A Prediction Model for Spot LNG Prices Based on Machine Learning Algorithms to Reduce Fluctuation Risks in Purchasing Prices

The ongoing Russia–Ukraine conflict has exacerbated the global crisis of natural gas supply, particularly in Europe. During the winter season, major importers of liquefied natural gas (LNG), such as South Korea and Japan, were directly affected by fluctuating spot LNG prices. This study aimed to use machine learning (ML) to predict the Japan Korea Marker (JKM), a spot LNG price index, to reduce price fluctuation risks for LNG importers such as the Korean Gas Corporation (KOGAS). Hence, price prediction models were developed based on long short-term memory (LSTM), artificial neural network (ANN), and support vector machine (SVM) algorithms, which were used for time series data prediction. Eighty-seven variables were collected for JKM prediction, of which eight were selected for modeling. Four scenarios (scenarios A, B, C, and D) were devised and tested to analyze the effect of each variable on the performance of the models. Among the eight variables, JKM, national balancing point (NBP), and Brent price indexes demonstrated the largest effects on the performance of the ML models. In contrast, the variable of LNG import volume in China had the least effect. The LSTM model showed a mean absolute error (MAE) of 0.195, making it the best-performing algorithm. However, the LSTM model demonstrated a decreased in performance of at least 57% during the COVID-19 period, which raises concerns regarding the reliability of the test results obtained during that time. The study compared the ML models' prediction performances with those of the traditional statistical model, autoregressive integrated moving averages (ARIMA), to verify their effectiveness. The comparison results showed that the LSTM model's performance deviated by an MAE of 15–22%, which can be attributed to the constraints of the small dataset size and conceptual structural differences between the ML and ARIMA models. However, if a sufficiently large dataset can be secured for training, the ML model is expected to perform better than the ARIMA. Additionally, separate tests were conducted to predict the trends of JKM fluctuations and comprehensively validate the practicality of the ML models. Based on the test results, LSTM model, identified as the optimal ML algorithm, achieved a performance of 53% during the regular period and 57% d during the abnormal period (i.e., COVID-19). Subject matter experts agreed that the performance of the ML models could be improved through additional studies, ultimately reducing the risk of price fluctuations when purchasing spot LNG. [ FROM AUTHOR] Copyright of Energies (19961073) is the property of MDPI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Novel Method for Estimating Time-Varying COVID-19 Transmission Rate

The transmission rate is an important indicator for characterizing a virus and estimating the risk of its outbreak in a certain area, but it is hard to measure. COVID-19, for instance, has greatly affected the world for more than 3 years since early 2020, but scholars have not yet found an effective method to obtain its timely transmission rate due to the fact that the value of COVID-19 transmission rate is not constant but dynamic, always changing over time and places. Therefore, in order to estimate the timely dynamic transmission rate of COVID-19, we performed the following: first, we utilized a rolling time series to construct a time-varying transmission rate model and, based on the model, managed to obtain the dynamic value of COVID-19 transmission rate in mainland China;second, to verify the result, we used the obtained COVID-19 transmission rate as the explanatory variable to conduct empirical research on the impact of the COVID-19 pandemic on China's stock markets. Eventually, the result revealed that the COVID-19 transmission rate had a significant negative impact on China's stock markets, which, to some extent, confirms the validity of the used measurement method in this paper. Notably, the model constructed in this paper, combined with local conditions, can not only be used to estimate the COVID-19 transmission rate in mainland China but also in other affected countries or regions and would be applicable to calculate the transmission rate of other pathogens, not limited to COVID-19, which coincidently fills the gaps in the research. Furthermore, the research based on this model might play a part in regulating anti-pandemic governmental policies and could also help investors and stakeholders to make decisions in a pandemic setting.

Concept Drift Adaptation Methods under the Deep Learning Framework: A Literature Review

With the advent of the fourth industrial revolution, data-driven decision making has also become an integral part of decision making. At the same time, deep learning is one of the core technologies of the fourth industrial revolution that have become vital in decision making. However, in the era of epidemics and big data, the volume of data has increased dramatically while the sources have become progressively more complex, making data distribution highly susceptible to change. These situations can easily lead to concept drift, which directly affects the effectiveness of prediction models. How to cope with such complex situations and make timely and accurate decisions from multiple perspectives is a challenging research issue. To address this challenge, we summarize concept drift adaptation methods under the deep learning framework, which is beneficial to help decision makers make better decisions and analyze the causes of concept drift. First, we provide an overall introduction to concept drift, including the definition, causes, types, and process of concept drift adaptation methods under the deep learning framework. Second, we summarize concept drift adaptation methods in terms of discriminative learning, generative learning, hybrid learning, and others. For each aspect, we elaborate on the update modes, detection modes, and adaptation drift types of concept drift adaptation methods. In addition, we briefly describe the characteristics and application fields of deep learning algorithms using concept drift adaptation methods. Finally, we summarize common datasets and evaluation metrics and present future directions.

An Improved Granulated Convolutional Neural Network Data Analysis Model for COVID-19 Prediction

As COVID-19 poses a major threat to people's health and economy, there is an urgent need for forecasting methodologies that can anticipate its trajectory efficiently. In non-stationary time series forecasting jobs, there is frequently a hysteresis in the anticipated values relative to the real values. The multilayer deep-time convolutional network and a feature fusion network are combined in this paper's proposal of an enhanced Multilayer Deep Time Convolutional Neural Network (MDTCNet) for COVID-19 prediction to address this problem. In particular, it is possible to record the deep features and temporal dependencies in uncertain time series, and the features may then be combined using a feature fusion network and a multilayer perceptron. Last but not least, the experimental verification is conducted on the prediction task of COVID-19 real daily confirmed cases in the world and the United States with uncertainty, realizing the short-term and long-term prediction of COVID-19 daily confirmed cases, and verifying the effectiveness and accuracy of the suggested prediction method, as well as reducing the hysteresis of the prediction results.

Demand Forecasting in SCM for Automobile Industry based on Time-series Modeling

In supply chain management (SCM), product classification and demand forecasting are crucial pillars to ensure companies to have production in the right category and quantity for long-term profitability. Due to COVID-19 from 2019, the automobile industry has been seriously negatively affected as the demand dropped dramatically. Therefore, it is necessary to make reasonable product classification and accurate demand forecasting to facilitate automobile companies in SCM to reduce unpopular product manufacture and unnecessary storage costs. In this paper, the Canada automobile market has been chosen with the period from 1946 to 2022. To classify a number of different types of motor vehicles into several categories with general characteristics, K-means Clustering method is applied. With the seasonal patterns and random generated features for auto sales, the time series models ARIMA and SARIMA are adopted for demand forecasting. According to the analysis, the automobiles fitting in the category with high demand and low price are valuable for further production. In addition, SARIMA Model is more accurate and fits better than ARIMA Model for both the training and test datasets for long-term prediction. The classification and forecasting results shed light on guiding manufacturers to adjust production schemes and ensuring auto dealers to predict more accurate sales in order to optimize the strategic planning. © 2023 SPIE.

Studying the impact of COVID-19 on the European Air Transportation Network

The European Air Transportation Network was significantly impacted by the COVID-19 pandemic, resulting in an unprecedented loss of flight connections. Utilizing a combination of graph representation learning and time series analysis, this paper studies the evolution of both the global connectivity as well as the structure of the European Air Transportation Network from January 2020 to December 2022. Specifically, it finds strong differences in recovery rates for flights across six different market segments. In terms of network structure, the study finds that structural roles that are present in the pre-covid network have seen a loss in performance over the course of the pandemic, but have recovered to pre-covid levels. Using regional changes in structural roles, this study identifies Italy as the region with the strongest increase and the United Kingdom as the region with the strongest decrease in structural role, finding substantial differences in recovery rates per market segment. Lastly, this study pays special attention on the effect of the Russia-Ukrainian war on the European Air Transportation Network. © 2023 IEEE.

Impact of the COVID-19 Pandemic on Cervical Cancer Screening Rates in Colombia: An Interrupted Time Series Analysis, Stratified By Region

Objectives: The objective of this study is to measure the national impact of COVID-19 on cervical cancer screening rates in Colombia in five of its geographic regions to inform future health policy decision making. Method(s): This study utilized a quasi-experimental interrupted time-series design to examine changes in trends for the number of cervical cancer screenings performed in five geographic regions of Colombia. Result(s): In the rural region of Vichada, we found the lowest incidence of cervical cancer screenings, totaling at 3,771 screenings. In Cundinamarca, the region which hosts the capital city, a total of 1,213,048 cervical cancer screenings were performed. The researcher measured the impact on cervical cancer screenings in December 2021 against the counterfactual. This impact was ~269 cases that were not performed in December 2021 as a result of the COVID-19 pandemic compared to the counterfactual. In Cundinamarca, unlike other regions, we observed a stagnant pre-pandemic trend, a sharp drop in screenings in March 2020, and an immediate upward trend starting in April 2020. In the month of April 2020, compared to the counterfactual, there were 27,359 screenings missed, and by the month of December 2021, there were only 5,633 cervical cancer screenings missed. Conclusion(s): The region of Cundinamarca's sharp climb back to pre-pandemic screening levels could signal the relatively stronger communication system in the region, and especially in the capital district of Bogota, in re-activating the economy. This can serve as an example of what should be implemented in other regions to improve cervical cancer screening rates. Areas for further research include the examination of social determinants of health, such as the breakdown of the type of insurance screened patients hold (public versus private), zone (urban versus rural), insurance providers of those screened, ethnicities of the patients screened, and percentage of screenings that resulted in early detection of cervical cancer.Copyright © 2023

CRYSTAL: A novel and effective method to remove clouds in daily nighttime light images by synergizing spatiotemporal information

Satellite nighttime light (NTL) images offer a valuable depiction of the rapidly changing world by revealing the presence of artificial illumination. Thus, daily NTL images are increasingly applied to monitor human dynamics and environmental events. However, data gaps caused by cloud contamination and low-quality observations inevitably impair the effectiveness of such applications. Although a temporal gap-filling method is employed in recent Black Marble NTL products to produce seamless images, the filled images are unsuitable for quantitative analysis. Therefore, we developed an effective method, named as Cloud Removing bY Synergizing spatio-TemporAL information (CRYSTAL), to generate cloud-free NTL images with satisfactorily accurate pixel brightness and spatial continuity. Simulation experiments show that CRYSTAL can produce more accurate results than the temporal gap-filling method in fifteen cities worldwide, with an average RMSE reduction of 33.69%. Images generated by CRYSTAL restore temporal variances in NTL and are thus suitable for multi-temporal quantitative analysis. CRYSTAL can reconstruct daily NTL time series by filling gaps using available partially clear images. Experiments in two cities demonstrated that the reconstructed time series had 31.85% more valid values than the original time series and effectively revealed urban dynamics during the early stages of the coronavirus disease 2019 pandemic. In summary, CRYSTAL is a novel and effective gap-filling method for the restoration of invalid NTL observations and has the potential to generate high-quality NTL data for use in future applications.

IMPACT OF THE COVID-19 PANDEMIC ON ADHERENCE TO DISEASE MODIFYING DRUGS AMONG PATIENTS WITH RHEUMATIC DISEASES: A POPULATION-BASED, INTERRUPTED TIME SERIES ANALYSIS

BackgroundAlthough studies have quantified adherence to medications among patients with rheumatic diseases (RD) during the COVID-19, lack of direct pre-pandemic comparison precludes understanding of impact of the pandemic.ObjectivesOur objective was to evaluate the effect of the COVID-19 pandemic on adherence to disease modifying drugs (DMARDs) including conventional synthetic (csDMARDs) and targeted synthetic (tsDMARDs).MethodsWe linked population-based health data on all physician visits, hospital admissions, and all dispensed medications, regardless of payer in British Columbia from 01/01/1996 to 3/31/2021. We identified prescriptions for csDMARDs (including methotrexate, hydroxychloroquine) and tsDMARDs, namely anti-TNFs (including infliximab, etanercept, adalimumab) and rituximab using drug identification numbers among indicated individuals with RD. We defined March 11, 2020, as the ‘index date' which corresponded to the date that mitigation measures for the COVID-19 pandemic were first introduced. We assessed adherence as proportion days covered (PDC), calculated monthly in the 12 months before and 12 months after the index date. We used interrupted time-series models, namely segmented regression to estimate changes and trends in adherence before and after the index date.ResultsOur analysis showed that the mean PDCs for all included DMARDs stayed relatively steady in the 12 months before and after mitigation measures were introduced (see Table 1). Adherence was highest among anti-TNFs, methotrexate, and azathioprine. Anti-TNFs were on a downward trajectory 12 months prior to the index date. Interrupted time-series modeling demonstrated statistically significant differences in the trends in PDCs post- vs. pre-mitigation measures for all anti-TNFS (slope [∂]: 1.38, standard error [SE]: 0.23), infliximab (∂: 1.35, SE: 0.23), adalimumab (∂: 0.82, SE: 0.25), and etanercept (∂: 1.07, SE: 0.25) (see Figure 1a). Conversely, the csDMARDs were on a flatter trajectory, and methotrexate (∂: -0.53, SE: 0.16), leflunomide (∂: 0.43, SE: 0.08), mycophenolate (∂: -1.26, SE: 0.48), cyclophosphamide (∂: 0.29, SE: 0.05), minocycline (∂: 0.04, SE: 0.02), chloroquine (∂: 0.02, SE: 0.00) showed statistically significant changes in estimated PDC trajectory after mitigation measures were introduced (see Figure 1b).ConclusionThis population-based study demonstrates that messaging and pandemic mitigation measures did not affect adherence to DMARDs.Table 1.Mean PDC 1 year before and after mitigation measures for the COVID-19 pandemic were introduced.MedicationMean PDC (%) 12 months before index dateMean PDC (%) 12 months after index datecsDMARDsmethotrexate28.926.8azathioprine21.819.5sulfasalazine16.214.9leflunomide14.313.0cyclosporine13.711.5hydroxychloroquine10.59.6mycophenolate4.52.9antimalarials4.43.9penicillamine3.53.4cyclophosphamide1.50.7chlorambucil1.20.4minocycline1.10.9gold0.50.2chloroquine0.10.0tsDMARDsanti-TNFs52.149.2infliximab41.838.3adalimumab40.336.8etanercept31.828.9rituximab3.42.9REFERENCES:NIL.Acknowledgements:NIL.Disclosure of InterestsNone Declared.

Time series prediction of the COVID-19 outbreak in India using LSTM based deep learning models

The epidemic caused by COVID-19 presents a significant risk to the continuation of human civilisation and has already done irreparable damage to society. In this paper, forecasting of Coronavirus outbreak in India is performed by LSTM and CovnLSTM deep neural network techniques. COVID-19 data of confirmed cases of India is used. It was taken from John Hopkins University. The loss rate of ConvLSTM is lower than LSTM and RMSE of ConvLSTM is lower than LSTM. For training Covn-LSTM shows 0.069% and testing ConvLSTM shows 0.32% improvement over LSTM model. Therefore, ConvLSTM outperformed over LSTM model. Further wise selection of hyper-parameters could increase the accuracy of the models. © 2023 IEEE.

The effectiveness of Covid-19 vaccination: time series evidence from the UK

Some claims have been made that that Covid vaccination is effective against both infection and mortality, even though the WHO is seeking more evidence to determine how well vaccines stop infection and transmission. On the basis of UK daily data over the period 10 January 2021–6 January 2022, evidence is presented indicating that vaccination is not effective against infection but it is highly effective against mortality. This makes scientific sense because the function of vaccination is to stimulate the production of antibodies that fight off the virus, which does not imply the ability to stop infection.

Who's minding the children: Gender equity in the first 2 years of the pandemic

The wholesale changes brought about by the COVID‐19 pandemic to men and women's paid work arrangements and work–family balance provide a natural experiment for testing the common elements of two theories, needs exposure (Schafer et al. Canadian Review of Sociology/Revue Canadienne De Sociologie, 57(4);2020:523–549) and parental proximity (Sullivan et al. Family Theory & Review, 2018;10(1):263–279) against a third theory also suggested by Schafer et al. (2020), and labelled in this article, entrenchment/exacerbation of gender inequality. Both needs exposure and parental proximity suggest that by being home because of the pandemic, in proximity to their children, fathers are exposed to new and enduring family needs, which may move them toward more equal sharing in childcare and other domestic responsibilities. By contrast to studies that have tested such theories using retrospective, self‐report survey data over a 2‐year period, we analyse more than a decade of time‐use diary data from the American Time Use Survey (ATUS) that covers the first 2 years of the pandemic. We model the secular and quarterly trends to predict what would have occurred in the absence of the pandemic, contrasting this to what indeed happened. Our analyses consider aggregate and individual impacts, using methods of sequence analysis, clustering, and matching. Among our results, we find that the division of childcare responsibilities did not become more equitable during the pandemic. Suggestions for future research are provided as are suggestions for the implementation of social policies that could influence greater gender equity in unpaid work and childcare. [ FROM AUTHOR] Copyright of International Journal of Social Welfare is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Visualising the Optimistic, Realistic, and Pessimistic Financial Distress Outlooks for Airport Operations in Malaysia

This paper aims to visualise three financial distress outlooks using computer simulations. The financial distress exposure for airport operations in Malaysia between 1991 and 2021 is given by Altman Z”-score and modelled by the multivariate generalized linear model (MGLM). Seven determinants contributing to the financial distress from literature are examined. The determinant series are fitted individually by using linear model with time series components and autoregressive integrated moving average models to forecast values for the next 10 financial years. Future short- to long-term memory effects following COVID-19 are apparent in time series plots. In the simulations, the MGLM procedure utilised Gaussian, gamma, and Cauchy probability distributions associated with expectations and challenges of doing business as well as uncertainties in the economy. The underlying trends of realistic, optimistic, and pessimistic financial distress outlooks insinuate that the increasing risk of financial distress of airport operations in Malaysia is expected to continue for the next decade.

Integration of climate, transmission, and spread of dengue hemorrhagic fever in endemic areas

Introduction. Dengue Hemorrhagic Fever (DHF) is still a public health problem even in the era of the COVID-19 pandemic in 2020, including in Indonesia. This study aimed to analyze the incidence of DHF based on the integration of climatic factors, including rainfall, humidity, air temperature, and duration of sunlight and their distribution. Materials and Methods. This was an ecological time series study with secondary data from the Surabaya City Health Office covering the incidence of DHF and larva-free rate and climate data on rainfall, humidity, air temperature, and duration of sunlight obtained from the Meteorology and Geophysics Agency (BMKG). Silver station in Surabaya, the distribution of dengue incidence during 2018-2020. Results and Discussion. The results showed that humidity was correlated with the larvae-free rate. Meanwhile, the larva-free rate did not correlate with the number of DHF cases. DHF control is estimated due to the correlation of climatic factors and the incidence of DHF, control of vectors and disease agents, control of transmission media, and exposure to the community. Conclusions. The integration of DHF control can be used for early precautions in the era of the COVID-19 pandemic by control-ling DHF early in the period from January to June in Surabaya. It is concluded that humidity can affect the dengue outbreak and it can be used as an early warning system and travel warning regarding the relative risk of DHF outbreak.Copyright © the Author(s), 2023.

Forecasting COVID-19 Vaccination Rates using Social Media Data

The COVID-19 pandemic has had a profound impact on the global community, and vaccination has been recognized as a crucial intervention. To gain insight into public perceptions of COVID-19 vaccines, survey studies and the analysis of social media platforms have been conducted. However, existing methods lack consideration of individual vaccination intentions or status and the relationship between public perceptions and actual vaccine uptake. To address these limitations, this study proposes a text classification approach to identify tweets indicating a user's intent or status on vaccination. A comparative analysis between the proportions of tweets from different categories and real-world vaccination data reveals notable alignment, suggesting that tweets may serve as a precursor to actual vaccination status. Further, regression analysis and time series forecasting were performed to explore the potential of tweet data, demonstrating the significance of incorporating tweet data in predicting future vaccination status. Finally, clustering was applied to the tweet sets with positive and negative labels to gain insights into underlying focuses of each stance. © 2023 ACM.

Impact of COVID-19 Pandemic on Cultural Products Interests

The COVID-19 pandemic has had a significant impact on human behaviors and how it influenced peoples' interests in cultural products is an unsolved problem. While prior studies mostly adopt subjective surveys to find an answer, these methods are always suffering from high cost, limited size, and subjective bias. Inspired by the rich user-oriented data over the Internet, this work explores the possibility to leverage users' search logs to reflect humans' underlying cultural product interests. To further examine how the COVID-19 mobility policy might influence cultural interest changes, we propose a new regression discontinuity design that has the additional potential to predict the recovery phase of peoples' cultural product interests. By analyzing the 1592 search interest time series in 6 countries, we found different patterns of change in interest in movies, music, and art during the COVID-19 pandemic, but a clear overall incremental increase. Across the six countries we studied, we found that changes in interest in cultural products were found to be strongly correlated with mobility and that as mobility declined, interest in movies, music, and art increased by an average of 35, 27 and 20, respectively, with these changes lasting at least eight weeks. © 2023 ACM.

How do the sectoral indices react to COVID-19? Evidence from an emerging economy

The study empirically examines the impact of the COVID-19 on different sectoral indices of the National Stock Exchange (India) using the event study method and a generalised autoregressive conditional heteroskedasticity (GARCH) model. We provide evidence of positive impacts on the auto, oil and gas, healthcare, and pharma sectors. While the bank, financial services, and private bank sectors are the most adversely impacted sectors, the PSU bank, media, and reality sectors are the least impacted, and the rest are moderately impacted sectors. The overall impact of COVID-19 was negative until the implementation of nationwide lockdowns and the announcement of stimulus packages. The GARCH results exhibit more substantial evidence for the negative impact of the pandemic on the FMCG, IT, metal, oil and gas, and PSU bank sectors. We also find a more favourable impact on FMCG, pharma, and healthcare sectors in India.

Detecting COVID-19 spreading phases with time series analysis

Piecewise linear regression (PLR) method is applied to study cumulative cases of COVID-19 evolving everyday in England up to 6th February 2022 just before travel restrictions are removed and people started not to get tested anymore in the UK and factors e.g. the lockdowns behind the spread COVID-19 are also investigated. It is clear that different periods exhibit distinct patterns depending on variants and government-imposed restriction. Therefore, the effectiveness of lockdown measures is evaluated by comparing the rate of increase after a certain period (delay effect of measures) and that of time before as well as how new variants take over as a dominant variant. In addition, autoregression function is studied to show strong effect of cases in the past on today's cases since the disease is highly infectious. Most of work is carried out thorough python built-in libraries such as pandas for preprocessing data and matplotlib which allows us to gain more insight and better visualization into the real scenario. Visualization is conducted by Geoda showing the regional level of infections. © 2023 SPIE.

Forecasting Residential Energy Consumption: A Case Study for Greece

Residential energy consumption forecasting has immense value in energy efficiency and sustainability. In the current work we tried to forecast energy consumption on residences in Athens, Greece. As a proof of concept, smart sensors were installed into two residences that recorded energy consumption, as well as indoors environmental variables (humidity and temperature). It should be noted that the data set was collected during the COVID-19 pandemic. Moreover, we integrated weather data from a public weather site. A dashboard was designed to facilitate monitoring of the sensors' data. We addressed various issues related to data quality and then we tried different models to forecast daily energy consumption. In particular, LSTM neural networks, ARIMA, SARIMA, SARIMAX and Facebook (FB) Prophet were tested. Overall SARIMA and FB Prophet had the best performance. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

A COVID-19 Infection Prediction Model in Egypt Based on Deep Learning Using Population Mobility Reports

The rapidly spreading COVID-19 disease had already infected more than 190 countries. As a result of this scenario, nations everywhere monitored confirmed cases of infection, cures, and fatalities and made predictions about what the future would hold. In the event of a pandemic, governments had set limit rules for the spread of the virus and save lives. Multiple computer methods existed for forecasting epidemic time series. Deep learning was one of the most promising methods for time-series prediction. In this research, we propose a model for predicting the spread of COVID-19 in Egypt based on deep learning sequence-to-sequence regression, which makes use of data on the population mobility reports. The presented model utilized a new combined dataset from two different sources. The first source is Google population mobility reports, and the second source is the number of infected cases reported daily "world in data” website. The suggested model could predict new cases of COVID-19 infection within 3–7 days with the least amount of prediction error. The proposed model achieved 96.69% accuracy for 3 days of prediction. This study is noteworthy since it is one of the first trials to estimate the daily influx of new COVID-19 infections using population mobility data instead of daily infection rates. © 2023, The Author(s).