Scholarlink

<p>Reference evapotranspiration (ET<sub>o</sub>) plays a critical role in hydrological modeling and water resources management, and its variability is highly sensitive to climate change. This study evaluated future spatio-temporal trends of ET<sub>o</sub> in the Aras River Basin, Iran, under climate change scenarios defined by the Sixth Phase of the Coupled Model Intercomparison Project (CMIP6). Future climate variables were statistically downscaled using LARS-WG 8, driven by projections from the MPI-ESM1-2-LR model under two Shared Socioeconomic Pathways (SSP1-2.6 and SSP5-8.5). Daily meteorological data, including precipitation, maximum temperature, and minimum temperature from 1985 to 2022, were used as inputs to predict ET<sub>o</sub> using multiple linear regression (MLR), random forest (RF), and artificial neural network (ANN) models. The results showed that the ANN outperformed the MLR and RF in estimating ET<sub>o</sub>. Hence, it was used to project future ET<sub>o</sub> using MPI-ESM1-2-LR data for three time periods: 2021–2040, 2041–2060, and 2061–2080. The projection results revealed a consistent upward trend in ET<sub>o</sub> across all stations, with substantially greater intensification under the SSP5-8.5 scenario. The most pronounced increase was observed at the Jolfa station, which currently exhibits the highest ET<sub>o</sub>. Annual ETo at this station is projected to increase by up to 358.83 mm for the 2061–2080 period under SSP5-8.5. Seasonal analysis indicated that the most substantial increases are projected to occur in summer, intensifying water demand during the peak irrigation season. Spatial assessments further showed that low-elevation, warmer stations are likely to experience the most pronounced changes in ETo.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluating climate change impacts on reference evapotranspiration using CMIP6 projections and machine learning in the Aras River Basin

  • 期刊论文

  • 发表日期：

    2025年10月18日

查看全文
  • Simin Ganjei,
  • Jalal Shiri,
  • Sepideh Karimi

摘要

Reference evapotranspiration (ETo) plays a critical role in hydrological modeling and water resources management, and its variability is highly sensitive to climate change. This study evaluated future spatio-temporal trends of ETo in the Aras River Basin, Iran, under climate change scenarios defined by the Sixth Phase of the Coupled Model Intercomparison Project (CMIP6). Future climate variables were statistically downscaled using LARS-WG 8, driven by projections from the MPI-ESM1-2-LR model under two Shared Socioeconomic Pathways (SSP1-2.6 and SSP5-8.5). Daily meteorological data, including precipitation, maximum temperature, and minimum temperature from 1985 to 2022, were used as inputs to predict ETo using multiple linear regression (MLR), random forest (RF), and artificial neural network (ANN) models. The results showed that the ANN outperformed the MLR and RF in estimating ETo. Hence, it was used to project future ETo using MPI-ESM1-2-LR data for three time periods: 2021–2040, 2041–2060, and 2061–2080. The projection results revealed a consistent upward trend in ETo across all stations, with substantially greater intensification under the SSP5-8.5 scenario. The most pronounced increase was observed at the Jolfa station, which currently exhibits the highest ETo. Annual ETo at this station is projected to increase by up to 358.83 mm for the 2061–2080 period under SSP5-8.5. Seasonal analysis indicated that the most substantial increases are projected to occur in summer, intensifying water demand during the peak irrigation season. Spatial assessments further showed that low-elevation, warmer stations are likely to experience the most pronounced changes in ETo.