Forecasting Brazilian and American COVID-19 cases based on artificial intelligence coupled with climatic exogenous variables

Abstract The novel coronavirus disease (COVID-19) is a public health problem once according to the World Health Organization up to June 24th, 2020, more than 9.1 million people were infected, and more than 470 thousand have died worldwide. In the current scenario, the Brazil and the United States of America present a high daily incidence of new cases and deaths. Therefore, it is important to forecast the number of new cases in a time window of one week, once this can help the public health system developing strategic planning to deals with the COVID-19. The application of the forecasting artificial intelligence (AI) models has the potential of deal with dynamical behavior of time-series like of COVID-19. In this paper, Bayesian regression neural network, cubist regression, k-nearest neighbors, quantile random forest, and support vector regression, are used stand-alone, and coupled with the recent pre-processing variational mode decomposition (VMD) employed to decompose the time series into several intrinsic mode functions. All AI techniques are evaluated in the task of time-series forecasting with one, three, and six-days-ahead the cumulative COVID-19 cases in five Brazilian and American states, with a high number of cases up to April 28th, 2020. Previous cumulative COVID-19 cases and exogenous variables as daily temperature and precipitation were employed as inputs for all forecasting models. The models’ effectiveness are evaluated based on the performance criteria. In general, the hybridization of VMD outperformed single forecasting models regarding the accuracy, specifically when the horizon is six-days-ahead, the hybrid VMD–single models achieved better accuracy in 70% of the cases. Regarding the exogenous variables, the importance ranking as predictor variables is, from the upper to the lower, past cases, temperature, and precipitation. Therefore, due to the efficiency of evaluated models to forecasting cumulative COVID-19 cases up to six-days-ahead, the adopted models can be recommended as a promising models for forecasting and be used to assist in the development of public policies to mitigate the effects of COVID-19 outbreak.

[1]  Lin Wang,et al.  Predicting turning point, duration and attack rate of COVID-19 outbreaks in major Western countries , 2020, Chaos, Solitons & Fractals.

[2]  Marcos Felipe Falcão Sobral,et al.  Association between climate variables and global transmission oF SARS-CoV-2 , 2020, Science of The Total Environment.

[3]  Viviana Cocco Mariani,et al.  Multi-step wind speed forecasting based on hybrid multi-stage decomposition model and long short-term memory neural network , 2020, Energy Conversion and Management.

[4]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[5]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[6]  Mario Coccia,et al.  Factors determining the diffusion of COVID-19 and suggested strategy to prevent future accelerated viral infectivity similar to COVID , 2020, Science of The Total Environment.

[7]  Jinchao Li,et al.  Monthly crude oil spot price forecasting using variational mode decomposition , 2019, Energy Economics.

[8]  Viviana Cocco Mariani,et al.  Forecasting Epidemiological Time Series Based on Decomposition and Optimization Approaches , 2020, Anais do 14. Congresso Brasileiro de Inteligência Computacional.

[9]  Leandro dos Santos Coelho,et al.  Short-term forecasting COVID-19 cumulative confirmed cases: Perspectives for Brazil , 2020, Chaos, Solitons & Fractals.

[10]  Manish Bansal,et al.  Cardiovascular disease and COVID-19 , 2020, Diabetes & Metabolic Syndrome: Clinical Research & Reviews.

[11]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[12]  Dominique Zosso,et al.  Variational Mode Decomposition , 2014, IEEE Transactions on Signal Processing.

[13]  Jungang Luo,et al.  Decomposition ensemble model based on variational mode decomposition and long short-term memory for streamflow forecasting , 2020 .

[14]  Senén Barro,et al.  An extensive experimental survey of regression methods , 2019, Neural Networks.

[15]  Wei Liu,et al.  Impact of temperature on the dynamics of the COVID-19 outbreak in China , 2020, Science of The Total Environment.

[16]  D. Kibler,et al.  Instance-based learning algorithms , 2004, Machine Learning.

[17]  G. D. Barmparis,et al.  Estimating the infection horizon of COVID-19 in eight countries with a data-driven approach , 2020, Chaos, Solitons & Fractals.

[18]  Qunli Wu,et al.  Daily urban air quality index forecasting based on variational mode decomposition, sample entropy and LSTM neural network , 2019, Sustainable Cities and Society.

[19]  W. Ko,et al.  Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and coronavirus disease-2019 (COVID-19): The epidemic and the challenges , 2020, International Journal of Antimicrobial Agents.

[20]  Ahmed M. Abbas,et al.  The mutual effects of COVID-19 and obesity , 2020, Obesity Medicine.

[21]  Gilberto Reynoso-Meza,et al.  Multi-objective Support Vector Machines Ensemble Generation for Water Quality Monitoring , 2018, 2018 IEEE Congress on Evolutionary Computation (CEC).

[22]  H. Kourie,et al.  Cancer patients and research during COVID-19 pandemic: A systematic review of current evidence , 2020, Critical Reviews in Oncology/Hematology.

[23]  Sarbjit Singh,et al.  Development of new hybrid model of discrete wavelet decomposition and autoregressive integrated moving average (ARIMA) models in application to one month forecast the casualties cases of COVID-19 , 2020, Chaos, Solitons & Fractals.

[24]  Scott Chamberlain,et al.  'NOAA' Weather Data from R , 2016 .

[25]  Claudio José Struchiner,et al.  Risk of the Brazilian health care system over 5572 municipalities to exceed health care capacity due to the 2019 novel coronavirus (COVID-19) , 2020, Science of The Total Environment.

[26]  K. Yuen,et al.  Clinical Characteristics of Coronavirus Disease 2019 in China , 2020, The New England journal of medicine.

[27]  Vinay Kumar Reddy Chimmula,et al.  Time series forecasting of COVID-19 transmission in Canada using LSTM networks , 2020, Chaos, Solitons & Fractals.

[28]  Muhammad Farhan Bashir,et al.  Correlation between climate indicators and COVID-19 pandemic in New York, USA , 2020, Science of The Total Environment.

[29]  Ivan Cruz,et al.  Ministério da Agricultura, Pecuária e Abastecimento Centro Nacional de Pesquisa de Milho e S orgo , 2009 .

[30]  Jue Liu,et al.  Effects of temperature and humidity on the daily new cases and new deaths of COVID-19 in 166 countries , 2020, Science of The Total Environment.

[31]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[32]  Akhtar Hussain,et al.  COVID-19 and diabetes: Knowledge in progress , 2020, Diabetes Research and Clinical Practice.

[33]  Zeynep Ceylan.  Estimation of COVID-19 prevalence in Italy, Spain, and France , 2020, Science of The Total Environment.

[34]  Leandro dos Santos Coelho,et al.  Ensemble approach based on bagging, boosting and stacking for short-term prediction in agribusiness time series , 2020, Appl. Soft Comput..

[35]  David N. Prata,et al.  Temperature significantly changes COVID-19 transmission in (sub)tropical cities of Brazil , 2020, Science of The Total Environment.

[36]  Mohsen Ahmadi,et al.  Investigation of effective climatology parameters on COVID-19 outbreak in Iran , 2020, Science of The Total Environment.

[37]  Philippe Lagacherie,et al.  Using quantile regression forest to estimate uncertainty of digital soil mapping products , 2017 .

[38]  Cheng Wan,et al.  Renal histopathological analysis of 26 postmortem findings of patients with COVID-19 in China , 2020, Kidney International.

[39]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[40]  T. Chakraborty,et al.  Real-time forecasts and risk assessment of novel coronavirus (COVID-19) cases: A data-driven analysis , 2020, Chaos, Solitons & Fractals.

[41]  A. Ahmar,et al.  SutteARIMA: Short-term forecasting method, a case: Covid-19 and stock market in Spain , 2020, Science of The Total Environment.

[42]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[43]  Nicolai Meinshausen,et al.  Quantile Regression Forests , 2006, J. Mach. Learn. Res..

[44]  Fan Zhang,et al.  A hybrid VMD-BiGRU model for rubber futures time series forecasting , 2019, Appl. Soft Comput..

[45]  Delfim F. M. Torres,et al.  Mathematical modeling of COVID-19 transmission dynamics with a case study of Wuhan , 2020, Chaos, Solitons & Fractals.

[46]  F. Cássaro,et al.  Evidence that high temperatures and intermediate relative humidity might favor the spread of COVID-19 in tropical climate: A case study for the most affected Brazilian cities , 2020, Science of The Total Environment.