In the heart of China’s bustling urban landscapes, a silent yet potent threat looms—surface compound ozone and heat (SCOH). This synergistic effect of extreme heat and ozone poses a more significant risk to public health and environmental safety than isolated events. A groundbreaking study led by Yufeng Chi from Sanming University, published in the journal ‘Ecological Indicators’ (translated as ‘生态指标’), sheds light on the spatiotemporal mechanisms of SCOH, offering critical insights for risk mitigation and urban planning.
Chi and his team integrated the Multiple Air Pollutants dataset (MuAP) with surface heat datasets to map the time delay correlation between surface ozone and heat at an unprecedented 1 km scale. By combining advanced machine learning techniques, specifically BayesConvLightGBM and SHapley Additive exPlanations (SHAP), they quantified the influence of urban factors such as building height, canopy cover, and road length on SCOH.
“The results show that SCOH has significant temporal and spatial distribution characteristics,” Chi explained. “More compact planning of urban areas can help reduce the complex risk of SCOH.” This finding is particularly relevant for the energy sector, where urban planning and infrastructure development play a pivotal role in mitigating environmental risks.
The study revealed that buildings, roads, and trees significantly impact SCOH both locally and globally within urban areas. The BayesConvLightGBM model, with its superior performance (R2 values 0.03–0.07 higher than LightGBM), provided a more effective spatiotemporal response to SCOH. This advanced modeling approach deepens the understanding of nonlinear interactions between urban infrastructure and SCOH propagation.
One of the most compelling findings is the need for awareness of SCOH exposure risks within a 4 km range during a 30-day time delay period. This insight is crucial for urban planners and energy sector professionals, as it highlights the importance of long-term planning and monitoring to mitigate SCOH risks.
The research not only strengthens the quantification of key elements using optimized machine learning but also provides an important reference for studying compound exposure. As cities continue to grow and evolve, the findings from this study will be instrumental in shaping future developments in urban planning and environmental safety.
In the words of Chi, “This study is of great significance in explaining the spatiotemporal response of SCOH and provides an important reference for the study of compound exposure.” The implications for the energy sector are vast, as understanding and mitigating SCOH risks can lead to more sustainable and resilient urban environments.
As we move forward, the integration of advanced machine learning techniques and comprehensive datasets will be crucial in addressing the complex challenges posed by SCOH. This research serves as a beacon, guiding us towards a future where urban planning and environmental safety go hand in hand, ensuring a healthier and more sustainable world for all.