Filling the gap between GRACE- and GRACE-FO-derived terrestrial water storage anomalies with Bayesian convolutional neural networks

There is an approximately one-year observation gap of terrestrial water storage anomalies (TWSAs) between the Gravity Recovery and Climate Experiment (GRACE) satellite and its successor GRACE Follow-On (GRACE-FO). This poses a challenge for water resources management, as discontinuity in the TWSA observations may introduce significant biases and uncertainties in hydrological model predictions and consequently mislead decision making. To tackle this challenge, a Bayesian convolutional neural network (BCNN) is proposed in this study to bridge this gap using climatic data as inputs. Enhanced by integrating recent advances in deep learning, BCNN can efficiently extract important features for TWSA predictions from multi-source input data. The predicted TWSAs are compared to the hydrological model outputs and three recent TWSA prediction products. Results suggest the superior performance of BCNN in bridging the gap. The extreme dry and wet events during the gap period are also successfully identified by BCNN. Plain Language Summary The remote sensing satellites Gravity Recovery and Climate Experiment (GRACE) provide valuable and accurate observations of terrestrial water storage changes at a global scale. These observations have been used widely for sustainable water resources management and understanding water cycle. However, there is an about one-year gap that the GRACE observations are missing due to a break-in period between two satellites. Filling this gap is thus of crucial significance for practical hydrological, agricultural, and ecological applications. We propose in this work a Bayesian convolutional neural network (BCNN) by leveraging recent advances in deep learning to bridge this gap based on climatic data. Results show that our BCNN achieves a state-of-the-art performance in terms of filling accuracy compared to previous studies.

[1]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[2]  Yunzhong Shen,et al.  Bridging the gap between GRACE and GRACE follow-on monthly gravity field solutions using improved multichannel singular spectrum analysis , 2021 .

[3]  Frank Flechtner,et al.  Contributions of GRACE to understanding climate change , 2019, Nature Climate Change.

[4]  Anna Klos,et al.  Reconstructing GRACE-type time-variable gravity from the Swarm satellites , 2021, Scientific reports.

[5]  C. Simmons,et al.  Review of assimilating GRACE terrestrial water storage data into hydrological models: Advances, challenges and opportunities , 2021 .

[6]  Ehsan Forootan,et al.  Comparison of Data‐Driven Techniques to Reconstruct (1992–2002) and Predict (2017–2018) GRACE‐Like Gridded Total Water Storage Changes Using Climate Inputs , 2020, Water Resources Research.

[7]  D. Long,et al.  Reconstruction of GRACE Data on Changes in Total Water Storage Over the Global Land Surface and 60 Basins , 2020, Water Resources Research.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Dennis P. Lettenmaier,et al.  How much groundwater did California's Central Valley lose during the 2012–2016 drought? , 2017 .

[10]  Hoshin V. Gupta,et al.  Why Is the Terrestrial Water Storage in Dryland Regions Declining? A Perspective Based on Gravity Recovery and Climate Experiment Satellite Observations and Noah Land Surface Model With Multiparameterization Schemes Model Simulations , 2020, Water Resources Research.

[11]  F. Landerer,et al.  Emerging trends in global freshwater availability , 2018, Nature.

[12]  B. Scanlon,et al.  Comparison of Groundwater Storage Changes From GRACE Satellites With Monitoring and Modeling of Major U.S. Aquifers , 2020, Water Resources Research.

[13]  Jeffrey P. Walker,et al.  THE GLOBAL LAND DATA ASSIMILATION SYSTEM , 2004 .

[14]  Mohamed Sultan,et al.  Forecasting GRACE Data over the African Watersheds Using Artificial Neural Networks , 2019, Remote. Sens..

[15]  Vincent Humphrey,et al.  A global reconstruction of climate‐driven subdecadal water storage variability , 2017 .

[16]  Zizhan Zhang,et al.  Groundwater Depletion in the West Liaohe River Basin, China and Its Implications Revealed by GRACE and In Situ Measurements , 2018, Remote. Sens..

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  M. Rodell,et al.  Assimilation of GRACE Terrestrial Water Storage Data into a Land Surface Model: Results for the Mississippi River Basin , 2008 .

[19]  Jichun Wu,et al.  Deep Autoregressive Neural Networks for High‐Dimensional Inverse Problems in Groundwater Contaminant Source Identification , 2018, Water Resources Research.

[20]  Dilin Wang,et al.  Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm , 2016, NIPS.

[21]  Zizhan Zhang,et al.  Long-Term Groundwater Variations in Northwest India From Satellite Gravity Measurements , 2014 .

[22]  S. Swenson,et al.  Quantifying renewable groundwater stress with GRACE , 2015, Water resources research.

[23]  Nicholas Zabaras,et al.  Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities , 2020 .

[24]  Henryk Dobslaw,et al.  Quantifying the Central European Droughts in 2018 and 2019 With GRACE Follow‐On , 2020, Geophysical Research Letters.

[25]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jichun Wu,et al.  Deep Convolutional Encoder‐Decoder Networks for Uncertainty Quantification of Dynamic Multiphase Flow in Heterogeneous Media , 2018, Water Resources Research.

[27]  Nicholas Zabaras,et al.  Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification , 2018, J. Comput. Phys..

[28]  Yun Pan,et al.  Groundwater Storage Changes in China from Satellite Gravity: An Overview , 2018, Remote. Sens..

[29]  S. Majumdar,et al.  Groundwater Storage Loss Associated With Land Subsidence in Western United States Mapped Using Machine Learning , 2020, Water Resources Research.

[30]  Chaopeng Shen,et al.  A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists , 2017, Water Resources Research.

[31]  Ke Wei,et al.  Reflections on the Catastrophic 2020 Yangtze River Basin Flooding in Southern China , 2020, Innovation.

[32]  J. Kusche,et al.  Multivariate Prediction of Total Water Storage Changes Over West Africa from Multi-Satellite Data , 2014, Surveys in Geophysics.

[33]  M. Watkins,et al.  Improved methods for observing Earth's time variable mass distribution with GRACE using spherical cap mascons , 2015 .

[34]  Sujay V. Kumar,et al.  Global GRACE Data Assimilation for Groundwater and Drought Monitoring: Advances and Challenges , 2019, Water Resources Research.

[35]  Chenghu Zhou,et al.  Can Terrestrial Water Storage Dynamics be Estimated From Climate Anomalies? , 2020, Earth and Space Science.

[36]  S. Swenson,et al.  Satellites measure recent rates of groundwater depletion in California's Central Valley , 2011 .

[37]  Yu Zhang,et al.  An Iterative ICA-Based Reconstruction Method to Produce Consistent Time-Variable Total Water Storage Fields Using GRACE and Swarm Satellite Data , 2020, Remote. Sens..

[38]  Himanshu Save,et al.  Reconstruction of GRACE Total Water Storage Through Automated Machine Learning , 2020, Water Resources Research.

[39]  Yang Hong,et al.  Drought and flood monitoring for a large karst plateau in Southwest China using extended GRACE data , 2014 .

[40]  Joachim Denzler,et al.  Deep learning and process understanding for data-driven Earth system science , 2019, Nature.

[41]  Shin‐Chan Han,et al.  Improved water storage estimates within the North China Plain by assimilating GRACE data into the CABLE model , 2020 .

[42]  R. Reedy,et al.  Global models underestimate large decadal declining and rising water storage trends relative to GRACE satellite data , 2018, Proceedings of the National Academy of Sciences.

[43]  Pierre Gentine,et al.  Coupling between the terrestrial carbon and water cycles—a review , 2019, Environmental Research Letters.

[44]  Diganta Misra.  Mish: A Self Regularized Non-Monotonic Activation Function , 2020, BMVC.

[45]  David Walling,et al.  Combining Physically Based Modeling and Deep Learning for Fusing GRACE Satellite Data: Can We Learn From Mismatch? , 2019, Water Resources Research.

[46]  Vincent Humphrey,et al.  Assessing Global Water Storage Variability from GRACE: Trends, Seasonal Cycle, Subseasonal Anomalies and Extremes , 2016, Surveys in Geophysics.

[47]  W. Feng,et al.  Evaluation of groundwater depletion in North China using the Gravity Recovery and Climate Experiment (GRACE) data and ground‐based measurements , 2013 .

[48]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[49]  Vincent Humphrey,et al.  GRACE-REC: a reconstruction of climate-driven water storage changes over the last century , 2019, Earth System Science Data.