ABSTRACT
The Coronavirus disease 2019 (COVID-19) pandemic has severely crippled the economy on a global scale. Effective and accurate forecasting models are essential for proper management and preparedness of the healthcare system and resources, eventually aiding in preventing the rapid spread of the disease. With the intention to provide better forecasting tools for the management of the pandemic, the current research work analyzes the effect of the inclusion of environmental parameters in the forecasting of daily COVID-19 cases. Three univariate variants of the long short-term memory (LSTM) model (basic/vanilla, stacked, and bi-directional) were employed for the prediction of daily cases in 9 cities across 3 countries with varying climatic zones (tropical, sub-tropical, and frigid), namely India (New Delhi and Nagpur), USA (Yuma and Los Angeles) and Sweden (Stockholm, Skane, Uppsala and Vastra Gotaland). The results were compared to a basic multivariate LSTM model with environmental parameters (temperature (T) and relative humidity (RH)) as additional inputs. Periods with no or minimal lockdown were chosen specifically in these cities to observe the uninhibited spread of COVID-19 and explore its dependence on daily environmental parameters. The multivariate LSTM model showed the best overall performance; the mean absolute percentage error (MAPE) showed an average of 64% improvement from other univariate models upon the inclusion of the above environmental parameters. Correlation with temperature was generally positive for the cold regions and negative for the warm regions. RH showed mixed correlations, most likely driven by its temperature dependence and effect of allied local factors. The results suggest that the inclusion of environmental parameters could significantly improve the performance of LSTMs for predicting daily cases of COVID-19, although other positive and negative confounding factors can affect the forecasting power.
ABSTRACT
The ongoing pandemic of coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in unprecedented disease burden, healthcare costs, and economic impacts worldwide. Despite several measures, SARS-CoV-2 has been extremely impactful due to its extraordinary infection potential mainly through coronavirus-borne saliva respiratory and droplet nuclei of an infected person and its considerable stability on surfaces. Although the disease has affected over 180 countries, its extent and control are significantly different across the globe, making it a strong case for exploration of its behavior and dependence across various environmental pathways and its interactions with the virus. This has spurred efforts to characterize the coronavirus and understand the factors impacting its transmission and survival such as aerosols, air quality, meteorology, chemical compositions and characteristics of particles and surfaces, which are directly or indirectly associated with coronaviruses infection spread. Nonetheless, many peer-reviewed articles have studied these aspects but mostly in isolation; a complete array of coronavirus survival and transmission from an infected individual through air- and water-borne channels and its subsequent intractions with environmental factors, surfaces, particulates and chemicals is not comprehensively explored. Particulate matter (PM) is omnipresent with variable concentrations, structures and composition, while most of the surfaces are also covered by PM of different characteristics. Learning from the earlier coronavirus studies, including SARS and MERS, an attempt has been made to understand the survival of SARS-CoV-2 outside of the host body and discuss the probable air and water-borne transmission routes and its interactions with the outside environment. The present work 1) Helps appreciate the role of PM, its chemical constituents and surface characteristics and 2) Further identifies gaps in this field and suggests possible domains to work upon for better understanding of transmission and survival of this novel coronavirus.