Scholarlink

<p>The temperature in the United Arab Emirates (UAE) plays a critical role in shaping the country’s climate, lifestyle, and environmental challenges. Temperature changes in the UAE pose significant challenges that require urgent attention across multiple sectors, emphasizing the need for adaptive strategies to mitigate their effects on society and the economy. Understanding this significance involves examining the climatic conditions, seasonal variations, and implications for health and infrastructure. This research focuses on developing a system to forecast and analyze maximum and minimum monthly temperatures using deep neural network (DNN) and hybrid of Convolution Neural Network (CNN) and Gated Recurrent Unit (GRU). Time series data from 2000 to 2024 was used to test the system in key cities of the UAE, such as Abu Dhabi, Dubai, Al Ain, and Sharjah. The identification of optimal variables for precise single-variable forecasting in multiple cities was achieved using AMI. The performance was evaluated using root mean square error (RMSE), coefficient of determination (R<sup>2</sup>), and Nash–Sutcliffe efficiency (NSE). The GRU-CNN hybrid model outperformed the DNN model, achieving a lower RMSE (1.68) and higher R<sup>2</sup> (0.94) and NSE (0.91), demonstrating strong potential for single-variable prediction in temperature forecasting.</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

Enhancing temperature prediction in the UAE: a process-driven framework for adaptive learning with GRU-CNN hybrid models

  • 期刊论文

  • 发表日期：

    2025年1月22日

查看全文
  • SeyedHadi Haghrahmani

摘要

The temperature in the United Arab Emirates (UAE) plays a critical role in shaping the country’s climate, lifestyle, and environmental challenges. Temperature changes in the UAE pose significant challenges that require urgent attention across multiple sectors, emphasizing the need for adaptive strategies to mitigate their effects on society and the economy. Understanding this significance involves examining the climatic conditions, seasonal variations, and implications for health and infrastructure. This research focuses on developing a system to forecast and analyze maximum and minimum monthly temperatures using deep neural network (DNN) and hybrid of Convolution Neural Network (CNN) and Gated Recurrent Unit (GRU). Time series data from 2000 to 2024 was used to test the system in key cities of the UAE, such as Abu Dhabi, Dubai, Al Ain, and Sharjah. The identification of optimal variables for precise single-variable forecasting in multiple cities was achieved using AMI. The performance was evaluated using root mean square error (RMSE), coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE). The GRU-CNN hybrid model outperformed the DNN model, achieving a lower RMSE (1.68) and higher R2 (0.94) and NSE (0.91), demonstrating strong potential for single-variable prediction in temperature forecasting.