Deep Learning Approaches to Spatial Downscaling of GRACE Terrestrial Water Storage Products Using EALCO Model Over Canada

2021 ◽  
pp. 1-19
Author(s):  
Hongjie He ◽  
Ke Yang ◽  
Shusen Wang ◽  
Hasti Andon Petrosians ◽  
Ming Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Water Storage ◽  
Learning Approaches ◽  
Terrestrial Water Storage ◽  
Terrestrial Water ◽  
Storage Products ◽  
Spatial Downscaling

scholarly journals Self‐Validating Deep Learning for Recovering Terrestrial Water Storage From Gravity and Altimetry Measurements

2020 ◽  
Vol 47 (17) ◽  
Author(s):  
Christopher Irrgang ◽  
Jan Saynisch‐Wagner ◽  
Robert Dill ◽  
Eva Boergens ◽  
Maik Thomas
Keyword(s):  
Deep Learning ◽  
Water Storage ◽  
Terrestrial Water Storage ◽  
Terrestrial Water

scholarly journals Improving the Spatial Resolution of GRACE-Derived Terrestrial Water Storage Changes in Small Areas Using the Machine Learning Spatial Downscaling Method

2021 ◽  
Vol 13 (23) ◽  
pp. 4760
Author(s):  
Zhiwei Chen ◽  
Wei Zheng ◽  
Wenjie Yin ◽  
Xiaoping Li ◽  
Gangqiang Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Spatial Resolution ◽  
Water Storage ◽  
Small Scale ◽  
Terrestrial Water Storage ◽  
Coarse Resolution ◽  
Downscaling Method ◽  
Before And After ◽  
Terrestrial Water ◽  
Spatial Downscaling

Gravity Recovery and Climate Experiment (GRACE) satellites can effectively monitor terrestrial water storage (TWS) changes in large-scale areas. However, due to the coarse resolution of GRACE products, there is still a large number of deficiencies that need to be considered when investigating TWS changes in small-scale areas. Hence, it is necessary to downscale the GRACE products with a coarse resolution. First, in order to solve this problem, the present study employs modeling windows of different sizes (Window Size, WS) combined with multiple machine learning algorithms to develop a new machine learning spatial downscaling method (MLSDM) in the spatial dimension. Second, The MLSDM is used to improve the spatial resolution of GRACE observations from 0.5° to 0.25°, which is applied to Guantao County. The present study has verified the downscaling accuracy of the model developed through the combination of WS3, WS5, WS7, and WS9 and jointed with Random Forest (RF), Extra Tree Regressor (ETR), Adaptive Boosting Regressor (ABR), and Gradient Boosting Regressor (GBR) algorithms. The analysis shows that the accuracy of each combined model is improved after adding the residuals to the high-resolution downscaled results. In each modeling window, the accuracy of RF is better than that of ETR, ABR, and GBR. Additionally, compared to the changes in the TWS time series that are derived by the model before and after downscaling, the results indicate that the downscaling accuracy of WS5 is slightly more superior compared to that of WS3, WS7, and WS9. Third, the spatial resolution of the GRACE data was increased from 0.5° to 0.05° by integrating the WS5 and RF algorithm. The results are as follows: (1) The TWS (GWS) changes before and after downscaling are consistent, decreasing at −20.86 mm/yr and −21.79 mm/yr (−14.53 mm/yr and −15.46 mm/yr), respectively, and the Nash–Sutcliffe efficiency coefficient (NSE) and correlation coefficient (CC) values of both are above 0.99 (0.98). (2) The CC between the 80% deep groundwater well data and the downscaled GWS changes are above 0.70. Overall, the MLSDM can not only effectively improve the spatial resolution of GRACE products but also can preserve the spatial distribution of the original signal, which can provide a reference scheme for research focusing on the downscaling of GRACE products.

scholarly journals A time series assessment of terrestrial water storage and its relationship with hydro-meteorological factors in Gilgit-Baltistan region using GRACE observation and GLDAS-Noah model

2021 ◽  
Vol 3 (5) ◽  
Author(s):  
Dostdar Hussain ◽  
Aftab Ahmed Khan ◽  
Syed Najam Ul Hassan ◽  
Syed Ali Asad Naqvi ◽  
Akhtar Jamil
Keyword(s):  
Snow Water Equivalent ◽  
Gravity Data ◽  
Water Storage ◽  
Indus Basin ◽  
Flood Hazards ◽  
Terrestrial Water Storage ◽  
Satellite Gravity ◽  
Terrestrial Water ◽  
Gilgit Baltistan

AbstractMountains regions like Gilgit-Baltistan (GB) province of Pakistan are solely dependent on seasonal snow and glacier melt. In Indus basin which forms in GB, there is a need to manage water in a sustainable way for the livelihood and economic activities of the downstream population. It is important to monitor water resources that include glaciers, snow-covered area, lakes, etc., besides traditional hydrological (point-based measurements by using the gauging station) and remote sensing-based studies (traditional satellite-based observations provide terrestrial water storage (TWS) change within few centimeters from the earth’s surface); the TWS anomalies (TWSA) for the GB region are not investigated. In this study, the TWSA in GB region is considered for the period of 13 years (from January 2003 to December 2016). Gravity Recovery and Climate Experiment (GRACE) level 2 monthly data from three processing centers, namely Centre for Space Research (CSR), German Research Center for Geosciences (GFZ), and Jet Propulsion Laboratory (JPL), System Global Land Data Assimilation System (GLDAS)-driven Noah model, and in situ precipitation data from weather stations, were used for the study investigation. GRACE can help to forecast the possible trends of increasing or decreasing TWS with high accuracy as compared to the past studies, which do not use satellite gravity data. Our results indicate that TWS shows a decreasing trend estimated by GRACE (CSR, GFZ, and JPL) and GLDAS-Noah model, but the trend is not significant statistically. The annual amplitude of GLDAS-Noah is greater than GRACE signal. Mean monthly analysis of TWSA indicates that TWS reaches its maximum in April, while it reaches its minimum in October. Furthermore, Spearman’s rank correlation is determined between GRACE estimated TWS with precipitation, soil moisture (SM) and snow water equivalent (SWE). We also assess the factors, SM and SWE which are the most efficient parameters producing GRACE TWS signal in the study area. In future, our results with the support of more in situ data can be helpful for conservation of natural resources and to manage flood hazards, droughts, and water distribution for the mountain regions.

scholarly journals Evaluation of hydrological and cryospheric angular momentum estimates based on GRACE, GRACE-FO and SLR data for their contributions to polar motion excitation

2021 ◽  
Vol 73 (1) ◽  
Author(s):  
Justyna Śliwińska ◽  
Jolanta Nastula ◽  
Małgorzata Wińska
Keyword(s):  
Angular Momentum ◽  
Spherical Harmonic ◽  
Polar Motion ◽  
Spectral Band ◽  
Water Storage ◽  
Terrestrial Water Storage ◽  
Terrestrial Water ◽  
High Consistency ◽  
Polar Motion Excitation

AbstractIn geodesy, a key application of data from the Gravity Recovery and Climate Experiment (GRACE), GRACE Follow-On (GRACE-FO), and Satellite Laser Ranging (SLR) is an interpretation of changes in polar motion excitation due to variations in the Earth’s surficial fluids, especially in the continental water, snow, and ice. Such impacts are usually examined by computing hydrological and cryospheric polar motion excitation (hydrological and cryospheric angular momentum, HAM/CAM). Three types of GRACE and GRACE-FO data can be used to determine HAM/CAM, namely degree-2 order-1 spherical harmonic coefficients of geopotential, gridded terrestrial water storage anomalies computed from spherical harmonic coefficients, and terrestrial water storage anomalies obtained from mascon solutions. This study compares HAM/CAM computed from these three kinds of gravimetric data. A comparison of GRACE-based excitation series with HAM/CAM obtained from SLR is also provided. A validation of different HAM/CAM estimates is conducted here using the so-called geodetic residual time series (GAO), which describes the hydrological and cryospheric signal in the observed polar motion excitation. Our analysis of GRACE mission data indicates that the use of mascon solutions provides higher consistency between HAM/CAM and GAO than the use of other datasets, especially in the seasonal spectral band. These conclusions are confirmed by the results obtained for data from first 2 years of GRACE-FO. Overall, after 2 years from the start of GRACE-FO, the high consistency between HAM/CAM and GAO that was achieved during the best GRACE period has not yet been repeated. However, it should be remembered that with the systematic appearance of subsequent GRACE-FO observations, this quality can be expected to increase. SLR data can be used for determination of HAM/CAM to fill the one-year-long data gap between the end of GRACE and the start of the GRACE-FO mission. In addition, SLR series could be particularly useful in determination of HAM/CAM in the non-seasonal spectral band. Despite its low seasonal amplitudes, SLR-based HAM/CAM provides high phase consistency with GAO for annual and semiannual oscillation.

Use of a multiscalar GRACE-based standardized terrestrial water storage index for assessing global hydrological droughts

2021 ◽  
Vol 603 ◽  
pp. 126871
Author(s):  
Aihong Cui ◽  
Jianfeng Li ◽  
Qiming Zhou ◽  
Ruoxin Zhu ◽  
Huizeng Liu ◽  
...  
Keyword(s):  
Water Storage ◽  
Terrestrial Water Storage ◽  
Terrestrial Water ◽  
Hydrological Droughts

Links between global terrestrial water storage and large-scale modes of climatic variability

2021 ◽  
pp. 126419
Author(s):  
Lanlan Guo ◽  
TieWei Li ◽  
Deliang Chen ◽  
Junguo Liu ◽  
Bin He ◽  
...  
Keyword(s):  
Large Scale ◽  
Climatic Variability ◽  
Water Storage ◽  
Terrestrial Water Storage ◽  
Terrestrial Water
Sign in / Sign up

Export Citation Format

Share Document