Log In Sign Up

Continental-scale streamflow modeling of basins with reservoirs: a demonstration of effectiveness and a delineation of challenges

by   Wenyu Ouyang, et al.

A large fraction of major waterways have dams influencing streamflow, which must be accounted for in large-scale hydrologic modeling. However, daily streamflow prediction for basins with dams is challenging for various modeling approaches, especially at large scales. Here we took a divide-and-conquer approach to examine which types of basins could be well represented by a long short-term memory (LSTM) deep learning model using only readily-available information. We analyzed data from 3557 basins (83 United States and noted strong impacts of reservoir purposes, capacity-to-runoff ratio (dor), and diversion on streamflow on streamflow modeling. Surprisingly, while the LSTM model trained on a widely-used reference-basin dataset performed poorly for more non-reference basins, the model trained on the whole dataset presented a median test Nash-Sutcliffe efficiency coefficient (NSE) of 0.74, reaching benchmark-level performance. The zero-dor, small-dor, and large-dor basins were found to have distinct behaviors, so migrating models between categories yielded catastrophic results. However, training with pooled data from different sets yielded optimal median NSEs of 0.73, 0.78, and 0.71 for these groups, respectively, showing noticeable advantages over existing models. These results support a coherent, mixed modeling strategy where smaller dams are modeled as part of rainfall-runoff processes, but dammed basins must not be treated as reference ones and must be included in the training set; then, large-dor reservoirs can be represented explicitly and future work should examine modeling reservoirs for fire protection and irrigation, followed by those for hydroelectric power generation, and flood control, etc.


page 7

page 16

page 19

page 21

page 25


Prediction in ungauged regions with sparse flow duration curves and input-selection ensemble modeling

While long short-term memory (LSTM) models have demonstrated stellar per...

Optimal Reservoir Operations using Long Short-Term Memory Network

A reliable forecast of inflows to the reservoir is a key factor in the o...

Benchmarking a Catchment-Aware Long Short-Term Memory Network (LSTM) for Large-Scale Hydrological Modeling

Regional rainfall-runoff modeling is an old but still mostly out-standin...

Strict baselines for Covid-19 forecasting and ML perspective for USA and Russia

Currently, the evolution of Covid-19 allows researchers to gather the da...

A Bi-Encoder LSTM Model For Learning Unstructured Dialogs

Creating a data-driven model that is trained on a large dataset of unstr...

An Ample Approach to Data and Modeling

In the present work, we describe a framework for modeling how models can...

Code Repositories


Streamflow Prediction in (Dammed) Basins (SPDB) with Deep Learning models

view repo