  27. A. Zela, J. Siems, and F. Hutter, “Nas-bench-1shot1: Benchmarking and dissecting one-shot neural architecture search,” arXiv preprint arXiv:2001.10422, 2020.
  28. X. Li, C. Lin, C. Li, M. Sun, W. Wu, J. Yan, and W. Ouyang, “Improving one-shot nas by suppressing the posterior fading,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 13 836–13 845.
  29. B. Moons, P. Noorzad, A. Skliar, G. Mariani, D. Mehta, C. Lott, and T. Blankevoort, “Distilling optimal neural networks: Rapid search in diverse spaces,” arXiv preprint arXiv:2012.08859, 2020.
  30. C. Li, J. Peng, L. Yuan, G. Wang, X. Liang, L. Lin, and X. Chang, “Block-wisely supervised neural architecture search with knowledge distillation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 1989–1998.
  31. K. He, H. Fan, Y. Wu, S. Xie, and R. B. Girshick, “Momentum contrast for unsupervised visual representation learning,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9726–9735, 2020.
  32. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” nature, vol. 323, no. 6088, pp. 533–536, 1986.
  33. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).   Las Vegas, NV, United States: IEEE, 2016, pp. 770–778.
  34. L. Yang, R.-Y. Zhang, L. Li, and X. Xie, “Simam: A simple, parameter-free attention module for convolutional neural networks,” in International Conference on Machine Learning.   PMLR, 2021, pp. 11 863–11 874.
  35. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” in nips, 2017.
  36. M. Zhang, H. Li, S. Pan, X. Chang, and S. Su, “Overcoming multi-model forgetting in one-shot nas with diversity maximization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 7809–7818.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now