Session 7A Data-Driven Methods for Hydrological Modeling, Prediction, and Uncertainty Estimation

Tuesday, 30 January 2024: 1:45 PM-3:00 PM
318/319 (The Baltimore Convention Center)
Host: 38th Conference on Hydrology
Chairs:
Sujay V. Kumar, PhD, GSFC, HSL, Greenbelt, MD and Forrest M. Hoffman
CoChair:
Koushan Mohammadi, University of Connecticut, Department of Civil and Environmental Engineering, Storrs, CT

This session highlights advances in the development and applications of artificial intelligence (AI), machine learning (ML), and deep learning (DL) in hydrological, hydrometeorological, and hydroclimatological analysis, modeling, and predictions across a wide range of scales in space (local-to-global) and time (hours-to-decades). This includes theoretical developments in physics-informed machine learning, knowledge guided deep learning, hydroinformatics, and their applications in areas related to hydrology and water resources. We also encourage papers on the application of AI/ML/DL in improving process-based hydrological and land surface models, uncertainty quantification, and hydrologically relevant climate downscaling. Papers describing current challenges for model developers and users are also welcome, with a special interest in highlighting needs and opportunities to address national and societal challenges for living in a changing environment.

Submitters: Guiling Wang, Univ. of Connecticut, Storrs, CT; Sujay V. Kumar, Code 617 (HSL), GSFC, Greenbelt, MD; Forrest M. Hoffman, PhD, Earth System Science, Computational Earth Sciences Group, ORNL, Oak Ridge, TN and Heather Grams, Element 84, Alexandria, VA

Papers:
1:45 PM
7A.1
An approach towards including watershed traits in machine learning models for predictions in unmonitored basins (INVITED)
Charuleka Varadharajan, LBNL, Berkeley, CA; and J. D. Willard, F. Ciulla, H. Weierbach, A. R. Lima, N. Bouskill, E. Brodie, and V. Kumar

2:00 PM
7A.2
New knowledge discovery through coevolution of machine learning and process-based modelling (INVITED)
Saman Razavi, Australian National University and University of Saskatchewan, Saskatoon, SK, Canada; and K. Li

2:15 PM
7A.3
Combining physical process and deep learning models for reliable precipitation nowcasts
Shangshang Yang, Nanjing Univ., Nanjing, 32, China; and H. Yuan

2:30 PM
7A.4
Integrating data-driven methods with a complex hydrodynamic modelling system to assess sensitivity, uncertainty, and forecast performance
Nathan Michael Barber, Pennsylvania State University, University Park, PA; and A. Mejia and S. J. Greybush

2:45 PM
7A.5
Detection of Extreme Streamflow Reoccurrence Patterns over the Southeast United States
Krzysztof Raczynski, Mississippi State University, Starkville, MS; and J. Dyer

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner