Selected article for: "lockdown group and machine learning"
Author: Cole, Matthew A.; Elliott, Robert J R; Liu, Bowen
Title: The Impact of the Wuhan Covid-19 Lockdown on Air Pollution and Health: A Machine Learning and Augmented Synthetic Control Approach
  • Cord-id: mp6a5yjz
  • Document date: 2020_8_10
    • ID: mp6a5yjz
    Snippet: We quantify the impact of the Wuhan Covid-19 lockdown on concentrations of four air pollutants using a two-step approach. First, we use machine learning to remove the confounding effects of weather conditions on pollution concentrations. Second, we use a new augmented synthetic control method (Ben-Michael et al. in The augmented synthetic control method. University of California Berkeley, Mimeo, 2019. https://arxiv.org/pdf/1811.04170.pdf) to estimate the impact of the lockdown on weather normali
    Document: We quantify the impact of the Wuhan Covid-19 lockdown on concentrations of four air pollutants using a two-step approach. First, we use machine learning to remove the confounding effects of weather conditions on pollution concentrations. Second, we use a new augmented synthetic control method (Ben-Michael et al. in The augmented synthetic control method. University of California Berkeley, Mimeo, 2019. https://arxiv.org/pdf/1811.04170.pdf) to estimate the impact of the lockdown on weather normalised pollution relative to a control group of cities that were not in lockdown. We find NO[Formula: see text] concentrations fell by as much as 24 [Formula: see text] g/m[Formula: see text] during the lockdown (a reduction of 63% from the pre-lockdown level), while PM10 concentrations fell by a similar amount but for a shorter period. The lockdown had no discernible impact on concentrations of SO[Formula: see text] or CO. We calculate that the reduction of NO[Formula: see text] concentrations could have prevented as many as 496 deaths in Wuhan city, 3368 deaths in Hubei province and 10,822 deaths in China as a whole.

    Search related documents:
    Co phrase search for related documents
    • lockdown period and long term impact: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
    • lockdown period and low concentration: 1, 2
    • lockdown period and low mortality: 1, 2, 3
    • lockdown period and machine learning: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14
    • lockdown period and machine learning approach: 1, 2
    • lockdown policy and low mortality: 1
    • lockdown policy and machine learning: 1, 2, 3, 4
    • lockdown prior and long term impact: 1, 2, 3
    • lockdown respond and machine learning: 1
    • lockdown result and machine learning: 1
    • long term impact and machine learning: 1, 2, 3, 4, 5, 6, 7
    • long term impact and machine learning approach: 1
    • low concentration and machine learning: 1
    • low concentration and machine learning approach: 1
    • low mortality and machine learning: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11