Effects of Big Data on PM2.5: A Study Based on Double Machine Learning DOI Creative Commons
Xinyu Wei, Mingwang Cheng, Kaifeng Duan

et al.

Land, Journal Year: 2024, Volume and Issue: 13(3), P. 327 - 327

Published: March 4, 2024

The critical role of high-quality urban development and scientific land use in leveraging big data for air quality enhancement is paramount. application machine learning causal inferences research related to pollution presents considerable potential. This study employs a double model explore the impact on PM2.5 concentration 277 prefecture-level cities across China. analysis grounded quasi-natural experiment named National Big Data Comprehensive Pilot Zone. findings reveal significant inverse relationship between levels, with correlation coefficient −0.0149, result consistently supported by various robustness checks. Further mechanism analyses elucidate that markedly diminishes levels through avenues enhanced planning. examination heterogeneity underscores data’s suppressive effect central, eastern, western regions, as well both resource-dependent non-resource-dependent cities, albeit varying degrees significance. offers policy recommendations formulation execution policies, emphasizing importance acknowledging local variances structural nuances economies.

Language: Английский

Effects of Big Data on PM2.5: A Study Based on Double Machine Learning DOI Creative Commons
Xinyu Wei, Mingwang Cheng, Kaifeng Duan

et al.

Land, Journal Year: 2024, Volume and Issue: 13(3), P. 327 - 327

Published: March 4, 2024

The critical role of high-quality urban development and scientific land use in leveraging big data for air quality enhancement is paramount. application machine learning causal inferences research related to pollution presents considerable potential. This study employs a double model explore the impact on PM2.5 concentration 277 prefecture-level cities across China. analysis grounded quasi-natural experiment named National Big Data Comprehensive Pilot Zone. findings reveal significant inverse relationship between levels, with correlation coefficient −0.0149, result consistently supported by various robustness checks. Further mechanism analyses elucidate that markedly diminishes levels through avenues enhanced planning. examination heterogeneity underscores data’s suppressive effect central, eastern, western regions, as well both resource-dependent non-resource-dependent cities, albeit varying degrees significance. offers policy recommendations formulation execution policies, emphasizing importance acknowledging local variances structural nuances economies.

Language: Английский

Citations

3