Forecasting Covid-19 Transmission with ARIMA and LSTM Techniques in Morocco.

In this paper, we are interested to forecast and predict the time evolution of the Covid-19 in Morocco based on two different time series forecasting models. We used Auto-Regressive Integrated Moving Average (ARIMA) and Long short-term memory (LSTM) models to predict the outbreak of Covid-19 in the upcoming 2 months in Morocco. In this work, we measured the effective reproduction number using the real data and also the fitted forecasted data produced by the two used approaches, to reveal how effective the measures taken by the Moroccan government have been controlling the Covid-19 outbreak.

Relaxation dynamics in congested traffic.

We investigate the relaxation dynamics in congested traffic when starting from the "megajam" initial condition (all cars standing in one big cluster of density 1) in the framework of the traffic model proposed by Nagel and Schreckenberg. On the one hand, a simple comparison of the time evolutions of some relevant traffic quantities shows that the slowest relaxing quantity is the density of "go and stop" cars rather than the average velocity of cars. On the other hand, we find that the relaxation time diverges in the form of a power law tau approximately tau(0) p(-beta) .

Car accidents in cellular automata models for one-lane traffic flow.

Conditions for the occurrence of car accidents are introduced in the Nagel-Schreckenberg model. These conditions are based on the thought that a real accident depends on several parameters: an unexpected action of the car ahead (sudden stop or abrupt deceleration), the gap between the two cars, the velocity of the successor car and its delayed reaction time. We discuss then the effect of this delayed reaction time on the probability of traffic accidents.