|
|
SAR-UNet：一种基于空间注意力机制的大气河识别网络模型
|
Abstract:
准确、高效地识别大气河可以有效地预防洪涝和干旱等自然灾害，对地区的经济、社会和生态发展具有非常重大的意义。现有的大气河识别算法主要是基于多个物理量的阈值来实现的，它们能有效地识别大气河，但需要手动设置阈值和几何度量标准。由于现有方法在复杂度和泛化能力上的局限性，本文基于深度学习的方法，提出了名为SAR-UNet的网络模型，该模型基于UNet网络结构，在特征提取时创新性地加入了空间注意力机制，从而能够更好地获取大气河的局部特征信息。通过深度学习的方法来对大气河进行自动识别，有效地解决了现有方法需要确定阈值和度量标准的不足。实验结果表明，基于SAR-UNet的大气河识别方法在ERA-Interim气候再分析数据集上具有最佳的识别效果，大气河识别的精度上达到了97.27%，MIoU值高达85.22%。
Accurate and efficient identification of atmospheric rivers can effectively prevent natural disasters such as floods and droughts, and is of great significance to the economic, social and ecological development of the region. Existing atmospheric river identification algorithms are mainly based on the thresholds of multiple physical quantities, which can effectively identify atmospheric rivers, but need to manually set thresholds and geometric metrics. Due to the limitations of existing methods in complexity and generalization ability, this paper proposes a network model named SAR-UNet based on deep learning, which is based on UNet network structure and innovatively adds spatial attention mechanism during feature extraction, so as to better obtain local feature information of atmospheric rivers. The automatic identification of atmospheric rivers by deep learning effectively solves the shortcomings of existing methods that need to determine thresholds and metrics. The experimental results show that the atmospheric river identification method based on SAR-UNet has the best identification effect on the ERA-Interim climate reanalysis dataset, the accuracy of atmos-pheric river identification reaches 97.27%, and the MIoU value is as high as 85.22%.
| [1] | Zhu, Y. and Newell, R.E. (1994) Atmospheric Rivers and Bombs. Geophysical Research Letters, 21, 1999-2002.
https://doi.org/10.1029/94GL01710 |
| [2] | Ralph, F.M., Wilson, A.M., Shulgina, T., et al. (2019) ARTMIP-Early Start Comparison of Atmospheric River Detection Tools: How Many Atmospheric Rivers Hit Northern California’s Russian River Watershed? Climate Dynamics, 52, 4973-4994. https://doi.org/10.1007/s00382-018-4427-5 |
| [3] | Shields, C.A., Rutz, J.J., Leung, L.Y., et al. (2018) Atmospheric River Tracking Method Intercomparison Project (ARTMIP): Project Goals and Experimental Design. Geoscientific Mod-el Development, 11, 2455-2474.
https://doi.org/10.5194/gmd-11-2455-2018 |
| [4] | Leung, L.R. and Qian, Y. (2009) Atmospheric Rivers Induced Heavy Precipitation and Flooding in the Western US Simulated by the WRF Regional Climate Model. Geophysical Re-search Letters, 36, L03820.
https://doi.org/10.1029/2008GL036445 |
| [5] | Tang, Y., Huang, A.N., Wu, P.L., et al. (2021) Drivers of Summer Extreme Precipitation Events over East China. Geophysical Research Letters, 48, e2021GL093670. https://doi.org/10.1029/2021GL093670 |
| [6] | Chapman, W.E., Subramanian, A.C., Delle Monache, L., Xie, S.P. and Ralph, F.M. (2019) Improving Atmospheric River Forecasts with Machine Learning. Geophysical Research Letters, 46, 10627-10635.
https://doi.org/10.1029/2019GL083662 |
| [7] | Xu, G.Z., Ma, X.H., Chang, P. and Wang, L. (2020) Im-age-Processing-Based Atmospheric River Tracking Method Version 1 (IPART-1). Geoscientific Model Development, 13, 4639-4662. https://doi.org/10.5194/gmd-2020-135 |
| [8] | Neiman, P.J., White, A.B., Ralph, F.M., et al. (2013) A Water Vapour Flux Tool for Precipitation Forecasting. Water and Energy International, 70, 72-73. |
| [9] | Lavers, D.A., et al. (2012) A Water Vapour Flux Tool for Precipitation Forecasting. Proceedings of the Institution of Civil Engineers Wa-ter Management, 162, 83-94. https://doi.org/10.1680/wama.2009.162.2.83 |
| [10] | 苏亮宇, 余骁禹. 基于骨架模型的大气河流识别算法[J]. 移动信息, 2021(4). |
| [11] | Ralph, F.M., Coleman, T., Neiman, P.J., et al. (2013) Observed Impacts of Duration and Seasonality of Atmospheric-River Landfalls on Soil Moisture and Runoff in Coastal Northern California. Journal of Hydrometeorology, 14, 443-459.
https://doi.org/10.1175/JHM-D-12-076.1 |
| [12] | Wick, G.A., Neiman, P.J. and Ralph, F.M. (2012) Description and Validation of an Automated Objective Technique for Identification and Characterization of the Integrated Water Vapor Signature of Atmospheric Rivers. IEEE Transactions on Geoscience and Remote Sensing, 51, 2166-2176. https://doi.org/10.1109/TGRS.2012.2211024 |
| [13] | Rutz, J.J., Steenburgh, W.J. and Ralph, F.M. (2014) Climato-logical Characteristics of Atmospheric Rivers and Their Inland Penetration over the Western United States. Monthly Weather Review, 142, 905-921.
https://doi.org/10.1175/MWR-D-13-00168.1 |
| [14] | Guan, B. and Waliser, D.E. (2015) Detection of Atmospheric Rivers: Evaluation and Application of an Algorithm for Global Studies. Journal of Geophysical Research: Atmospheres, 120, 12514-12535.
https://doi.org/10.1002/2015JD024257 |
| [15] | Pan, M. and Lu, M. (2020) East Asia Atmospheric River Catalog: Annual Cycle, Transition Mechanism, and Precipitation. Geophysical Research Letters, 47, e2020GL089477. https://doi.org/10.1029/2020GL089477 |
| [16] | Ohanuba, F.O., Ismail, M.T., Ali, M.K.M., et al. (2021) On the Clus-ter Validity Test(s) in Unsupervised Machine Learning TDA Approach for Atmospheric River Patterns on Flood Detec-tion in Nigeria.
https://doi.org/10.21203/rs.3.rs-459258/v1 |
| [17] | Muszynski, G., Kashinath, K., Kurlin, V., Wehner, M. and Prabhat (2019) Topological Data Analysis and Machine Learning for Recognizing Atmospheric River Patterns in Large Climate Datasets. Geoscientific Model Development, 12, 613-628. https://doi.org/10.5194/gmd-12-613-2019 |
| [18] | Guan, B. and Waliser, D.E. (2019) Tracking Atmospheric Rivers Globally: Spatial Distributions and Temporal Evolution of Life Cycle Characteristics. Journal of Geophysical Research: Atmospheres, 124, 12523-12552.
https://doi.org/10.1029/2019JD031205 |
| [19] | Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., et al. (2017) A Re-view on Deep Learning Techniques Applied to Semantic Segmentation. Applied Soft Computing, 70, 41-65. https://doi.org/10.1016/j.asoc.2018.05.018 |
| [20] | Ronneberger, O., Fischer, P. and Brox, T. (2015) U-net: Convolu-tional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Com-puter-Assisted Intervention, Springer, Cham, 234-241.
https://doi.org/10.1007/978-3-319-24574-4_28 |
| [21] | Sultana, F., Sufian, A. and Dutta, P. (2020) Evolution of Im-age Segmentation Using Deep Convolutional Neural Network: A Survey. Knowledge-Based Systems, 201, Article ID: 106062. https://doi.org/10.1016/j.knosys.2020.106062 |
| [22] | Simonyan, K. and Zisserman, A. (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition. ArXiv: 1409.1556. |
| [23] | Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recog-nition, Salt Lake City, 18-23 June 2018, 7132-7141.
https://doi.org/10.1109/CVPR.2018.00745 |
| [24] | He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778.
https://doi.org/10.1109/CVPR.2016.90 |
| [25] | Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, 4-9 December 2017, 1-15. |
| [26] | Zhao, H., Shi, J., Qi, X., et al. (2017) Pyramid Scene Parsing Network. Proceedings of the IEEE Con-ference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 2881-2890. https://doi.org/10.1109/CVPR.2017.660 |
| [27] | Badrinarayanan, V., Kendall, A. and Cipolla, R. (2017) Segnet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 2481-2495.
https://doi.org/10.1109/TPAMI.2016.2644615 |
| [28] | Chen, L.C., Zhu, Y., Papandreou, G., et al. (2018) Encod-er-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Confer-ence on Computer Vision (ECCV), Munich, 8-14 September 2018, 801-818. https://doi.org/10.1007/978-3-030-01234-2_49 |
| [29] | Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolu-tional Networks for Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, 7-12 June 2015, 3431-3440.
https://doi.org/10.1109/CVPR.2015.7298965 |
| [30] | Chen, L.C., Papandreou, G., Schroff, F., et al. (2017) Rethink-ing Atrous Convolution for Semantic Image Segmentation. ArXiv: 1706.05587. |
| [31] | Weiss, K., Khoshgoftaar, T.M. and Wang, D.D. (2016) A Survey of Transfer Learning. Journal of Big Data, 3, Article No. 9. https://doi.org/10.1186/s40537-016-0043-6 |
| [32] | Pan, S.J., Tsang, I.W., Kwok, J.T., et al. (2010) Domain Adapta-tion via Transfer Component Analysis. IEEE Transactions on Neural Networks, 22, 199-210. https://doi.org/10.1109/TNN.2010.2091281 |
| [33] | Zhuang, F., Qi, Z., Duan, K., et al. (2020) A Comprehensive Survey on Transfer Learning. Proceedings of the IEEE, 109, 43-76. https://doi.org/10.1109/JPROC.2020.3004555 |
