key: cord-333162-gwmvsoru authors: Malki, Zohair; Atlam, El-Sayed; Hassanien, Aboul Ella; Dagnew, Guesh; Elhosseini, Mostafa A.; Gad, Ibrahim title: Association between Weather Data and COVID-19 Pandemic Predicting Mortality Rate: Machine Learning Approaches date: 2020-07-17 journal: Chaos Solitons Fractals DOI: 10.1016/j.chaos.2020.110137 sha: doc_id: 333162 cord_uid: gwmvsoru Nowadays, a significant number of infectious diseases such as human coronavirus disease (COVID-19) are threatening the world by spreading at an alarming rate. Some of the literatures pointed out that the pandemic is exhibiting seasonal patterns in its spread, incidence and nature of the distribution. In connection to the spread and distribution of the infection, scientific analysis that answers the questions whether the next summer can save people from COVID-19 is required. Many researchers have been exclusively asked whether high temperature during summer can slow down the spread of the COVID-19 as it has with other seasonal flues. Since there are a lot of questions that are unanswered right now, and many mysteries aspects about the COVID-19 that is still unknown to us, in-depth study and analysis of associated weather features are required. Moreover, understanding the nature of COVID-19 and forecasting the spread of COVID-19 request more investigation of the real effect of weather variables on the transmission of the COVID-19 among people. In this work, various regressor machine learning models are proposed to extract the relationship between different factors and the spreading rate of COVID-19. The machine learning algorithms employed in this work estimate the impact of weather variables such as temperature and humidity on the transmission of COVID-19 by extracting the relationship between the number of confirmed cases and the weather variables on certain regions. To validate the proposed method, we have collected the required datasets related to weather and census features and necessary prepossessing is carried out. From the experimental results, it is shown that the weather variables are more relevant in predicting the mortality rate when compared to the other census variables such as population, age, and urbanization. Thus, from this result, we can conclude that temperature and humidity are important features for predicting COVID-19 mortality rate. Moreover, it is indicated that the higher the value of temperature the lower number of infection cases. cently, researchers found that a notable association be- 22 tween the weather variables (temperature and humidity) 23 and the regions that have major COVID-19 outbreaks. 24 Moreover, these regions are located at the same temper-25 ature zone in the northern hemisphere [4] . 26 Even though the pandemic is becoming a global is-27 sue, the most infected areas include outbreak epicentres 28 such as parts of Northeastern United States, Chinas cen-29 tral province of Hubei, South Korea, Japan, Iran, Italy, 30 Spain, Germany, and England, all of which share an av-31 erage temperature of 5C to 11C and 47% to 79% hu-32 midity in January and February 2020. For Italy, regions 33 with a temperature higher than 15 degrees Celsius and 34 75% humidity have less spread of COVID-19 cases. 35 Therefore, we hypothesise that the spread of the virus 36 will decrease in the area with higher temperature and 37 humidity than areas with average records. From our ex- Melin et al. [6] conducted a study to analyze the 73 spatial evolution of coronavirus pandemic around the 74 world using unsupervised neural network namely self-75 organizing maps. The researchers concluded that the 76 clustering abilities of self-organizing maps enable to 77 group countries based on COVID-19 confirmed cases. The main contribution of our work includes: • Find the best predictive model for daily confirmed to regions that are below this threshold (see Figure 6 ). Based on the experimental results as shown in Table 379 2, we have proved that climatic conditions such as tem- Table 3 . These models help to un- in Table 1 . Clinical 537 features of patients infected with 2019 novel coronavirus 538 in wuhan, china Potential for global spread of a novel coron-544 avirus from china Geographic information systems and COVID-548 19: The johns hopkins university dashboard Temperature and latitude 554 analysis to predict potential spread and seasonality for COVID-555 19 COVID-19 spreading in rio de janeiro, brazil: 559 do the policies of social isolation really work? Anal-564 ysis of spatial spread relationships of coronavirus 565 (COVID-19) pandemic in the world using self organiz-566 ing maps Temperature, population and longitu-571 dinal analysis to predict potential spread for COVID-19 Temperature de-575 creases spread parameters of the new covid-19 case dynamics Demystifying a hidden trend: Do tempera-579 ture variations affect COVID-19 virus spread? SEIRA 607 model for the spread of COVID-19 among heterogeneous 608 populations On a 613 comprehensive model of the novel coronavirus (COVID-19) 614 under mittag-leffler derivative Real-time forecasts and risk assess-619 ment of novel coronavirus (COVID-19) cases: A data-driven 620 analysis A 624 model based study on the dynamics of COVID-19: Prediction 625 and control Multiple ensem-630 ble neural network models with fuzzy response aggregation for 631 predicting COVID-19 time series: The case of mexico, Health-632 care covid-19 jhu data web scrap and cleaning Funda-650 mentals of Machine Learning Introduction to scikit-learn Ehsanes Saleh, Mohammad Arashi, In-660 troduction to ridge regression Introduction to ensemble learn-665 ing Predicting hard rock pil-669 lar stability using GBDT, XGBoost, and LightGBM algorithms Short-term weather 673 forecast based on wavelet denoising and catboost Chinese Control Conference (CCC) A comparative study of prediction 679 and classification models on NCDC weather data, Inter-680 national Getting started with scikit-learn for machine learn-685 ing Decision tree classifier: a detailed sur-689 Review of ordinary least 696 squares and generalized least squares Credit Author Statement Zohair Malki: Supervision and Project administration Guesh Dagnew: Data curation, Writing-Original draft preparation