Advances in Statistical and Machine Learning Approaches for Hydrological Time Series Analysis
Advances in Statistical and Machine Learning Approaches for Hydrological Time Series Analysis
Session ID#: 282185
Session Description:
The utilization of hydrological time series is imperative for detecting trends and variability in water systems and for understanding system responses to extreme events such as heavy rainfall and drought. This understanding is also crucial for advancing predictive capabilities and supporting the sustainable management of water quality and quantity.
This session invites contributions on statistical, machine learning, and hybrid approaches for analyzing, forecasting, and interpreting hydrological time series. Topics may include, but are not limited to, regression, SARIMAX, state-space models, LSTM, Transformers, foundation models, knowledge-guided AI, etc. We welcome applications to streamflow, flooding, groundwater, soil moisture, surface runoff, water quality, and related hydroclimatic and environmental variables.
Index Terms:
1849 Numerical approximations and analysis [HYDROLOGY]
1872 Time series analysis [HYDROLOGY]
1873 Uncertainty assessment [HYDROLOGY]
Primary Convener: Thomas Heinze, Ruhr-University Bochum, Hydrogeology and Environmental Geology, Bochum, Germany
Conveners: Xiaofeng Liu, PhD, University of Michigan Ann Arbor, Michigan Institute for Data and AI in Society, Ann Arbor, United States and Yuan Yang, University of California San Diego, Center for Western Weather and Water Extremes (CW3E), Scripps Institution of Oceanography, La Jolla, United States
Student/Early Career Convener: Florian Lam, Ruhr-University Bochum, Hydrogeology and Environmental Geology, Bochum, Germany
See more of: Hydrology