H006
Advances in Data Assimilation, Data Mining, and Data Fusion in Earth System Modeling and Applications

Session ID#: 162206

Session Description:
Data learning approaches, including data assimilation, data mining, and data fusion, have recently garnered significant attention in a wide range of earth science applications, including hydrology, due to progress in satellite technologies and Earth observations, which provided unprecedented data at the global scale and great possibility to study different aspects of land surface and subsurface processes. This opportunity paves the way for improving the accuracy and reliability of model forecasts and projections under climate change which enhance non-stationarity and uncertainty of model predictions.         

This session will be devoted to the methodological development and applications of data assimilation (i.e., sequential and variational techniques), data mining (e.g., machine learning and deep learning, association learning, clustering, and classification analysis), and data fusion techniques in improving our understanding of different aspects of surface and subsurface hydrology at different spatial and temporal scales. We encourage studies with a focus on solving inverse problems, predictability, and uncertainty quantification using these approaches while utilizing remotely sensed satellite or in-situ observations and handling computational complexity of DA using High-Performance Computing. We particularly welcome contributions on  coupled data assimilation, data mining, and data fusion for different elements of Earth systems including precipitation, evapotranspiration, soil, snow, vegetation, and water bodies that can be used in understanding, characterizing, estimating or predicting hydroclimate extremes.

Index Terms:

1805 Computational hydrology [HYDROLOGY]
1817 Extreme events [HYDROLOGY]
1847 Modeling [HYDROLOGY]
1873 Uncertainty assessment [HYDROLOGY]

Primary Convener:  Peyman Abbaszadeh, Princeton University, Department of Civil and Environmental Engineering, Princeton, NJ, United States
Conveners:  Sujay V Kumar, NASA Goddard Space Flight Center, Greenbelt, United States, Harrie-Jan Hendricks Franssen, Forschungszentrum Jülich GmbH, Julich, Germany and Hamid Moradkhani, The University of Alabama, Center for Complex Hydrosystems Research, Tuscaloosa, United States
 
Dynamic Covariance Matrix Generation Approaches for Ensemble Optimal Interpolation Implementation in a Distributed Hydrological Model (1045301)
Manoj Khaniya1, Yasuto Tachikawa2, Takahiro Sayama3 and Sunmin Kim2, (1)Kyoto University, Kyoto, Japan, (2)Kyoto University, Department of Civil and Earth Resources Engineering, Graduate School of Engineering, Kyoto, Japan, (3)Disaster Prevention Research Institute, Kyoto University, Kyoto, Japan
 
Deep Learning from Model Errors (Invited) (1052859)
Stefan J Kollet, Research Centre Juelich, Agrosphere (IBG-3), Institute of Bio- and Geosciences, Juelich, Germany, Kaveh Patakchi Yousefi, Research Centre Juelich, Agrosphere (IBG-3), Institute for Bio- and Geosciences, Juelich, Germany and Centre for High Performance Scientific Computing in Terrestrial Systems, Geoverbund ABC/J
 
GPR-BMP-SPI: High-spatial-resolution Multi-scale SPI Datasets by Blending Multi-source Data based on Machine Learning (1058424)
Qian He, Ming Wang, Kai Liu, Bohao Li and Ziyu Jiang, Beijing Normal University, Beijing, China
 
A New Soil Moisture Bias Correction in Land Data Assimilation Using a Geolocation Independent Cumulative Distribution Function (1058613)
Mahdi Navari, NASA Goddard Space Flight Center, Greenbelt, MD, United States, Sujay V Kumar, NASA Goddard Space Flight Center, Greenbelt, United States and Sue Chen, Naval Research Laboratory, Monterey, CA, United States
 
Deep learning-based uncertainty characterization of precipitation forcing in a hydrologic data assimilation framework (1063137)
Keyhan Gavahi, University of Alabama, Civil, Construction, and Environmental Engineering, Tuscaloosa, United States and Hamid Moradkhani, The University of Alabama, Civil, Construction, and Environmental Engineering, Tuscaloosa, United States
 
A Multiple Model Adaptive System for Assimilating Satellite-based Vegetation Observations (1072253)
Viviana Maggioni1, Azbina Rahman2, Xinxuan Zhang3, Paul Houser4 and Timothy Sauer2, (1)George Mason University Fairfax, Sid and Reva Dewberry Department of Civil, Environmental, and Infrastructure Engineering, Fairfax, VA, United States, (2)George Mason University Fairfax, Fairfax, VA, United States, (3)University of Connecticut, Groton, CT, United States, (4)George Mason University Fairfax, Geography and Geoinformation Sciences, Fairfax, VA, United States
 
Mapping Evapotranspiration and Recharge from Near Surface State Observations and Quantifying Their Relationship with the Atmospheric and Environmental Variables (1073428)
Asif Mahmood and Leila Farhadi, George Washington University, Washington, DC, United States
 
Ensemble U-Net Kalman Filter: Predicting Ensemble Covariances with Deep Learning (1073929)
Feiyu Lu, Princeton University, Princeton, NJ, United States; NOAA/Geophysical Fluid Dynamics Laboratory, Princeton, United States
 
Four-Dimensional Super-Resolution Data Assimilation (4D-SRDA) (1087003)
Yuki Yasuda and Ryo Onishi Prof, Tokyo Institute of Technology, Global Scientific Information and Computing Center, Tokyo, Japan
 
Monitoring CONUS River Sediment Concentration Through Landsat, Sentinel, and MODIS Satellite Sensor Fusion (1093046)
Elisa Friedmann, University of Massachusetts Amherst, Amherst, MA, United States, Colin J Gleason, University of Massachusetts Amherst, Civil & Environmental Engineering, Amherst, MA, United States and Dongmei Feng, University of Cincinnati Main Campus, Ohio, United States
 
Two decades (2003-2021) of storage changes in the soil water and groundwater of CONUS (1105102)
Nooshin Mehrnegar1, Maike Schumacher1, Thomas Jagdhuber2,3 and Ehsan Forootan1, (1)Geodesy Group, Department of Planning, Aalborg University, Aalborg, Denmark, (2)Microwaves and Radar Institute, German Aerospace Center, Wessling, Germany, (3)Institute of Geography, University of Augsburg, Augsburg, Germany
 
Data Fusion and Mining Techniques to Map Water Use and Drought across Spatial Scales (Invited) (1116951)
Christopher Hain, NASA Marshall Space Flight Center, Earth Science Office, Huntsville, United States, Martha Anderson, USDA ARS Hydrology and Remote Sensing Laboratory, Beltsville, MD, United States, Yun Yang, University of Maryland College Park, ESSIC, College Park, MD, United States and Vikalp Mishra, University of Alabama in Huntsville, Huntsville, AL, United States
 
A deep learning-based emulator for flood forecasting in coastal areas (1130454)
Atieh Alipour, University of Alabama, Center for Complex Hydrosystems Research, Tuscaloosa, AL, United States, Peyman Abbaszadeh, Princeton University, Department of Civil and Environmental Engineering, Princeton, NJ, United States and Hamid Moradkhani, The University of Alabama, Center for Complex Hydrosystems Research, Tuscaloosa, United States
 
Fusing Remotely Sensed Dynamic Vegetation Characteristics into Hydrologic Simulation in the Upper Colorado River Basin (1131731)
Qianqiu Longyang, Arizona State University, School of Sustainable Engineering and the Built Environment, Tempe, AZ, United States and Ruijie Zeng, Arizona State University, School of Sustainable Engineering and the Built Environment, Tempe, United States
 
Forest Flows – Data Fusion of Remote Sensing and Real Time Terrestrial Data for Identifying and Quantifying the Drivers of Forest Hydrological Processes across Different Scales (1138529)
Dean Meason1, Serajis Salekin2, Priscilla Lad2, Jennifer Owens2, Yi Zhang2, Ashley Wade2, Bruce Dudley3, James Griffins3, Jing Yang4, Alec Dempster3, MS Srinivasan3, Channa Rajanayaka3, Albert Bifet5, Guilherme Cassales5, Delwyn Moller6, Mahta Moghaddam7, Robert Schafer8, Joao Palma9, Adedamola Wuraola10, Amanda Matson11 and Don White12, (1)Scion Research, Rotorua, Bay of Plenty, NEW ZEALAND, (2)Scion, Rotorua, New Zealand, (3)National Institute of Water and Atmospheric Research, Wellington, New Zealand, (4)Singapore-MIT Alliance for Research and Technology (SMART), Singapore, Singapore, (5)University of Waikato, Hamilton, New Zealand, (6)Department of Electrical Computer & Software Engineering, The University of Auckland, Auckland, New Zealand, (7)University of Southern California, Ming Hsieh Department of Electrical and Computer Engineering, Los Angeles, CA, United States, (8)XERRA, Alexandra, New Zealand, (9)MV Agroecology Research Centre, Espírito Santo, Portugal, (10)Imagr, Auckland, New Zealand, (11)Thunen Institute of Climate Smart Agriculture, Braunschweig, Germany, (12)Whitegum Forest and Natural Resources, Perth, Australia
 
Improving the Reliability of Geological Models with Pattern Classification Distribution Method (1150229)
Chen Zuo1, Juzheng Liu1, Zhuo Li1, Zhenzhen Fan2 and Chen Guo2, (1)Chang'an University, Department of Big Data Management and Applications, Xi'an, China, (2)Chang'an University, School of Information Engineering, Xi'an, China
 
An investigation of post-wildfire changes in hydrologic parameters using data assimilation in a southern California watershed (1199203)
Elsa Culler, University of Colorado at Boulder, Civil, Environmental, and Architectural Engineering, Boulder, United States and Ben Livneh, Western Water Assessment, CIRES, University of Colorado, Boulder, United States
See more of: Hydrology
<< Previous Session Proposal | Next Session Proposal >>