Scholarlink

<p>Freshwater from surface runoff, vital for drinking water, faces contamination from various sources, including climate change, land use, industry, and agriculture. However, the specific mechanisms through which climate change contributes to river water pollution require further clarification. To address this research gap, we propose an innovative approach integrating the Bayesian network model, the IHACRES method, and a climate change model. Precipitation and temperature data from 2022 to 2041 were extracted from the Coupled Model Intercomparison Project Phase 6 (CMIP6) dataset, which provides a comprehensive collection of climate model simulations produced by international climate research organizations. The IHACRES model was employed to generate future runoff projections using rainfall and temperature inputs to return discharge as an output. Key IHACRES parameters included an area of 1512 m<sup>2</sup>, a delay coefficient of 1, and the single Exponential Store Eq.&#xa0;(1,0). These runoff projections were then used as inputs to the Bayesian network model to predict future river water quality indicators, including Total Dissolved Solids (TDS), Total Hardness (TH), Calcium (Ca), and Magnesium (Mg). The integrated approach yielded high R-squared values of 0.98, 0.96, 0.93, and 0.93 for TDS, TH, Ca, and Mg, respectively. Additionally, the IHACRES model showed significant predictive capability, with R-squared values of 0.72 for runoff and precipitation and 0.70 for runoff and temperature. This study successfully predicted surface runoff quality and quantity under climate change, demonstrating the effectiveness of combining IHACRES and Bayesian network models in accurately forecasting surface runoff characteristics under evolving climatic conditions. These findings underscore the potential for improved management of water resources in the face of climate change.</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

Prediction of surface runoff quality and quantity using an integrated model and machine learning under climate change conditions

  • 期刊论文

  • 发表日期：

    2025年1月19日

查看全文
  • Pourya Alipour Atmianlu,
  • Nasser Mehrdadi,
  • Majid Shafiepour Motlagh,
  • Mohammad Hossein Niksokhan,
  • Naser Einollahi

摘要

Freshwater from surface runoff, vital for drinking water, faces contamination from various sources, including climate change, land use, industry, and agriculture. However, the specific mechanisms through which climate change contributes to river water pollution require further clarification. To address this research gap, we propose an innovative approach integrating the Bayesian network model, the IHACRES method, and a climate change model. Precipitation and temperature data from 2022 to 2041 were extracted from the Coupled Model Intercomparison Project Phase 6 (CMIP6) dataset, which provides a comprehensive collection of climate model simulations produced by international climate research organizations. The IHACRES model was employed to generate future runoff projections using rainfall and temperature inputs to return discharge as an output. Key IHACRES parameters included an area of 1512 m2, a delay coefficient of 1, and the single Exponential Store Eq. (1,0). These runoff projections were then used as inputs to the Bayesian network model to predict future river water quality indicators, including Total Dissolved Solids (TDS), Total Hardness (TH), Calcium (Ca), and Magnesium (Mg). The integrated approach yielded high R-squared values of 0.98, 0.96, 0.93, and 0.93 for TDS, TH, Ca, and Mg, respectively. Additionally, the IHACRES model showed significant predictive capability, with R-squared values of 0.72 for runoff and precipitation and 0.70 for runoff and temperature. This study successfully predicted surface runoff quality and quantity under climate change, demonstrating the effectiveness of combining IHACRES and Bayesian network models in accurately forecasting surface runoff characteristics under evolving climatic conditions. These findings underscore the potential for improved management of water resources in the face of climate change.