Tackling Data Quality Challenges in Remote Sensing: Solutions for Reliable Urban Heat Island Analysis

Abstract

Urban heat islands (UHIs) pose critical challenges to public health, energy demand, and environmental sustainability, particularly in rapidly expanding urban regions. This study examines the complex relationship between building configurations and integrated green spaces, as well as their combined impact on thermal regulation. It focuses on addressing data quality issues commonly encountered in remote sensing applications. Using highresolution multispectral and thermal imagery, we developed an integrated modeling approach that captures the collective influence of built form and green infrastructure on urban microclimates. A key finding is the significant linear inverse relationship between green space coverage and land surface temperature, underscoring the cooling potential of strategically planned green zones. However, achieving robust insights required addressing several data quality challenges, including image misalignment, atmospheric distortions, variable spatial resolutions, and annotation inconsistencies, which can compromise model performance. We applied preprocessing methods, including geometric correction, atmospheric calibration, and multi-source data fusion, alongside rigorous ground-truthing using in situ temperature measurements. We also implemented data augmentation and label refinement strategies to enhance the training of deep learning models for thermal pattern prediction. This study demonstrates that, when properly corrected, urban microclimate models can accurately capture temperature variations of up to 3.5°C across similar urban settings, providing actionable insights for thermal comfort planning. This study highlights the critical role of high-quality, preprocessed remote sensing data in enabling reliable analysis and offers a framework for integrating urban design and green infrastructure to mitigate UHI effects. These findings have implications for scalable urban cooling strategies and climate-resilient city planning.