ABSTRACT:

The flow duration curve characterizes streamflow variability, crucial for river management. Constructing FDCs is challenging in areas without gauging stations. This study explores machine learning and deep learning models, including random forest, deep neural network, support vector regression, and elastic net regression, to predict FDCs in ungauged basins. Using data from streamflow stations, we predict streamflow percentiles . The models utilize various combinations of accumulated precipitation and topographic features to improve prediction accuracy.

ABSTRACT:

Floods are among the most prevalent natural disasters, posing substantial threats to human activities. Using flood forecast information, reservoirs can pre-release water or adjust storage to enhance flood control and water conservation benefits. Yet, the absence of intuitive guidelines for the reservoir operators in making immediate operational decisions under flood events present a significant challenge. The objective of this study is to develop a flood operation model that provides the pre-release guideline to minimize flood damage considering downstream conditions. The developed model includes five Flood Operation Method (FOMs) and tested which FOM fits the best for the Seomjingang Reservoir as a case study. As part of developing the model, this study provides a Graphical User Interface (GUI) that encompasses reservoir characteristics and operational data for multipurpose reservoirs in South Korea. The developed GUI generates the reference graphs and tables that assists the reservoir operators with hourly guidelines to make prompt decisions on the flood control for pre-release and storage usage. This model is applicable if operational information for multipurpose reservoirs in other countries is available. This approach not only enhances reservoir management but also advances the broader dialogue on water resources management, signaling a move towards more secure, efficient, and adaptable strategies for reservoir operations.

ABSTRACT:

Understanding the impact of human-made structures on groundwater levels is crucial, with structures like dams or weirs presenting both challenges and opportunities for study. The Baekje weir in South Korea offers an unique case as it has undergone full gate openings, a condition not typically observed in weirs and reservoirs, providing a unique opportunity to simulate conditions resembling weir removal. The primary objectives include investigating groundwater level fluctuations influenced by various weir operations, proximity to the weir, and seasonal variations. The study employs observed data to simulate conditions both with and without the weir, encompassing scenarios of full gate opening. This research illuminates the intricate interplay between weir manipulations and groundwater levels, offering practical knowledge for the management of water resources in comparable hydrogeological environments. This research is part of the submission WaterResourcesResearch2022WR032779RRRR to the journal Water Resources Research, aiming to deepen our understanding of how such structures impact water resources.

ABSTRACT:

The reservoir operation changes the downstream water level and the surrounding groundwater level. Predicting the groundwater level flux is crucial, especially before making the dam removal decision. However, investigating the condition of dam removal without demolishing the infrastructure is challenging. The novelty of this study comes from analyzing the groundwater level changes using the observed pre- and post-weir removal data. We built daily groundwater level prediction models for 14 groundwater observation wells using five machine learning algorithms. The support vector regression was the best machine learning algorithm in predicting the daily groundwater level. The groundwater level was the highest during normal operation and summer (rainy season) and the lowest during the full opening and winter (dry season). The groundwater changes were up to 3.15 m near the weir, and impacts extended 3.80 km but no further than 7 km. The final product was groundwater level maps that can assist groundwater level management and weir operation strategies based on groundwater level forecasting. Future studies can reconfigure and modify the groundwater prediction process used in this research to fit different hydrological and metrological variables to dams or weirs under consideration for removal.

ABSTRACT:

None