CHAIR - India Daily 1km x 1km Modeled PM2.5 2008 - 2022

The work is led and coordinated centrally through the Institute of Environmental Medicine, Karolinska Institute, Stockholm, Sweden (PI Petter Ljungman) in close collaboration with the Centre for Chronic Disease Control, Delhi, India (PI Dorairaj Prabhakaran), Centre for Health Analytics Research and Trends, Trivedi School of Biosciences, Ashoka University (PI Poornima Prabhakaran) and Department of Environmental Health, Harvard T H Chan School of Public Health (PI Joel Schwartz). We developed a model for daily average ambient PM2.5 between 2008 and 2020 based on monitoring data, meteorology, land use, satellite observations, and emissions inventories. Daily average predictions at each 1 km × 1 km grid from each learner were ensembled using a Gaussian process regression with anisotropic smoothing over spatial coordinates, and regression calibration was used to account for exposure error.

本研究由瑞典斯德哥尔摩卡罗林斯卡学院环境医学研究所牵头统筹（项目负责人：Petter Ljungman），并与印度德里慢性病控制中心（项目负责人：Dorairaj Prabhakaran）、阿育王大学特里维迪生物科学学院健康分析研究与趋势中心（项目负责人：Poornima Prabhakaran）以及哈佛大学陈曾熙公共卫生学院环境卫生系（项目负责人：Joel Schwartz）展开密切合作。研究团队基于监测数据、气象资料、土地利用数据、卫星观测结果与排放清单，构建了2008年至2020年逐日平均环境细颗粒物（PM2.5）预测模型。各学习器在每1千米×1千米网格上生成的逐日平均预测结果，通过结合空间坐标各向异性平滑的高斯过程回归（Gaussian process regression）进行集成；同时采用回归校准方法以校正暴露误差。