Skip to main content

ORIGINAL RESEARCH article

Front. Energy Res.
Sec. Sustainable Energy Systems
Volume 12 - 2024 | doi: 10.3389/fenrg.2024.1447655
This article is part of the Research Topic Low to medium-grade thermal energy utilization in renewable energies and industries View all articles

An experimental analysis and deep learning model to assess the cooling performance of green walls in humid climates

Provisionally accepted
Abdollah Baghaei Daemei Abdollah Baghaei Daemei 1*Tomasz Bradecki Tomasz Bradecki 2Alina Pancewicz Alina Pancewicz 2Amirali Razzaghipour Amirali Razzaghipour 3Asma Jamali Asma Jamali 4Seyedeh Maryam Abbaszadegan Seyedeh Maryam Abbaszadegan 5Reza Askarizad Reza Askarizad 6Mostafa Kazemi Mostafa Kazemi 7Amir Aslan Darvish Amir Aslan Darvish 8Ayyoob Sharifi Ayyoob Sharifi 9
  • 1 School of Built Environment, College of Sciences, Massey University, Palmerston North, New Zealand
  • 2 Silesian University of Technology, Gliwice, Silesian, Poland
  • 3 Curtin University, Perth, Western Australia, Australia
  • 4 Rahbord Shomal University, Rasht, Gilan, Iran
  • 5 La Trobe University, Melbourne, Victoria, Australia
  • 6 Polytechnic University of Madrid, Madrid, Madrid, Spain
  • 7 Islamic Azad University, Tabriz, Tabriz, Iran
  • 8 University of Massachusetts Amherst, Amherst, Massachusetts, United States
  • 9 The IDEC Institute, Hiroshima University, Higashi Hiroshima, Japan

The final, formatted version of the article will be published soon.

    Amidst escalating global temperatures and rapid urbanization, addressing urban heat islands and improving outdoor thermal comfort is paramount for sustainable urban development. Green walls offer a promising strategy by effectively lowering ambient air temperatures in urban environments. While previous studies have explored their impact in various climates, their effectiveness in humid climates remains underexplored. This research investigates the cooling effect of a green wall during summer in a humid climate, employing two approaches: Field Measurement-Based Analysis (SC 1: FMA) and Deep Learning Model (SC 2: DLM). In SC 1: FMA, experiments utilized data loggers at varying distances from the green wall to capture real-time conditions. SC 2: DLM utilized a deep learning model to predict the green wall's performance over time. Results indicate a significant reduction in air temperature, with a 1.5°C (6%) decrease compared to real-time conditions. Long-term analysis identified specific distances (A, B, C, and D) contributing to temperature reductions ranging from 1.5°C to 2.5°C, highlighting optimal distances for green wall efficacy. This study contributes novel insights by determining effective distances for green wall systems to mitigate ambient temperatures, addressing a critical gap in current literature. The integration of a deep learning model enhances analytical precision and forecasts future outcomes. Despite limitations related to a single case study and limited timeframe, this research offers practical benefits in urban heat island mitigation, enhancing outdoor comfort, and fostering sustainable urban environments.

    Keywords: Green walls1, Experimental measurementHumid climate2, Cooling performance3, Ambient air temperature4, urban heat island5

    Received: 11 Jun 2024; Accepted: 19 Jul 2024.

    Copyright: © 2024 Baghaei Daemei, Bradecki, Pancewicz, Razzaghipour, Jamali, Abbaszadegan, Askarizad, Kazemi, Darvish and Sharifi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Abdollah Baghaei Daemei, School of Built Environment, College of Sciences, Massey University, Palmerston North, New Zealand

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.