Forecasting daily new infections, deaths and recovery cases due to COVID-19 in Pakistan by using Bayesian Dynamic Linear Models

Time series forecasting of COVID-19 infections and deaths in Alpha and Delta variants using LSTM networks

Since the beginning of the rapidly spreading COVID-19 pandemic, several mutations have occurred in the genetic sequence of the virus, resulting in emerging different variants of concern. These variants vary in transmissibility, severity of infections, and mortality rate. Designing models that are capable of predicting the future behavior of these variants in the societies can help decision makers and the healthcare system to design efficient health policies, and to be prepared with the sufficient medical devices and an adequate number of personnel to fight against this virus and the similar ones. Among variants of COVID-19, Alpha and Delta variants differ noticeably in the virus structures. In this paper, we study these variants in the geographical regions with different size, population densities, and social life styles. These regions include the country of Iran, the continent of Asia, and the whole world. We propose four deep learning models based on Long Short-Term Memory (LSTM), and examine their predictive power in forecasting the number of infections and deaths for the next three, next five, and next seven days in each variant. These models include Encoder Decoder LSTM (ED-LSTM), Bidirectional LSTM (Bi-LSTM), Convolutional LSTM (Conv-LSTM), and Gated Recurrent Unit (GRU). Performance of these models in predictions are evaluated using the root mean square error, mean absolute error, and mean absolute percentage error. Then, the Friedman test is applied to find the leading model for predictions in all conditions. The results show that ED-LSTM is generally the leading model for predicting the number of infections and deaths for both variants of Alpha and Delta, with the ability to forecast long time intervals ahead.

Water availability and response of Tarbela Reservoir under the changing climate in the Upper Indus Basin, Pakistan

Agriculture is one of the major contributors to the Gross Domestic Product (GDP) of Pakistan which relies on the availability of water. Hydropower contributes approximately 35% to the national electricity gid of Pakistan. Indus River is the main river of the Indus River System (IRS) which provides water for agriculture, hydropower and other purposes. The outputs of the Conformal-Cubic Atmospheric Model (CCAM) are used to force the University of British Columbia Watershed Model (UBCWM) in the Upper Indus Basin (UIB), to investigate future water availability under the two IPCC emission scenarios (RCP4.5 and RCP8.5). Tarbela Reservoir which is the outlet of UIB is used as a measurement tool to assess water availability and response of the reservoir to climate change. The results show that maximum and minimum temperature are increasing in the future in comparison to the reference period. The largest increases in maximum temperature are projected for MAM (March–April–May) and JJA (June–July–August), with increases up to 2 °C in MAM and increases up to 6.4 °C in JJA under the RCP4.5 and RCP8.5, respectively, in the future. Minimum temperature has maximum increase (6.7 °C) in DJF (December–January–February) during 2071–2100 under RCP8.5. Precipitation shows a 5.1% decrease in DJF during 2011–2040 under RCP4.5. The statistics about water availability suggest that there is consistent increase in most of the months in the future, however, under the RCP4.5, there is decline in the river flow during 2071–2100 as compared to the 2041–2070. The findings of this study show that most of the time there will be more water available but in some months, there may be water scarcity under the RCP4.5, however, proper management and optimal utilization can reduce the water scarcity.

Fractional Stochastic Differential Equation Approach for Spreading of Diseases

The nonlinear fractional stochastic differential equation approach with Hurst parameter H within interval H∈(0,1) to study the time evolution of the number of those infected by the coronavirus in countries where the number of cases is large as Brazil is studied. The rises and falls of novel cases daily or the fluctuations in the official data are treated as a random term in the stochastic differential equation for the fractional Brownian motion. The projection of novel cases in the future is treated as quadratic mean deviation in the official data of novel cases daily since the beginning of the pandemic up to the present. Moreover, the rescaled range analysis (RS) is employed to determine the Hurst index for the time series of novel cases and some statistical tests are performed with the aim to determine the shape of the probability density of novel cases in the future.

Prediction of COVID-19 Pandemic in Bangladesh: Dual Application of Susceptible-Infective-Recovered (SIR) and Machine Learning Approach

The outbreak of COVID-19 is a global problem today, and, to reduce infectious cases and increase recovered cases, it is relevant to estimate the future movement and pattern of the disease. To identify the hotspot for COVID-19 in Bangladesh, we performed a cluster analysis based on the hierarchical k-means approach. A well-known epidemiological model named "susceptible-infectious-recovered (SIR)" and an additive regression model named "Facebook PROPHET Procedure" were used to predict the future direction of COVID-19 using data from IEDCR. Here we compare the results of the optimized SIR model and a well-known machine learning algorithm (PROPHET algorithm) for the forecasting trend of the COVID-19 pandemic. The result of the cluster analysis demonstrates that Dhaka city is now a hotspot for the COVID-19 pandemic. The basic reproduction ratio value was 2.1, which indicates that the infection rate would be greater than the recovery rate. In terms of the SIR model, the result showed that the virus might be slightly under control only after August 2022. Furthermore, the PROPHET algorithm observed an altered result from SIR, implying that all confirmed, death, and recovered cases in Bangladesh are increasing on a daily basis. As a result, it appears that the PROPHET algorithm is appropriate for pandemic data with a growing trend. Based on the findings, the study recommended that the pandemic is not under control and ensured that if Bangladesh continues the current pattern of infectious rate, the spread of the pandemic in Bangladesh next year will increase.

eHealth Engagement on Facebook during COVID-19: Simplistic Computational Data Analysis

Understanding social media networks and group interactions is crucial to the advancement of linguistic and cultural behavior. This includes how people accessed advice on health during COVID-19 lockdown. Some people turned to social media to access information on health when other routes were curtailed by isolation rules, particularly among older generations. Facebook public pages, groups and verified profiles using keywords “senior citizen health”, “older generations”, and “healthy living” were analyzed over a 12-month period to examine engagement with social media promoting good mental health. CrowdTangle was used to source status updates, photo and video sharing information in the English language, which resulted in an initial 116,321 posts and 6,462,065 interactions. Data analysis and visualization were used to explore large datasets, including natural language processing for “message” content discovery, word frequency and correlational analysis as well as co-word clustering. Preliminary results indicate strong links to healthy aging information shared on social media, which showed correlations to global daily confirmed cases and daily deaths. The results can identify public concerns early on and address mental health issues among senior citizens on Facebook.

A Novel βSA Ensemble Model for Forecasting the Number of Confirmed COVID-19 Cases in the US

In December 2019, Severe Special Infectious Pneumonia (SARS-CoV-2)–the novel coronavirus (COVID-19)– appeared for the first time, breaking out in Wuhan, China, and the epidemic spread quickly to the world in a very short period time. According to WHO data, ten million people have been infected, and more than one million people have died; moreover, the economy has also been severely hit. In an outbreak of an epidemic, people are concerned about the final number of infections. Therefore, effectively predicting the number of confirmed cases in the future can provide a reference for decision-makers to make decisions and avoid the spread of deadly epidemics. In recent years, the α-Sutte indicator method is an excellent predictor in short-term forecasting; however, the α-Sutte indicator uses fixed static weights. In this study, by adding an error-based dynamic weighting method, a novel β-Sutte indicator is proposed. Combined with ARIMA as an ensemble model (βSA), the forecasting of the future COVID-19 daily cumulative number of cases and the number of new cases in the US are evaluated from the experiment. The experimental results show that the forecasting accuracy of βSA proposed in this study is better than other methods in forecasting with metrics MAPE and RMSE. It proves the feasibility of adding error-based dynamic weights in the β-Sutte indicator in the area of forecasting.

Forecasting COVID-19 infections in the Arabian Gulf region

In this paper, an empirical analysis of linear state space models and long short-term memory neural networks is performed to compare the statistical performance of these models in predicting the spread of COVID-19 infections. Data on the pandemic daily infections from the Arabian Gulf countries from 2020/03/24 to 2021/05/20 are fitted to each model and a statistical analysis is conducted to assess their short-term prediction accuracy. The results show that state space model predictions are more accurate with notably smaller root mean square errors than the deep learning forecasting method. The results also indicate that the poorer forecast performance of long short-term memory neural networks occurs in particular when health surveillance data are characterized by high fluctuations of the daily infection records and frequent occurrences of abrupt changes. One important result of this study is the possible relationship between data complexity and forecast accuracy with different models as suggested in the entropy analysis. It is concluded that state space models perform better than long short-term memory networks with highly irregular and more complex surveillance data.

Short-term forecasting of daily infections, fatalities and recoveries about COVID-19 in Algeria using statistical models

Background

A viral disease due to a virus called SARS-Cov-2 spreads globally with a total of 34,627,141 infected people and 1,029,815 deaths. Algeria is an African country where 51,690, 1,741 and 36,282 are currently reported as infected, dead and recovered. A multivariate time series model has been used to model these variables and forecast their future scenarios for the next 20 days.

Results

The results show that there will be a minimum of 63 and a maximum of 147 new infections in the next 20 days with their corresponding 95% confidence intervals of − 89 to 214 and 108–186, respectively. Deaths’ forecast shows that there will be 8 and 12 minimum and maximum numbers of deaths in the upcoming 20 days with their 95% confidence intervals of 1–17 and 4–20, respectively. Minimum and maximum numbers of recovered cases will be 40 and 142 with their corresponding 95% confidence intervals of − 106 to 185 and 44–239, respectively. The total number of infections, fatalities and recoveries in the next 20 days will be 1850, 186 and 1680, respectively.

Conclusion

The results of this study suggest that the new infections are higher in number than recover cases, and therefore, the number of infected people may increase in future. This study can provide valuable information for policy makers including health and education departments.