Table 1.
The different periods of COVID-19 outbreaks in Thailand.
Table 2.
Levels of COVID-19 lockdown measures in Thailand.
Table 3.
Definitions of mobility categories in the Google Community Mobility Reports.
Table 4.
Example of daily mobility in Thailand derived from Google Community Mobility Reports.
Fig 1.
The analysis of trends in mobility, policy stringency, and COVID-19 case rates across different location categories during the period of 2020–2022, considering the various phases of COVID-19 and government implications.
Table 5.
COVID-19 control phases in Thailand and corresponding government interventions.
Fig 2.
Granger causality (p < 0.05) across activities and time periods with government intervention.
Fig 3.
Correlation heatmap showing relationships among mobility trends, policy stringency, and new COVID-19 case counts.
Fig 4.
Forecasted mobility changes and actual data in Thailand using ARIMA model.
Fig 5.
Forecasted mobility changes and actual data in Thailand using Facebook Prophet model.
Table 6.
Forecast accuracy of mobility trends using ARIMA, FB-PROPHET and Feature Engineered XGBoost, across location categories.
Table 7.
Feature importance for mobility prediction across six location categories (Weight, Gain, and Cover).
Fig 6.
Forecasted mobility changes and actual data in Thailand using Feature Engineered XGBoost model.
Fig 7.
Comparison of MAE across 4 COVID-19-Waves using ARIMA, FB-PROPHET and XGBoost based on Rolling-Origin Evaluation Approach.
Fig 8.
Feature importance analysis of the Feature Engineered XGBoost Approach.