Drought has significant impacts on both society and the environment, but it is a gradual and comprehensive process that affects a region over time. Therefore, non-structural measures are necessary to prepare and respond to the damage caused by drought in a flexible manner according to the stage of drought. In this study, an AI-based water demand prediction model was developed using deep neural network (DNN) and long short-term memory (LSTM) models. The model was trained from 2004 to 2015 and verified from 2016 to 2021. Model accuracy was evaluated using data, with the LSTM model achieving a correlation coefficient (CC) of 0.95 and normalized root mean square error (NRMSE) of 8.38, indicating excellent performance. The probability of the random variable X falling within the interval [a,b], as described by the probability density function f(x), was calculated using the water demand data. The cumulative distribution function was used to calculate the probability of the random variable being less than or equal to a specific value. These calculations were used to establish the criteria for each stage of the crisis alert system. Decision tree (DT) and random forest (RF) models, based on AI-based classification, were used to predict water demand at the Gurye intake station. The models took into account the impact of water demand from the previous day, as well as the effects of rainfall, maximum temperature, and average temperature. Daily water demand data from the Gurye intake station and the previous day’s rainfall, maximum temperature, and average temperature data from a nearby observatory were collected from 2004 to 2021. The models were trained on data from 2004 to 2015 and validated on data from 2016 to 2021. Model accuracy was evaluated using the F1-score, with the random forest model achieving a score of 0.88, indicating excellent performance.

Seomijn River Basin has numerous hydraulic structures designed to satisfy water demands and mitigate future droughts. However, the increasing water demand and export to neighboring areas cause water deficits and conflicts between water users. Therefore, practical strategies to mitigate the potential damage from climate change are essential. In this study, we aimed to propose practical strategies under climate change by examining the future water security of the Seomjin River Basin under five different water allocation scenarios referenced from the practical policies of various countries. Future climate models determined based on extreme precipitation indices of the ETCCDI were used to investigate their impact on water security, which was evaluated using unmet demand; demand coverage; reliability, resilience, and vulnerability; and aggregation index metrics. We found that prioritizing domestic and industrial water use is the optimal water security strategy, and unconditional allocation of instream flow can cause a significant water deficit for other water uses. However, prioritizing all water uses equally also proved effective under some conditions. Thus, our study highlights the importance of adaptive management and suggests that the optimal water allocation strategy lies in its flexibility in response to varying circumstances.

In this study, we suggest various improvement measures for water balance analysis, a basic step in water resources planning. First, we confirmed the assumptions and problem of the water balance method currently being carried out in Korea and suggest five methods to solve these problems. In order to analyze the applicability and the effectiveness of the proposed improvement measures, 10 cases were constructed using two rainfall-runoff model simulation results for the Geum River basin. Water supply and demand networks were constructed reflecting five proposed improvement measures and two simulation results, and conducted a water balance analysis. The results of the analysis of each case show the degree of improvement by comparing and analyzing the observed discharge of Gongju and Seokhwa points which are representative points in the Geum River basin. The applicability of the improvement measures was confirmed through comparison and examination with the past restricted water supply area. More realistic analysis will be possible when establishing water resources planning through the proposed water balance method in this study.

This study evaluated the impact of climate change and water allocation scenarios on water security in the Seomjin River Basin using K-WEAP (Korea-Water Evaluation and Planning System). The findings indicated that domestic water and instream flow are vulnerable to climate change, while industrial water supply may fail to meet future demand in certain regions. Moreover, prioritizing instream flow was found to compromise the stability of the domestic water, and equal allocation adversely affected both domestic and industrial water security. Consequently, maintaining the current system appears to be the most effective approach; however, future studies should focus on developing flexible strategies that consider the effects of climate change and regional characteristics in a more detailed manner.

The Daap intake plant located downstream of the Seomjin River was relocated in 2005, and the amount of intake increased. Accordingly, it significantly influenced the change in the flow rate downstream of the Seomjin River. After relocating the Daap intake plant, the production of Corbicula in the downstream of the Seomjin River decreased; there is a demand for investigation into the damage to the downstream fishermen and preparation of countermeasures. An increase in instream flow to increase the production of Corbicula downstream of the Seomjin River may cause difficulties in the stable water supply of the Seomjin River basin; therefore, a preliminary review is necessary. In this study, the supply stability was evaluated through water budget analysis after setting several instream flow at the downstream of the Seomjin River in Gurye-gun (Songjeong-ri). In addition, the supply stability of the water resource system in the Seomjin River according to the instream flow rate was evaluated. It was intended to suggest an alternative to the supply of instream flow. If the instream flow is set large to increase the production of Corbicula, it may cause difficulties in supplying instream flow and problems in supplying water necessary for human activities; therefore, related information must be provided through various analyses.