Interpretable Convolutional Neural Network for Analyzing Precipitation in the Pre-Rainy Season of South China

Shengjun Liu aSchool of Mathematics and Statistics, Central South University, Changsha, China

Search for other papers by Shengjun Liu in
Current site
Google Scholar
PubMed
Close
,
Wenjie Yan aSchool of Mathematics and Statistics, Central South University, Changsha, China

Search for other papers by Wenjie Yan in
Current site
Google Scholar
PubMed
Close
,
Xinru Liu aSchool of Mathematics and Statistics, Central South University, Changsha, China

Search for other papers by Xinru Liu in
Current site
Google Scholar
PubMed
Close
,
Yamin Hu bGuangdong Climate Center, Guangzhou, China

Search for other papers by Yamin Hu in
Current site
Google Scholar
PubMed
Close
, and
Dangfu Yang aSchool of Mathematics and Statistics, Central South University, Changsha, China

Search for other papers by Dangfu Yang in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

The research and application of convolutional neural networks (CNNs) on statistical downscaling have been hampered by the fact that deep learning is highly dependent on sample size and is considered to be a black-box model. Therefore, a CNN model with transfer learning (CNN-TL) is proposed to study the pre-rainy season precipitation of South China. First, an augmented monthly dataset is created by sliding a fixed-length window over the daily circulation field and precipitation data for the entire year. Next, a base CNN network is pretrained on the augmented dataset, and then the network parameters are tuned on the actual monthly dataset from South China. Then, guided backpropagation is conducted to obtain the distribution regions of the key features and explain the net. The coefficient of determination R2 and root-mean-square error (RMSE) show that the CNN-TL model has higher explanatory power and better fitting performance than the feature extraction–based random forest. In comparison with the base CNN, the transfer learning approach can improve the explanatory power of the model by 10.29% and reduce the average RMSE by 6.82%. In addition, the interpretation results of the model show that the critical regions are primarily South China and its surrounding areas, including the Indochina Peninsula, the Bay of Bengal, and the South China Sea. Furthermore, the ablation experiments and composite analysis illustrate that these regions are very important.

Significance Statement

To mitigate the challenges posed by small sample sizes and the transparency of deep learning in downscaling problems, we propose a convolutional neural network based on sample augmentation and transfer learning to study the monthly precipitation downscaling problem during the preflood period in South China. In comparison with random forests and conventional convolutional neural networks, our model achieves an optimal interpretation rate and stability. In addition, we explore the interpretability of the model using guided backpropagation to find the distribution of key features within the large-scale circulation field, thus increasing the credibility of the model.

© 2024 American Meteorological Society. This published article is licensed under the terms of the default AMS reuse license. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding authors: Xinru Liu, liuxinru@csu.edu.cn; Yamin Hu, huym@gd121.cn.

Abstract

The research and application of convolutional neural networks (CNNs) on statistical downscaling have been hampered by the fact that deep learning is highly dependent on sample size and is considered to be a black-box model. Therefore, a CNN model with transfer learning (CNN-TL) is proposed to study the pre-rainy season precipitation of South China. First, an augmented monthly dataset is created by sliding a fixed-length window over the daily circulation field and precipitation data for the entire year. Next, a base CNN network is pretrained on the augmented dataset, and then the network parameters are tuned on the actual monthly dataset from South China. Then, guided backpropagation is conducted to obtain the distribution regions of the key features and explain the net. The coefficient of determination R2 and root-mean-square error (RMSE) show that the CNN-TL model has higher explanatory power and better fitting performance than the feature extraction–based random forest. In comparison with the base CNN, the transfer learning approach can improve the explanatory power of the model by 10.29% and reduce the average RMSE by 6.82%. In addition, the interpretation results of the model show that the critical regions are primarily South China and its surrounding areas, including the Indochina Peninsula, the Bay of Bengal, and the South China Sea. Furthermore, the ablation experiments and composite analysis illustrate that these regions are very important.

Significance Statement

To mitigate the challenges posed by small sample sizes and the transparency of deep learning in downscaling problems, we propose a convolutional neural network based on sample augmentation and transfer learning to study the monthly precipitation downscaling problem during the preflood period in South China. In comparison with random forests and conventional convolutional neural networks, our model achieves an optimal interpretation rate and stability. In addition, we explore the interpretability of the model using guided backpropagation to find the distribution of key features within the large-scale circulation field, thus increasing the credibility of the model.

© 2024 American Meteorological Society. This published article is licensed under the terms of the default AMS reuse license. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding authors: Xinru Liu, liuxinru@csu.edu.cn; Yamin Hu, huym@gd121.cn.
Save
  • Baker, L. H., L. C. Shaffrey, and A. A. Scaife, 2018: Improved seasonal prediction of UK regional precipitation using atmospheric circulation. Int. J. Climatol., 38, e437e453, https://doi.org/10.1002/joc.5382.

    • Search Google Scholar
    • Export Citation
  • Beecham, S., M. Rashid, and R. K. Chowdhury, 2014: Statistical downscaling of multi-site daily rainfall in a South Australian catchment using a generalized linear model. Int. J. Climatol., 34, 36543670, https://doi.org/10.1002/joc.3933.

    • Search Google Scholar
    • Export Citation
  • Chen, S.-T., P.-S. Yu, and Y.-H. Tang, 2010: Statistical downscaling of daily precipitation using support vector machines and multivariate analysis. J. Hydrol., 385, 1322, https://doi.org/10.1016/j.jhydrol.2010.01.021.

    • Search Google Scholar
    • Export Citation
  • Chen, Y., and Y. Luo, 2018: Analysis of paths and sources of moisture for the South China rainfall during the presummer rainy season of 1979–2014. J. Meteor. Res., 32, 744757, https://doi.org/10.1007/s13351-018-8069-7.

    • Search Google Scholar
    • Export Citation
  • Chu, J. T., J. Xia, C.-Y. Xu, and V. P. Singh, 2010: Statistical downscaling of daily mean temperature, pan evaporation and precipitation for climate change scenarios in Haihe River, China. Theor. Appl. Climatol., 99, 149161, https://doi.org/10.1007/s00704-009-0129-6.

    • Search Google Scholar
    • Export Citation
  • Davenport, F. V., and N. S. Diffenbaugh, 2021: Using machine learning to analyze physical causes of climate change: A case study of U.S. Midwest extreme precipitation. Geophys. Res. Lett., 48, e2021GL093787, https://doi.org/10.1029/2021GL093787.

    • Search Google Scholar
    • Export Citation
  • Dikshit, A., and B. Pradhan, 2021a: Explainable AI in drought forecasting. Mach. Learn. Appl., 6, 100192, https://doi.org/10.1016/j.mlwa.2021.100192.

    • Search Google Scholar
    • Export Citation
  • Dikshit, A., and B. Pradhan, 2021b: Interpretable and explainable AI (XAI) model for spatial drought prediction. Sci. Total Environ., 801, 149797, https://doi.org/10.1016/j.scitotenv.2021.149797.

    • Search Google Scholar
    • Export Citation
  • Ham, Y.-G., J.-H. Kim, and J.-J. Luo, 2019: Deep learning for multi-year ENSO forecasts. Nature, 573, 568572, https://doi.org/10.1038/s41586-019-1559-7.

    • Search Google Scholar
    • Export Citation
  • Hamidi, O., J. Poorolajal, M. Sadeghifar, H. Abbasi, Z. Maryanaji, H. R. Faridi, and L. Tapak, 2015: A comparative study of support vector machines and artificial neural networks for predicting precipitation in Iran. Theor. Appl. Climatol., 119, 723731, https://doi.org/10.1007/s00704-014-1141-z.

    • Search Google Scholar
    • Export Citation
  • Hilburn, K. A., I. Ebert-Uphoff, and S. D. Miller, 2021: Development and interpretation of a neural-network-based synthetic radar reflectivity estimator using GOES-R satellite observations. J. Appl. Meteor. Climatol., 60, 321, https://doi.org/10.1175/JAMC-D-20-0084.1.

    • Search Google Scholar
    • Export Citation
  • Ingsrisawang, L., I. Supawadee, S. Saisuda, A. Prasert, and K. Warawut, 2008: Machine learning techniques for short-term rain forecasting system in the northeastern part of Thailand. Int. J. Comput. Electr. Autom. Control Inf. Eng., 2, 14221427.

    • Search Google Scholar
    • Export Citation
  • Jing, W., Y. Yang, X. Yue, and X. Zhao, 2016: A comparison of different regression algorithms for downscaling monthly satellite-based precipitation over North China. Remote Sens., 8, 835, https://doi.org/10.3390/rs8100835.

    • Search Google Scholar
    • Export Citation
  • Kakogeorgiou, I., and K. Karantzalos, 2021: Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing. Int. J. Appl. Earth Obs. Geoinf., 103, 102520, https://doi.org/10.1016/j.jag.2021.102520.

    • Search Google Scholar
    • Export Citation
  • Kalnay, E., and Coauthors, 1996: The NCEP/NCAR 40-Year Reanalysis Project. Bull. Amer. Meteor. Soc., 77, 437471, https://doi.org/10.1175/1520-0477(1996)077<0437:TNYRP>2.0.CO;2.

    • Search Google Scholar
    • Export Citation
  • Kistler, R., and Coauthors, 2001: The NCEP–NCAR 50-Year Reanalysis: Monthly means CD-ROM and documentation. Bull. Amer. Meteor. Soc., 82, 247268.

    • Search Google Scholar
    • Export Citation
  • Lagerquist, R., A. McGovern, and D. J. Gagne II, 2019: Deep learning for spatially explicit prediction of synoptic-scale fronts. Wea. Forecasting, 34, 11371160, https://doi.org/10.1175/WAF-D-18-0183.1.

    • Search Google Scholar
    • Export Citation
  • Li, H., P. Zhai, Y. Chen, and E. Lu, 2018: Potential influence of the East Asia–Pacific teleconnection pattern on persistent precipitation in South China: Implications of atypical Yangtze River valley cases. Wea. Forecasting, 33, 267282, https://doi.org/10.1175/WAF-D-17-0011.1.

    • Search Google Scholar
    • Export Citation
  • Li, W., B. Pan, J. Xia, and Q. Duan, 2022: Convolutional neural network-based statistical post-processing of ensemble precipitation forecasts. J. Hydrol., 605, 127301, https://doi.org/10.1016/j.jhydrol.2021.127301.

    • Search Google Scholar
    • Export Citation
  • Lu, X., Q. Li, W. Zhao, A. Xiao, G. Li, and Z. Yu, 2021: Spatiotemporal characteristics of rainfall in South China from 1967 to 2018. J. Appl. Meteor. Climatol., 60, 13331345, https://doi.org/10.1175/JAMC-D-20-0191.1.

    • Search Google Scholar
    • Export Citation
  • Luo, Y., H. Wang, R. Zhang, W. Qian, and Z. Luo, 2013: Comparison of rainfall characteristics and convective properties of monsoon precipitation systems over South China and the Yangtze and Huai river basin. J. Climate, 26, 110132, https://doi.org/10.1175/JCLI-D-12-00100.1.

    • Search Google Scholar
    • Export Citation
  • Ma, Z., H. Kang, X. Tan, W. F. Jintao Xu, Y. He, and Y. Hong, 2018: Comparisons of spatially downscaling TMPA and IMERG over the Tibetan Plateau. Remote Sens., 10, 1883, https://doi.org/10.3390/rs10121883.

    • Search Google Scholar
    • Export Citation
  • Mei, Y., V. Maggioni, P. Houser, Y. Xue, and T. Rouf, 2020: A nonparametric statistical technique for spatial downscaling of precipitation over high mountain Asia. Water Resour. Res., 56, e2020WR027472, https://doi.org/10.1029/2020WR027472.

    • Search Google Scholar
    • Export Citation
  • Ouyang, Q., W. Lu, X. Xin, Y. Zhang, W. Cheng, and T. Yu, 2016: Monthly rainfall forecasting using EEMD-SVR based on phase-space reconstruction. Water Resour. Manage., 30, 23112325, https://doi.org/10.1007/s11269-016-1288-8.

    • Search Google Scholar
    • Export Citation
  • Pan, B., K. Hsu, A. AghaKouchak, and S. Sorooshian, 2019: Improving precipitation estimation using convolutional neural network. Water Resour. Res., 55, 23012321, https://doi.org/10.1029/2018WR024090.

    • Search Google Scholar
    • Export Citation
  • Panigrahi, S., A. Nanda, and T. Swarnkar, 2021: A survey on transfer learning. Intelligent and Cloud Computing, Smart Innovation Systems and Technologies, Vol. 194, Springer, 781–789.

  • Pedregosa, F., and Coauthors, 2011: Scikit-learn: Machine learning in Python. J. Mach. Learn. Res., 12, 28252830, https://jmlr.org/papers/volume12/pedregosa11a/pedregosa11a.pdf.

    • Search Google Scholar
    • Export Citation
  • Pegion, K., E. J. Becker, and B. P. Kirtman, 2022: Understanding predictability of daily southeast U.S. precipitation using explainable machine learning. Artif. Intell. Earth Syst., 1, e220011, https://doi.org/10.1175/AIES-D-22-0011.1.

    • Search Google Scholar
    • Export Citation
  • Ramseyer, C. A., and T. L. Mote, 2016: Atmospheric controls on Puerto Rico precipitation using artificial neural networks. Climate Dyn., 47, 25152526, https://doi.org/10.1007/s00382-016-2980-3.

    • Search Google Scholar
    • Export Citation
  • Sachindra, D. A., and B. J. C. Perera, 2016: Statistical downscaling of general circulation model outputs to precipitation accounting for non-stationarities in predictor-predictand relationships. PLOS ONE, 11, e0168701, https://doi.org/10.1371/journal.pone.0168701.

    • Search Google Scholar
    • Export Citation
  • Sachindra, D. A., F. Huang, A. Barton, and B. J. C. Perera, 2014: Statistical downscaling of general circulation model outputs to precipitation—Part 1: Calibration and validation. Int. J. Climatol., 34, 32643281, https://doi.org/10.1002/joc.3914.

    • Search Google Scholar
    • Export Citation
  • Sachindra, D. A., K. Ahmed, M. M. Rashid, S. Shahid, and B. J. C. Perera, 2018: Statistical downscaling of precipitation using machine learning techniques. Atmos. Res., 212, 240258, https://doi.org/10.1016/j.atmosres.2018.05.022.

    • Search Google Scholar
    • Export Citation
  • Selvaraju, R. R., M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, 2017: Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proc. IEEE Int. Conf. on Computer Vision, Venice, Italy, Institute of Electrical and Electronics Engineers, 618–626, https://doi.org/10.1109/ICCV.2017.74.

  • Shen, Z., and B. Yong, 2021: Downscaling the GPM-based satellite precipitation retrievals using gradient boosting decision tree approach over Mainland China. J. Hydrol., 602, 126803, https://doi.org/10.1016/j.jhydrol.2021.126803.

    • Search Google Scholar
    • Export Citation
  • Shenify, M., D. A. Seyed, M. Gocić, T. R. Surya, A. W. A. Wahid, G. Abdullah, S. Shahaboddin, and P. Dalibor, 2016: Precipitation estimation using support vector machine with discrete wavelet transform. Water Resour. Manage., 30, 641652, https://doi.org/10.1007/s11269-015-1182-9.

    • Search Google Scholar
    • Export Citation
  • Shi, X., Z. Gao, L. Lausen, H. Wang, D.-Y. Yeung, W.-k. Wong, and W.-c. Woo, 2017: Deep learning for precipitation nowcasting: A benchmark and A new model. arXiv, 1706.03458v2, https://doi.org/10.48550/arXiv.1706.03458.

  • Silva, S. J., C. A. Keller, and J. Hardin, 2022: Using an explainable machine learning approach to characterize earth system model errors: Application of SHAP analysis to modeling lightning flash occurrence. J. Adv. Model. Earth Syst., 14, e2021MS002881, https://doi.org/10.1029/2021MS002881.

    • Search Google Scholar
    • Export Citation
  • Simonyan, K., and A. Zisserman, 2014: Very deep convolutional networks for large-scale image recognition. arXiv, 1409.1556v6, https://doi.org/10.48550/arXiv.1409.1556.

  • Springenberg, J. T., A. Dosovitskiy, T. Brox, and M. Riedmiller, 2015: Striving for simplicity: The all convolutional net. arXiv, 1412.6806v3, https://doi.org/10.48550/arXiv.1412.6806.

  • Su, S., Z. Cui, W. Guo, Z. Zhang, and W. Yu, 2022: Explainable analysis of deep learning methods for SAR image classification. 2022 IEEE Int. Geoscience and Remote Sensing Symp., Kuala Lumpur, Malaysia, Institute of Electrical and Electronics Engineers, 2570–2573, https://doi.org/10.1109/IGARSS46834.2022.9883815.

  • Sun, L., and Y. Lan, 2021: Statistical downscaling of daily temperature and precipitation over china using deep learning neural models: Localization and comparison with other methods. Int. J. Climatol., 41, 11281147, https://doi.org/10.1002/joc.6769.

    • Search Google Scholar
    • Export Citation
  • Tianjia, L., R. W. Schmitt, and L. Li, 2018: Global search for autumn-lead sea surface salinity predictors of winter precipitation in southwestern United States. Geophys. Res. Lett., 45, 84458454, https://doi.org/10.1029/2018GL079293.

    • Search Google Scholar
    • Export Citation
  • Toms, B. A., E. A. Barnes, and I. Ebert-Uphoff, 2020: Physically interpretable neural networks for the geosciences: Applications to Earth system variability. J. Adv. Model. Earth Syst., 12, e2019MS002002, https://doi.org/10.1029/2019MS002002.

    • Search Google Scholar
    • Export Citation
  • Tong, X., Z. Yan, J. Xia, and X. Lou, 2019: Decisive atmospheric circulation indices for July–August precipitation in North China based on tree models. J. Hydrometeor., 20, 17071720, https://doi.org/10.1175/JHM-D-19-0045.1.

    • Search Google Scholar
    • Export Citation
  • Wang, L., K. A. Scott, L. Xu, and D. A. Clausi, 2016: Sea ice concentration estimation during melt from dual-pol SAR scenes using deep convolutional neural networks: A case study. IEEE Trans. Geosci. Remote Sens., 54, 45244533, https://doi.org/10.1109/TGRS.2016.2543660.

    • Search Google Scholar
    • Export Citation
  • Wimmers, A., C. Velden, and J. H. Cossuth, 2019: Using deep learning to estimate tropical cyclone intensity from satellite passive microwave imagery. Mon. Wea. Rev., 147, 22612282, https://doi.org/10.1175/MWR-D-18-0391.1.

    • Search Google Scholar
    • Export Citation
  • Zhang, J., H. Fan, D. He, and J. Chen, 2019: Integrating precipitation zoning with random forest regression for the spatial downscaling of satellite-based precipitation: A case study of the Lancang–Mekong River basin. Int. J. Climatol., 39, 39473961, https://doi.org/10.1002/joc.6050.

    • Search Google Scholar
    • Export Citation
  • Zhou, B., A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, 2016: Learning deep features for discriminative localization. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, Institute of Electrical and Electronics Engineers, 2921–2929, https://doi.org/10.1109/CVPR.2016.319.

  • Zhuang, F., Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, and Q. He, 2021: A comprehensive survey on transfer learning. Proc. IEEE, 109, 4376, https://doi.org/10.1109/JPROC.2020.3004555.

    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 251 251 70
Full Text Views 89 89 8
PDF Downloads 102 102 8