A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population Mobility
Following the declaration by the World Health Organisation (WHO) on 11 March 2020, that the global COVID-19 outbreak had become a pandemic, South Africa implemented a full lockdown from 27 March 2020 for 21 days. The full lockdown was implemented after the publication of the National Disaster Regula...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Machine Learning and Knowledge Extraction |
Subjects: | |
Online Access: | https://www.mdpi.com/2504-4990/3/2/25 |
_version_ | 1797531801639452672 |
---|---|
author | Albert Whata Charles Chimedza |
author_facet | Albert Whata Charles Chimedza |
author_sort | Albert Whata |
collection | DOAJ |
description | Following the declaration by the World Health Organisation (WHO) on 11 March 2020, that the global COVID-19 outbreak had become a pandemic, South Africa implemented a full lockdown from 27 March 2020 for 21 days. The full lockdown was implemented after the publication of the National Disaster Regulations (NDR) gazette on 18 March 2020. The regulations included lockdowns, public health measures, movement restrictions, social distancing measures, and social and economic measures. We developed a hybrid model that consists of a long-short term memory auto-encoder (LSTMAE) and the kernel quantile estimator (KQE) algorithm to detect change-points. Thereafter, we utilised the Bayesian structural times series models (BSTSMs) to estimate the causal effect of the lockdown measures. The LSTMAE and KQE, successfully detected the changepoint that resulted from the full lockdown that was imposed on 27 March 2020. Additionally, we quantified the causal effect of the full lockdown measure on population mobility in residential places, workplaces, transit stations, parks, grocery and pharmacy, and retail and recreation. In relative terms, population mobility at grocery and pharmacy places decreased significantly by −17,137.04% (<i>p</i>-value = 0.001 < 0.05). In relative terms, population mobility at transit stations, retail and recreation, workplaces, parks, and residential places decreased significantly by −998.59% (<i>p</i>-value = 0.001 < 0.05), −1277.36% (<i>p</i>-value = 0.001 < 0.05), −2175.86% (<i>p</i>-value = 0.001 < 0.05), −370.00% (<i>p</i>-value = 0.001< 0.05), and −22.73% (<i>p</i>-value = 0.001 < 0.05), respectively. Therefore, the full lockdown Level 5 imposed on March 27, 2020 had a causal effect on population mobility in these categories of places. |
first_indexed | 2024-03-10T10:48:56Z |
format | Article |
id | doaj.art-8836922a7b934f72a282b31219c84cdf |
institution | Directory Open Access Journal |
issn | 2504-4990 |
language | English |
last_indexed | 2024-03-10T10:48:56Z |
publishDate | 2021-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Machine Learning and Knowledge Extraction |
spelling | doaj.art-8836922a7b934f72a282b31219c84cdf2023-11-21T22:21:54ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902021-06-013248150610.3390/make3020025A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population MobilityAlbert Whata0Charles Chimedza1School of Natural and Applied Sciences, Sol Plaatje University, Kimberley 8301, South AfricaSchool of Statistics and Actuarial Science, University of the Witwatersrand, Johannesburg 2050, South AfricaFollowing the declaration by the World Health Organisation (WHO) on 11 March 2020, that the global COVID-19 outbreak had become a pandemic, South Africa implemented a full lockdown from 27 March 2020 for 21 days. The full lockdown was implemented after the publication of the National Disaster Regulations (NDR) gazette on 18 March 2020. The regulations included lockdowns, public health measures, movement restrictions, social distancing measures, and social and economic measures. We developed a hybrid model that consists of a long-short term memory auto-encoder (LSTMAE) and the kernel quantile estimator (KQE) algorithm to detect change-points. Thereafter, we utilised the Bayesian structural times series models (BSTSMs) to estimate the causal effect of the lockdown measures. The LSTMAE and KQE, successfully detected the changepoint that resulted from the full lockdown that was imposed on 27 March 2020. Additionally, we quantified the causal effect of the full lockdown measure on population mobility in residential places, workplaces, transit stations, parks, grocery and pharmacy, and retail and recreation. In relative terms, population mobility at grocery and pharmacy places decreased significantly by −17,137.04% (<i>p</i>-value = 0.001 < 0.05). In relative terms, population mobility at transit stations, retail and recreation, workplaces, parks, and residential places decreased significantly by −998.59% (<i>p</i>-value = 0.001 < 0.05), −1277.36% (<i>p</i>-value = 0.001 < 0.05), −2175.86% (<i>p</i>-value = 0.001 < 0.05), −370.00% (<i>p</i>-value = 0.001< 0.05), and −22.73% (<i>p</i>-value = 0.001 < 0.05), respectively. Therefore, the full lockdown Level 5 imposed on March 27, 2020 had a causal effect on population mobility in these categories of places.https://www.mdpi.com/2504-4990/3/2/25causal effectencoder–decoderkernel quantile estimatorlong-short term memorypopulation mobilityreconstruction error |
spellingShingle | Albert Whata Charles Chimedza A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population Mobility Machine Learning and Knowledge Extraction causal effect encoder–decoder kernel quantile estimator long-short term memory population mobility reconstruction error |
title | A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population Mobility |
title_full | A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population Mobility |
title_fullStr | A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population Mobility |
title_full_unstemmed | A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population Mobility |
title_short | A Machine Learning Evaluation of the Effects of South Africa’s COVID-19 Lockdown Measures on Population Mobility |
title_sort | machine learning evaluation of the effects of south africa s covid 19 lockdown measures on population mobility |
topic | causal effect encoder–decoder kernel quantile estimator long-short term memory population mobility reconstruction error |
url | https://www.mdpi.com/2504-4990/3/2/25 |
work_keys_str_mv | AT albertwhata amachinelearningevaluationoftheeffectsofsouthafricascovid19lockdownmeasuresonpopulationmobility AT charleschimedza amachinelearningevaluationoftheeffectsofsouthafricascovid19lockdownmeasuresonpopulationmobility AT albertwhata machinelearningevaluationoftheeffectsofsouthafricascovid19lockdownmeasuresonpopulationmobility AT charleschimedza machinelearningevaluationoftheeffectsofsouthafricascovid19lockdownmeasuresonpopulationmobility |