Investigation of climate change impact on large dam projects equipped with hydropower

Hydrological prediction is crucial for managing water resources, and innovations like machine learning present an opportunity to enhance predictive modeling capabilities. The aim of this study is to compare the usage of the new machine learning method, CatBoost, with traditional methods about investigating prediction streamflow in the future under climate change scenarios and determining the effect of predicted streamflows on hydropower energy production. The investigation found that CatBoost was superior to conventional models. After it was proven that the best-performing model is CatBoost, future projections according to the NorESM2-MM scenarios were calculated using this model. Climate projections are based on simulations from the Coupled Model Intercomparison Project Phase 6 model, utilizing shared socioeconomic pathway (SSP) scenarios. The results show that SSP3-7.0 and SSP5-8.5 scenarios indicate an increasing trend between 2015 and 2100, while SSP1-2.6 and SSP2-4.5 expect a balancing tendency. This suggests that climate change has little effect on the measuring station and its basin and that the flow is increasing positively. On the other hand, it is noted that the estimated energy amount in the SSP1-2.6 and SSP2-4.5 scenarios is lower, particularly in the 2015–2039 timeframe. The amount of energy computed under the SSP3-7.0 and SSP5-8.5 scenarios, however, shows a notable increase.