This is an elementary page that collects work related to our group on hydrologic deep learning.

 

Resources

  1. Our code and benchmarks site
  2. Jupyter notebook for the first hydroDL tutorial on LSTM.

 

Notable Publications

  1. Liu, Jiangtao*, Yuchen Bian, and Chaopeng Shen. (2024). Probing the limit of hydrologic predictability with the Transformer network, Journal of Hydrology. doi: 10.1016/j.jhydrol.2024.131389
  2. Song, Yalan*, Piyaphat Chaemchuen*, Farshid Rahmani*, Wei Zhi, Li Li, Xiaofeng Liu, Elizabeth Boyer, Tadd Bindas*, Kathryn Lawson*, and Chaopeng Shen. (2024). Deep learning insights into suspended sediment concentrations across the conterminous United States: Strengths and limitations, Journal of Hydrology. doi: 10.1016/j.jhydrol.2024.131573 
  3. Song, Yalan*, Wen-Ping Tsai*, Jonah Gluck**, Alan Rhoades, Colin Zarzycki, Rachel McCrary, Kathryn Lawson*, and Chaopeng Shen. (2024). LSTM-based data integration to improve snow water equivalent prediction and diagnose error sources. Journal of Hydrometeorology. doi:10.1175/JHM-D-22-0220.1
  4. Zhi, Wei, Wenyu Ouyang, Chaopeng Shen, and Li Li. (2023). Temperature as the predominant driver of dissolved oxygen in US rivers. Nature Water. doi: 10.1038/s44221-023-00038-z
  5. Dwivedi, Dipankar, Xingyuan Chen, Chaopeng Shen, and Harihar Rajaram. (2023). Advancing AI and machine learning beyond predictive capabilities, Eos (Editor's Vox -- non-peer reviewed). doi: 10.1029/2023EO235032
  6. Saha, Gourab, Farshid Rahmani*, Cibin Raj, Chaopeng Shen, and Li Li. (2023). A deep learning-based novel approach to generate continuous daily stream nitrate concentration for nitrate data-sparse watersheds, Science of the Total Environment. doi:10.1016/j.scitotenv.2023.162930
  7. Liu, Jiangtao*, David Hughes, Farshid Rahmani*, Kathryn Lawson*, and Chaopeng Shen. (2023). Evaluating a global soil moisture dataset from a multitask model (GSM3 v1.0) for current and emerging threats to crops, Geoscientific Model Development. doi: 10.5194/gmd-16-1553-2023
  8. Sadayappan, Kayalvizhi, Devon Kerins, Chaopeng Shen, and Li Li. (2022). Riverine nitrate concentrations predominantly driven by human, climate, and soil property in the Contiguous United States. Water Research. doi: 10.1016/j.watres.2022.119295
  9. Nagendra, Savinay**, Daniel Kifer, Benjamin Mirus, Te Pei**, Kathryn Lawson*, Srikanth Banagere Manjunatha, Weixin Li*, Hien Nguyen, Tong Qiu, Sarah Tran, and Chaopeng Shen. (2022). Constructing a large-scale landslide database across heterogeneous environments using task-specific model updates, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. doi: 10.1109/JSTARS.2022.3177025
  10. Fang, Kuai*, Daniel Kifer, Dapeng Feng*, Kathryn Lawson*, and Chaopeng Shen. (2022). The data synergy effects of time-series deep learning models in hydrology, Water Resources Research. doi: 10.1029/2021WR029583
  11. Liu, Jiangtao*, Farshid Rahmani*, Kathryn Lawson*, and Chaopeng Shen. (2022). A multiscale deep learning model for soil moisture integrating satellite and in-situ data, Geophysical Research Letters. doi: 10.1029/2021GL096847 
  12. Rahmani, Farshid*, Chaopeng Shen, Samantha Oliver, Kathryn Lawson*, and Alison Appling. (2021). Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins, Hydrological Processes. doi: 10.1002/hyp.14400.
  13. Feng, Dapeng*, Kathryn Lawson*, and Chaopeng Shen. (2021). Mitigating prediction error of deep learning streamflow models in large data-sparse regions with ensemble modeling and soft data, Geophysical Research Letters. doi: 10.1029/2021GL092999
  14. Ouyang, Wenyu**, Kathryn Lawson*, Dapeng Feng*, Lei Ye, Chi Zhang, and Chaopeng Shen. (2021). Continental-scale streamflow modeling of basins with reservoirs: towards a coherent deep-learning-based strategy, Journal of Hydrology. doi: 10.1016/j.jhydrol.2021.126455
  15. Shen, Chaopeng, Xingyuan Chen, and Eric Laloy. (2021). Editorial: Broadening the use of machine learning in hydrology, Frontiers in Water -Water and Hydrocomplexity. doi: 10.3389/frwa.2021.681023
  16. Ma, Kai**, Dapeng Feng*, Kathryn Lawson*, Wen-Ping Tsai*, Chuan Liang, Xiaorong Huang, Ashutosh Sharma*, and Chaopeng Shen. (2021). Transferring hydrologic data across continents -- leveraging data-rich regions to improve hydrologic prediction in data-sparse regions, Water Resources Research. doi: 10.1029/2020WR028600
  17. Zhi, Wei, Dapeng Feng*, Wen-Ping Tsai*, Gary Sterle, Adrian Harpold, Chaopeng Shen, and Li Li. (2021). From hydrometeorology to river water quality: can a deep learning model predict dissolved oxygen at the continental scale? Environmental Science & Technology. doi: 10.1021/acs.est.0c06783
  18. Rahmani, Farshid*, Kathryn Lawson*, Wenyu Ouyang**, Alison Appling, Samantha Oliver, and Chaopeng Shen. (2021). Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data, Environmental Research Letters. doi: 10.1088/1748-9326/abd501
  19. Fang, Kuai*, Daniel Kifer, Kathryn Lawson*, and Chaopeng Shen. (2020). Evaluating the potential and challenges of an uncertainty quantification method for long short-term memory models for soil moisture predictions, Water Resources Research. doi: 10.1029/2020WR028095
  20. Feng, Dapeng*, Kuai Fang*, and Chaopeng Shen. (2020). Enhancing streamflow forecast and extracting insights using continental-scale long-short term memory networks with data integration, Water Resources Research. doi: 10.1029/2019WR026793
  21. Fang, Kuai*, and Chaopeng Shen. (2020). Near-real-time forecast of satellite-based soil moisture using long short-term memory with an adaptive data integration kernel, Journal of Hydrometeorology, JHM-D-19-0169.1. doi:10.1175/JHM-D-19-0169.1
  22. Fang, K*, M. Pan, and CP. Shen. (2018). The value of SMAP for long-term soil moisture estimation with the help of deep learning, Transactions on Geoscience and Remote Sensing, 57(4), 2221-2233. doi: 10.1109/TGRS.2018.2872131 
  23. Shen, CP.. (2018). A trans-disciplinary review of deep learning research and its relevance for water resources scientists, Water Resources Research. 54(11), 8558-8593. doi: 10.1029/2018WR022643
  24. Shen, CP., Laloy, E., Albert, A., Chang, F.-J., Elshorbagy, Bales, J., A., Ganguly, S., Hsu, K.-L., Kifer, D., Fang, Z., Fang, K.*, Li, D., Li, X., and Tsai, W.-P.* (2018). HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community, Hydrol. Earth Syst. Sci., 22, 5639–5656. doi: 10.5194/hess-22-5639-2018
  25. Shen, CP.. (2018). Deep learning: A next-generation big-data approach for hydrology, Eos (Editor's vox), 99. https://doi.org/10.1029/2018EO095649
  26. Fang, K.*, CP. Shen, D. Kifer, and X. Yang. (2017). Prolongation of SMAP to spatio-temporally seamless coverage of Continental US using a deep learning neural network, Geophysical Research Letters. doi: 10.1002/2017GL075619

 

Hydrologic Deep Learning

 

Fang, K.*, CP. Shen, D. Kifer and X. Yang, Prolongation of SMAP to Spatio-temporally Seamless Coverage of Continental US Using a Deep Learning Neural Network, Geophysical Research Letters, (2017), doi: 10.1002/2017GL075619, preprint accessible at: arXiv:1707.06611.

Here at Multi-scale Hydrology, Processes and Intelligence group, we study how mother nature works using state-of-the-art machine learning technique, especially times series deep learning. We first utilized time series deep learning to examine large, raw hydrologic data. Deep learning is not the end. It is a means to better advance our understanding of hydrology and a path toward stronger predictive capability.

We utilized the Long Short-Term Memory (LSTM) to reproduce soil moisture dynamics. We show it is not only viable but also more robust than simpler statistical methods. This research shows it is possible to hindcast soil moisture dynamics using deep learning, opening up a range of new possibilities for advancing science.

LSTM

In all tests, LSTM shows stronger performance for the test set, when compared to simple feedforward neural network, Auto-regressive models (AR), and regularized linear regression (LR).

LSTM outperforms other methods

 

LSTM is also suitable for long-term hindcasting:

long-term hindcast using LSTM