Synergizing AI and Physical Expertise to Close the Water Budget from Satellite Data

Filipe Aires aLERMA, CNRS/Observatoire de Paris/Sorbonne University, Paris, France

Search for other papers by Filipe Aires in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0002-9426-866X
and
Victor Pellet aLERMA, CNRS/Observatoire de Paris/Sorbonne University, Paris, France

Search for other papers by Victor Pellet in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

A multitude of Earth observation (EO) products are available for monitoring the terrestrial water cycle. These EO datasets have resulted in a multiplicity of datasets for the same geophysical variable. Furthermore, inconsistencies between the water components prevent the water budget closure. A maximum a posteriori (MAP) estimator has been used in the past to optimally combine EO datasets. This framework has many advantages, but it can only be utilized when all four water components are available (precipitation P, evapotranspiration E, total water storage change dS, and river discharge R) and solely at the basin scale. By combining physical expertise with the statistical inference of neural networks (NNs), we designed a custom deep learning scheme to optimize EO data. This hybrid approach benefits from the optimization capabilities of NNs to estimate the parameters of interconnected physical modules. The NN is trained using basin-scale data (from MAP results) over 38 basins to obtain optimized EOs globally. The NN integration offers several enhancements compared to MAP: Independent calibration/mixing models are obtained with imbalance reduction and optimization at the pixel level, and environmental variables can be used to extrapolate results to unmonitored regions. The NN integration enables combining EO estimates of individual water components (P, E, dS, and R) in a hydrologically coherent manner, resulting in a significant decrease in the water budget imbalance at the global scale. Mean imbalance errors can be significant on raw EOs, but they become negligible when EOs are integrated. The standard deviation (STD) of the imbalance is around 26 mm month−1 for raw EOs, and they decrease to 21 when combined and 19 when mixed.

© 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 author: Filipe Aires, filipe.aires@obspm.fr

Abstract

A multitude of Earth observation (EO) products are available for monitoring the terrestrial water cycle. These EO datasets have resulted in a multiplicity of datasets for the same geophysical variable. Furthermore, inconsistencies between the water components prevent the water budget closure. A maximum a posteriori (MAP) estimator has been used in the past to optimally combine EO datasets. This framework has many advantages, but it can only be utilized when all four water components are available (precipitation P, evapotranspiration E, total water storage change dS, and river discharge R) and solely at the basin scale. By combining physical expertise with the statistical inference of neural networks (NNs), we designed a custom deep learning scheme to optimize EO data. This hybrid approach benefits from the optimization capabilities of NNs to estimate the parameters of interconnected physical modules. The NN is trained using basin-scale data (from MAP results) over 38 basins to obtain optimized EOs globally. The NN integration offers several enhancements compared to MAP: Independent calibration/mixing models are obtained with imbalance reduction and optimization at the pixel level, and environmental variables can be used to extrapolate results to unmonitored regions. The NN integration enables combining EO estimates of individual water components (P, E, dS, and R) in a hydrologically coherent manner, resulting in a significant decrease in the water budget imbalance at the global scale. Mean imbalance errors can be significant on raw EOs, but they become negligible when EOs are integrated. The standard deviation (STD) of the imbalance is around 26 mm month−1 for raw EOs, and they decrease to 21 when combined and 19 when mixed.

© 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 author: Filipe Aires, filipe.aires@obspm.fr
Save
  • Abolafia-Rosenzweig, R., M. Pan, J. L. Zeng, and B. Livneh, 2021: Remotely sensed ensembles of the terrestrial water budget over major global river basins: An assessment of three closure techniques. Remote Sens. Environ., 252, 112191, https://doi.org/10.1016/j.rse.2020.112191.

    • Search Google Scholar
    • Export Citation
  • Aires, F., 2014: Combining datasets of satellite-retrieved products. Part I: Methodology and water budget closure. J. Hydrometeor., 15, 16771691, https://doi.org/10.1175/JHM-D-13-0148.1.

    • Search Google Scholar
    • Export Citation
  • Aires, F., M. Schmitt, A. Chédin, and N. Scott, 1999: The “weight smoothing” regularization of MLP for Jacobian stabilization. IEEE Trans. Neural Networks, 10, 15021510, https://doi.org/10.1109/72.809096.

    • Search Google Scholar
    • Export Citation
  • Aires, F., A. Chédin, N. A. Scott, and W. B. Rossow, 2002: A regularized neural net approach for retrieval of atmospheric and surface temperatures with the IASI instrument. J. Appl. Meteor., 41, 144159, https://doi.org/10.1175/1520-0450(2002)041<0144:ARNNAF>2.0.CO;2.

    • Search Google Scholar
    • Export Citation
  • Anderson, S., and V. Radić, 2022: Evaluation and interpretation of convolutional long short-term memory networks for regional hydrological modelling. Hydrol. Earth Syst. Sci., 26, 795825, https://doi.org/10.5194/hess-26-795-2022.

    • Search Google Scholar
    • Export Citation
  • Ba, Y., G. Zhao, and A. Kadambi, 2019: Blending diverse physical priors with neural networks. arXiv, 1910.00201v1, https://doi.org/10.48550/arXiv.1910.00201.

  • Beck, H. E., A. I. J. M. van Dijk, V. Levizzani, J. Schellekens, D. G. Miralles, B. Martens, and A. d. Roo, 2017: MSWEP: 3-hourly 0.25° global gridded precipitation (1979–2015) by merging gauge, satellite, and reanalysis data. Hydrol. Earth Syst. Sci., 21, 589615, https://doi.org/10.5194/hess-21-589-2017.

    • Search Google Scholar
    • Export Citation
  • Bulles-Jaramillo, A., and G. Poveda, 2018: Conjoint analysis of surface and atmospheric water balances in the Andes-Amazon system. Water Resour. Res., 54, 34723489, https://doi.org/10.1029/2017WR021338.

    • Search Google Scholar
    • Export Citation
  • Dahle, C., F. Flechtner, C. Gruber, D. König, R. König, G. Michalak, and K.-H. Neumayer, 2013: GFZ GRACE level-2 processing standards document for level-2 product release 0005. Scientific Tech. Rep. STR12/02, 25 pp., https://gfzpublic.gfz-potsdam.de/rest/items/item_61197_3/component/file_61227/content.

  • Do, H. X., L. Gudmundsson, M. Leonard, and S. Westra, 2018: The Global Streamflow Indices and Metadata archive (GSIM) – Part 1: The production of a daily streamflow archive and metadata. Earth Syst. Sci. Data, 10, 765785, https://doi.org/10.5194/essd-10-765-2018.

    • Search Google Scholar
    • Export Citation
  • Dorigo, W., and Coauthors, 2021: Closing the water cycle from observations across scales where do we stand? Bull. Amer. Meteor. Soc., 102, E1897E1935, https://doi.org/10.1175/BAMS-D-19-0316.1.

    • Search Google Scholar
    • Export Citation
  • Dramsch, J. S., 2020: Chapter one - 70 years of machine learning in geoscience in review. Adv. Geophys., 61, 155, https://doi.org/10.1016/bs.agph.2020.08.002.

    • Search Google Scholar
    • Export Citation
  • Durand, M., and Coauthors, 2016: An intercomparison of remote sensing river discharge estimation algorithms from measurements of river height, width, and slope. Water Resour. Res., 52, 45274549, https://doi.org/10.1002/2015WR018434.

    • Search Google Scholar
    • Export Citation
  • Fayek, H. M., M. Lech, and L. Cavedon, 2017: Evaluating deep learning architectures for speech emotion recognition. Neural Networks, 92, 6068, https://doi.org/10.1016/j.neunet.2017.02.013.

    • Search Google Scholar
    • Export Citation
  • Feng, D., J. Liu, K. Lawson, and C. Shen, 2022: Differentiable, learnable, regionalized process-based models with multiphysical outputs can approach state-of-the-art hydrologic prediction accuracy. Water Resour. Res., 58, e2022WR032404, https://doi.org/10.1029/2022WR032404.

    • Search Google Scholar
    • Export Citation
  • Fu, L.-L., D. Alsdorf, R. Morrow, E. Rodriguez, and N. Mognard, 2012: SWOT: The Surface Water and Ocean Topography Mission - Wide-Swath Altimetric Measurement of Water Elevation on Earth, https://swot.jpl.nasa.gov/system/documents/files/2179_SWOT_MSD_final-3-26-12.pdf.

  • He, L., J. Zhu, J. Li, D. Meng, J. Chanussot, and A. Plaza, 2020: Spectral-fidelity convolutional neural networks for hyperspectral pansharpening. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 13, 58985914, https://doi.org/10.1109/JSTARS.2020.3025040.

    • Search Google Scholar
    • Export Citation
  • Hersbach, H., and Coauthors, 2019: Global reanalysis: Goodbye ERA-Interim, hello ERA5. ECMWF Newsletter, No. 159, ECMWF, Reading, United Kingdom, 17–24, https://doi.org/10.21957/vf291hehd7.

  • Hobeichi, S., G. Abramowitz, and J. Evans, 2020: Conserving Land–Atmosphere Synthesis Suite (CLASS). J. Climate, 33, 18211844, https://doi.org/10.1175/JCLI-D-19-0036.1.

    • Search Google Scholar
    • Export Citation
  • Huffman, G. J., and Coauthors, 2007: The TRMM Multisatellite Precipitation Analysis (TMPA): Quasi-global, multiyear, combined-sensor precipitation estimates at fine scales. J. Hydrometeor., 8, 3855, https://doi.org/10.1175/JHM560.1.

    • Search Google Scholar
    • Export Citation
  • Huffman, G. J., D. T. Bolvin, and R. F. Adler, 2016: GPCP version 1.2 one-degree daily precipitation data set. Research Data Archive at the National Center for Atmospheric Research, Computational and Information Systems Laboratory, accessed 31 January 2024, https://doi.org/10.5065/D6D50K46.

  • Jiang, S., Y. Zheng, and D. Solomatine, 2020: Improving AI system awareness of geoscience knowledge: Symbiotic integration of physical approaches and deep learning. Geophys. Res. Lett., 47, e2020GL088229, https://doi.org/10.1029/2020GL088229.

    • Search Google Scholar
    • Export Citation
  • Kratzert, F., D. Klotz, C. Brenner, K. Schulz, and M. Herrnegger, 2018: Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrol. Earth Syst. Sci., 22, 60056022, https://doi.org/10.5194/hess-22-6005-2018.

    • Search Google Scholar
    • Export Citation
  • Landerer, F. W., and S. C. Swenson, 2012: Accuracy of scaled grace terrestrial water storage estimates. Water Resour. Res., 48, W04531, https://doi.org/10.1029/2011WR011453.

    • Search Google Scholar
    • Export Citation
  • LeCun, Y., Y. Bengio, and G. Hinton, 2015: Deep learning. Nature, 521, 436444, https://doi.org/10.1038/nature14539.

  • L’Ecuyer, T. S., and Coauthors, 2015: The observed state of the energy budget in the early twenty-first century. J. Climate, 28, 83198346, https://doi.org/10.1175/JCLI-D-14-00556.1.

    • Search Google Scholar
    • Export Citation
  • Lees, T., and Coauthors, 2022: Hydrological concept formation inside long short-term memory (LSTM) networks. Hydrol. Earth Syst. Sci., 26, 30793101, https://doi.org/10.5194/hess-26-3079-2022.

    • Search Google Scholar
    • Export Citation
  • Martens, B., and Coauthors, 2017: GLEAM v3: Satellite-based land evaporation and root-zone soil moisture. Geosci. Model Dev., 10, 19031925, https://doi.org/10.5194/gmd-10-1903-2017.

    • Search Google Scholar
    • Export Citation
  • Moen, E., D. Bannon, T. Kudo, W. Graf, M. Covert, and D. V. Valen, 2019: Deep learning for cellular image analysis. Nat. Methods, 16, 12331246, https://doi.org/10.1038/s41592-019-0403-1.

    • Search Google Scholar
    • Export Citation
  • Moreira, A. A., A. L. Ruhoff, D. R. Roberti, V. de Arruda Souza, H. R. da Rochac, and R. C. D. de Paiva, 2019: Assessment of terrestrial water balance using remote sensing data in South America. J. Hydrol., 575, 131147, https://doi.org/10.1016/j.jhydrol.2019.05.021.

    • Search Google Scholar
    • Export Citation
  • Moshe, Z., A. Metzger, F. Kratzert, E. Morin, S. Nevo, G. Elidan, and R. Elyaniv, 2020: HydroNets: Leveraging river network structure and deep neural networks for hydrologic modeling. 22nd EGU General Assembly, Online, EGU2020-4135, https://doi.org/10.5194/egusphere-egu2020-4135.

  • Munier, S., and F. Aires, 2018: A new global method of satellite dataset merging and quality characterization constrained by the terrestrial water budget. Remote Sens. Environ., 205, 119130, https://doi.org/10.1016/j.rse.2017.11.008.

    • Search Google Scholar
    • Export Citation
  • Munier, S., F. Aires, S. Schlaffer, C. Prigent, F. Papa, P. Maisongrande, and M. Pan, 2014: Combining data sets of satellite-retrieved products for basin-scale water balance study: 2. Evaluation on the Mississippi Basin and closure correction model. J. Geophys. Res. Atmos., 119, 12 10012 116, https://doi.org/10.1002/2014JD021953.

    • Search Google Scholar
    • Export Citation
  • Nearing, G., and Coauthors, 2020: A deep learning architecture for conservative dynamical systems: Application to rainfall-runoff modeling, https://ai4earthscience.github.io/neurips-2020-workshop/papers/ai4earth_neurips_2020_51.pdf.

  • Pan, M., and E. F. Wood, 2006: Data assimilation for estimating the terrestrial water budget using a constrained ensemble Kalman filter. J. Hydrometeor., 7, 534547, https://doi.org/10.1175/JHM495.1.

    • Search Google Scholar
    • Export Citation
  • Pellet, V., F. Aires, A. Mariotti, and D. Fernandez-Prieto, 2018: Analyzing the Mediterranean water cycle via satellite data integration. Pure Appl. Geophys., 175, 39093937, https://doi.org/10.1007/s00024-018-1912-z.

    • Search Google Scholar
    • Export Citation
  • Pellet, V., F. Aires, S. Munier, D. F. Prieto, G. Jordá, W. A. Dorigo, J. Polcher, and L. Brocca, 2019: Integrating multiple satellite observations into a coherent dataset to monitor the full water cycle – Application to the Mediterranean region. Hydrol. Earth Syst. Sci., 23, 465491, https://doi.org/10.5194/hess-23-465-2019.

    • Search Google Scholar
    • Export Citation
  • Pellet, V., F. Aires, F. Papa, S. Munier, and B. Decharme, 2020: Long-term total water storage change from a Satellite Water Cycle reconstruction over large southern Asian basins. Hydrol. Earth Syst. Sci., 24, 30333055, https://doi.org/10.5194/hess-24-3033-2020.

    • Search Google Scholar
    • Export Citation
  • Pellet, V., F. Aires, and D. Yamazaki, 2021: Coherent satellite monitoring of the water cycle over the amazon. Part 2: Total water storage change and river discharge estimation. Water Resour. Res., 57, e2020WR028648, https://doi.org/10.1029/2020WR028648.

    • Search Google Scholar
    • Export Citation
  • Prigent, C., D. P. Lettenmaier, F. Aires, and F. Papa, 2016: Toward a high-resolution monitoring of continental surface water extent and dynamics, at global scale: From GIEMS (Global Inundation Extent from Multi-satellites) to SWOT (Surface Water Ocean Topography). Surv. Geophys., 37, 339355, https://doi.org/10.1007/s10712-015-9339-x.

    • Search Google Scholar
    • Export Citation
  • Rodell, M., and Coauthors, 2015: The observed state of the water cycle in the early twenty-first century. J. Climate, 28, 82898318, https://doi.org/10.1175/JCLI-D-14-00555.1.

    • Search Google Scholar
    • Export Citation
  • Rodgers, C. D., 2000: Inverse Methods for Atmospheric Sounding: Theory and Practice. Series on Atmospheric, Oceanic and Planetary Physics, World Scientific, 256 pp.

  • Roscher, R., B. Bohn, M. F. Duarte, and J. Garcke, 2020: Explainable machine learning for scientific insights and discoveries. IEEE Access, 8, 42 20042 216, https://doi.org/10.1109/ACCESS.2020.2976199.

    • Search Google Scholar
    • Export Citation
  • Sahoo, A. K., M. Pan, T. J. Troy, R. K. Vinukollu, J. Sheffield, and E. F. Wood, 2011: Reconciling the global terrestrial water budget using satellite remote sensing. Remote Sens. Environ., 115, 18501865, https://doi.org/10.1016/j.rse.2011.03.009.

    • Search Google Scholar
    • Export Citation
  • Shao, Z., and J. Cai, 2018: Remote sensing image fusion with deep convolutional neural network. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 11, 16561669, https://doi.org/10.1109/JSTARS.2018.2805923.

    • Search Google Scholar
    • Export Citation
  • Shao, Z., J. Cai, P. Fu, L. Hu, and T. Liu, 2019: Deep learning-based fusion of Landsat-8 and Sentinel-2 images for a harmonized surface reflectance product. Remote Sens. Environ., 235, 111425, https://doi.org/10.1016/j.rse.2019.111425.

    • Search Google Scholar
    • Export Citation
  • Shwartz-Ziv, R., and N. Tishby, 2017: Opening the black box of deep neural networks via information. arXiv, 1703.00810v3, https://doi.org/10.48550/arXiv.1703.00810.

  • Tarpanelli, A., G. Amarnath, L. Brocca, and C. Massari, 2017: Discharge estimation and forecasting by MODIS and altimetry data in Niger-Benue River. Remote Sens. Environ., 195, 96106, https://doi.org/10.1016/j.rse.2017.04.015.

    • Search Google Scholar
    • Export Citation
  • Thomas, B. F., and J. S. Famiglietti, 2019: Identifying climate-induced groundwater depletion in grace observations. Sci. Rep., 9, 4124, https://doi.org/10.1038/s41598-019-40155-y.

    • Search Google Scholar
    • Export Citation
  • Thomas, C. M., B. Dong, and K. Haines, 2020: Inverse modeling of global and regional energy and water cycle fluxes using earth observation data. J. Climate, 33, 17071723, https://doi.org/10.1175/JCLI-D-19-0343.1.

    • Search Google Scholar
    • Export Citation
  • Toms, B. A., E. A. Barnes, and I. Ebert-Uphoff, 2019: Physically interpretable neural networks for the geosciences: Applications to earth system variability. arXiv, 1912.01752v2, https://doi.org/10.48550/arXiv.1912.01752.

  • Tourian, M. J., C. Schwatke, and N. Sneeuw, 2017: River discharge estimation at daily resolution from satellite altimetry over an entire river basin. J. Hydrol., 546, 230247, https://doi.org/10.1016/j.jhydrol.2017.01.009.

    • Search Google Scholar
    • Export Citation
  • Troy, T. J., J. Sheffield, and E. F. Wood, 2011: Estimation of the terrestrial water budget over northern Eurasia through the use of multiple data sources. J. Climate, 24, 32723293, https://doi.org/10.1175/2011JCLI3936.1.

    • Search Google Scholar
    • Export Citation
  • Watkins, M. M., and D.-N. Yuan, 2014: GRACE - JPL level-2 processing standards document for level-2 product release 05.1. 1–17, https://icgem.gfz-potsdam.de/docs/L2-JPL_ProcStds_v5.1.pdf.

  • Willard, J., X. Jia, S. Xu, M. Steinbach, and V. Kumar, 2020: Integrating physics-based modeling with machine learning: A survey. arXiv, 2003.04919v4, https://doi.org/10.1145/1122445.1122456.

  • Yilmaz, M. T., T. DelSole, and P. R. Houser, 2011: Improving land data assimilation performance with a water budget constraint. J. Hydrometeor., 12, 10401055, https://doi.org/10.1175/2011JHM1346.1.

    • Search Google Scholar
    • Export Citation
  • Yin, H., Z. Guo, X. Zhang, J. Chen, and Y. Zhang, 2022: RR-former: Rainfall-runoff modeling based on transformer. J. Hydrol., 609, 127781, https://doi.org/10.1016/j.jhydrol.2022.127781.

    • Search Google Scholar
    • Export Citation
  • Zhang, Y., J. P. Arancibia, T. McVicar, F. Chiew, J. Vaze, H. Zheng, and Y. P. Wang, 2016: Monthly global observation-driven Penman-Monteith-Leuning (PML) evapotranspiration and components. CSIRO, accessed 17 August 2024, https://doi.org/10.4225/08/5719A5C48DB85.

  • Zhou, W., S. Newsam, C. Li, and Z. Shao, 2017: Learning low dimensional convolutional neural networks for high-resolution remote sensing image retrieval. Remote Sens., 9, 489, https://doi.org/10.3390/rs9050489.

    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 479 479 288
Full Text Views 70 70 40
PDF Downloads 73 73 38