Scholarlink

<p>This study examines the effects of climate change using monthly precipitation, evapotranspiration, temperature, relative humidity, and streamflow data (1963–2021) obtained from meteorological and hydrological stations in the city center of Diyarbakır. For trend analysis, Mann–Kendall (MK) test, Sen’s Slope Test (SS), and Innovative Polygon Trend Analysis (IPTA) methods were applied, and the results were compared. The study evaluates the performance of these methods in different climate variables, showing that statistically significant trends in precipitation, temperature, humidity, evaporation, and flow variables occur in certain months in Diyarbakır. The findings provide an important data source for water resource management and drought risk assessments. Additionally, drought analyses were performed using the Standardized Precipitation Index (SPI), Standardized Precipitation-Evapotranspiration Index (SPEI), and Streamflow Drought Index (SDI), and SDI predictions were made using machine learning techniques such as Multilayer Perceptron (MLP), Linear Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) algorithms. The algorithm providing the best prediction performance was determined.</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

Climate change impacts on hydrological and meteorological variables in Diyarbakır Province: trend analysis and machine learning-based drought forecasting

  • 期刊论文

  • 发表日期：

    2025年5月9日

查看全文
  • Ergun Akbas,
  • Recep Çelik,
  • Musa Esit,
  • Ibrahim Halil Deger

摘要

This study examines the effects of climate change using monthly precipitation, evapotranspiration, temperature, relative humidity, and streamflow data (1963–2021) obtained from meteorological and hydrological stations in the city center of Diyarbakır. For trend analysis, Mann–Kendall (MK) test, Sen’s Slope Test (SS), and Innovative Polygon Trend Analysis (IPTA) methods were applied, and the results were compared. The study evaluates the performance of these methods in different climate variables, showing that statistically significant trends in precipitation, temperature, humidity, evaporation, and flow variables occur in certain months in Diyarbakır. The findings provide an important data source for water resource management and drought risk assessments. Additionally, drought analyses were performed using the Standardized Precipitation Index (SPI), Standardized Precipitation-Evapotranspiration Index (SPEI), and Streamflow Drought Index (SDI), and SDI predictions were made using machine learning techniques such as Multilayer Perceptron (MLP), Linear Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) algorithms. The algorithm providing the best prediction performance was determined.