In Vietnam, drought has been occurring persistently and in very complicated patterns, with a great impact on the water, energy, and food security nexus and regional development sustainability. The uncertainty surrounding annual water resources in combination with the low reliability of interbasin water transfer (IBWT) operations is the key driver of water deficits in several affected regions. This study aims to assess the impacts of four big IBWT projects in the Central Highlands of Vietnam, based on a proposed matrix of five evaluation criteria to quantify related impacts and to draw out lessons learned for future development of IBWT. The proposed criteria matrix was formulated on the basis of intensive reviews of IBWT assessments worldwide and relevant Vietnamese laws in force. The impacts were analysed and quantified mainly based on assessment of their operational database and water balance simulations for donor and recipient river basins in current and future states. The results show that the studied IBWT projects did not fully satisfy the proposed criteria set, all project did not meet the criteria of benefit sharing and information transparency; noticeably the Don Duong project fulfilled only one from five. Four lessons were determined for proper planning in river basins, flexibility in system design for unknown future, inadequate environmental impact assessment and delay in enactment of policies for IBWT project management. The results provide sound knowledge to revise the existing projects in the Central Highlands and procedures for impact assessment and approval of new IBWT systems.

Beyşehir Lake is the largest freshwater lake in the Mediterranean region of Turkey that is used for drinking and irrigation purposes. The aim of this paper is to examine the potential for data-driven methods to predict long-term lake levels. The surface water level variability was forecast using conventional machine learning models, including autoregressive moving average (ARMA), autoregressive integrated moving average (ARIMA), and seasonal autoregressive integrated moving average (SARIMA). Based on the monthly water levels of Beyşehir Lake from 1992 to 2016, future water levels were predicted up to 24 months in advance. Water level predictions were obtained using conventional time series stochastic models, including autoregressive moving average, autoregressive integrated moving average, and seasonal autoregressive integrated moving average. Using historical records from the same period, prediction models for precipitation and evaporation were also developed. In order to assess the model’s accuracy, statistical performance metrics were applied. The results indicated that the seasonal autoregressive integrated moving average model outperformed all other models for lake level, precipitation, and evaporation prediction. The obtained results suggested the importance of incorporating the seasonality component for climate predictions in the region. The findings of this study demonstrated that simple stochastic models are effective in predicting the temporal evolution of hydrometeorological variables and fluctuations in lake water levels.