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

Introduction: Amidst escalating global temperatures, increasing climate change, 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. Methods: 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: 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. Discussion: 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 and climate-resilient urban environments.