Sign in Subscribe
Green technology

Advancing Smart and Zero-Carbon Cities through Hybrid AI Solutions

Strategic Insights

— 2 min read

Researchers at the University of Melbourne have conducted a pioneering study on the transition to smart, zero-carbon cities, highlighting the crucial role of artificial intelligence (AI) in optimizing renewable energy management. The study's findings emphasize the need for advanced, sustainable energy solutions and demonstrate the effectiveness of hybrid AI models in enhancing the accuracy and sustainability of solar power forecasting.

Key Takeaways:

  • The transition to smart, zero-carbon cities relies on advanced, sustainable energy solutions, with AI playing a crucial role in optimizing renewable energy management.
  • The study evaluates state-of-the-art AI models for solar power forecasting, emphasizing accuracy, reliability, and environmental sustainability.
  • The research uses operational data from Benban Solar Park in Egypt and Sakaka Solar Power Plant in Saudi Arabia, two of the world's largest solar installations.
  • The hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model outperformed other models, achieving a Mean Absolute Percentage Error (MAPE) of 2.04%, Root Mean Square Error (RMSE) of 184, Mean Absolute Error (MAE) of 252, and R^2 of 0.99 for Benban, and an MAPE of 2.00%, RMSE of 190, MAE of 255, and R^2 of 0.98 for Sakaka.
  • The model excels at capturing complex spatiotemporal patterns in solar data while maintaining low computational CO2 emissions, supporting sustainable AI practices.
  • The findings demonstrate the potential of hybrid AI models to enhance the accuracy and sustainability of solar power forecasting, contributing to efficient, resilient, and zero-carbon urban environments.
  • The research provides valuable insights for policymakers and stakeholders aiming to advance smart energy infrastructure.
  • The study was conducted by Haytham Elmousalami, Felix Kin Peng Hui, Aljawharah A. Alnaser, with financial support from King Saud University, Riyadh, Saudi Arabia.

Statistics:

  • The MAPE of the CNN-LSTM model for Benban Solar Park is 2.04%.
  • The RMSE of the CNN-LSTM model for Benban Solar Park is 184.
  • The MAE of the CNN-LSTM model for Benban Solar Park is 252.
  • The R^2 of the CNN-LSTM model for Benban Solar Park is 0.99.
  • The MAPE of the CNN-LSTM model for Sakaka Solar Power Plant is 2.00%.
  • The RMSE of the CNN-LSTM model for Sakaka Solar Power Plant is 190.
  • The MAE of the CNN-LSTM model for Sakaka Solar Power Plant is 255.
  • The R^2 of the CNN-LSTM model for Sakaka Solar Power Plant is 0.98.

Sources:

  • NewsRx. New Sustainability Research Study Findings Have Been Reported by Researchers at University of Melbourne [Enhancing Smart and Zero-Carbon Cities Through a Hybrid CNN-LSTM Algorithm for Sustainable AI-Driven Solar Power Forecasting (SAI-SPF)]. Ecology, Environment & Conservation. August 29, 2025; p 234.
  • Elmousalami, H., Hui, F. K. P., & Alnaser, A. A. (2025). Enhancing Smart and Zero-Carbon Cities Through a Hybrid CNN-LSTM Algorithm for Sustainable AI-Driven Solar Power Forecasting (SAI-SPF). Buildings, 15(15), 2785.

Read more